diff --git a/.env.example b/.env.example
index 681280f2..8d412670 100644
--- a/.env.example
+++ b/.env.example
@@ -1,60 +1,43 @@
 # Ingestion Configuration
-# Set to true to disable Langflow ingestion and use the traditional OpenRAG processor.
-# If unset or false, the Langflow pipeline is used (default: upload -> ingest -> delete).
+# Set to true to disable Langflow ingestion and use traditional OpenRAG processor
+# If unset or false, Langflow pipeline will be used (default: upload -> ingest -> delete)
 DISABLE_INGEST_WITH_LANGFLOW=false
-
-# Create a Langflow secret key:
-# https://docs.langflow.org/api-keys-and-authentication#langflow-secret-key
+# make one like so https://docs.langflow.org/api-keys-and-authentication#langflow-secret-key
 LANGFLOW_SECRET_KEY=
 
-
-# Flow IDs for chat and ingestion
+# flow ids for chat and ingestion flows
 LANGFLOW_CHAT_FLOW_ID=1098eea1-6649-4e1d-aed1-b77249fb8dd0
 LANGFLOW_INGEST_FLOW_ID=5488df7c-b93f-4f87-a446-b67028bc0813
-# Ingest flow using Docling
+LANGFLOW_URL_INGEST_FLOW_ID=72c3d17c-2dac-4a73-b48a-6518473d7830
+# Ingest flow using docling
 # LANGFLOW_INGEST_FLOW_ID=1402618b-e6d1-4ff2-9a11-d6ce71186915
 NUDGES_FLOW_ID=ebc01d31-1976-46ce-a385-b0240327226c
 
-
-# OpenSearch Auth
-# Set a strong admin password for OpenSearch.
-# A bcrypt hash is generated at container startup from this value.
-# Do not commit real secrets.
-# Must be changed for secure deployments.
+# Set a strong admin password for OpenSearch; a bcrypt hash is generated at
+# container startup from this value. Do not commit real secrets.
+# must match the hashed password in secureconfig, must change for secure deployment!!!
 OPENSEARCH_PASSWORD=
 
-
-# Google OAuth
-# Create credentials here:
-# https://console.cloud.google.com/apis/credentials
+# make here https://console.cloud.google.com/apis/credentials
 GOOGLE_OAUTH_CLIENT_ID=
 GOOGLE_OAUTH_CLIENT_SECRET=
 
-
-# Microsoft (SharePoint/OneDrive) OAuth
-# Azure app registration credentials.
+# Azure app registration credentials for SharePoint/OneDrive
 MICROSOFT_GRAPH_OAUTH_CLIENT_ID=
 MICROSOFT_GRAPH_OAUTH_CLIENT_SECRET=
 
-
-# Webhooks (optional)
-# Public, DNS-resolvable base URL (e.g., via ngrok) for continuous ingestion.
+# OPTIONAL: dns routable from google (etc.) to handle continous ingest (something like ngrok works). This enables continous ingestion
 WEBHOOK_BASE_URL=
 
-
-# API Keys
 OPENAI_API_KEY=
 
 AWS_ACCESS_KEY_ID=
 AWS_SECRET_ACCESS_KEY=
 
-
-# Langflow UI URL (optional)
-# Public URL to link OpenRAG to Langflow in the UI.
+# OPTIONAL url for openrag link to langflow in the UI
 LANGFLOW_PUBLIC_URL=
 
-
-# Langflow Auth
+# Langflow auth
 LANGFLOW_AUTO_LOGIN=False
 LANGFLOW_SUPERUSER=
 LANGFLOW_SUPERUSER_PASSWORD=
diff --git a/.gitignore b/.gitignore
index 970b5bec..9c99e617 100644
--- a/.gitignore
+++ b/.gitignore
@@ -17,6 +17,7 @@ wheels/
 
 1001*.pdf
 *.json
+!flows/*.json
 .DS_Store
 
 config/
diff --git a/Dockerfile.langflow b/Dockerfile.langflow
index 86ee0ea5..71baf447 100644
--- a/Dockerfile.langflow
+++ b/Dockerfile.langflow
@@ -1,49 +1,5 @@
-FROM python:3.12-slim
+FROM langflowai/langflow-nightly:1.6.3.dev0
 
-# Set environment variables
-ENV DEBIAN_FRONTEND=noninteractive
-ENV PYTHONUNBUFFERED=1
-ENV RUSTFLAGS="--cfg reqwest_unstable"
-
-# Accept build arguments for git repository and branch
-ARG GIT_REPO=https://github.com/langflow-ai/langflow.git
-ARG GIT_BRANCH=test-openai-responses
-
-WORKDIR /app
-
-# Install system dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    ca-certificates \
-    gnupg \
-    npm \
-    rustc cargo pkg-config libssl-dev \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install uv for faster Python package management
-RUN pip install uv
-
-# Clone the repository and checkout the specified branch
-RUN git clone --depth 1 --branch ${GIT_BRANCH} ${GIT_REPO} /app
-
-# Install backend dependencies
-RUN uv sync --frozen --no-install-project --no-editable --extra postgresql
-
-# Build frontend
-WORKDIR /app/src/frontend
-RUN NODE_OPTIONS=--max_old_space_size=4096 npm ci && \
-    NODE_OPTIONS=--max_old_space_size=4096 npm run build && \
-    mkdir -p /app/src/backend/base/langflow/frontend && \
-    cp -r build/* /app/src/backend/base/langflow/frontend/
-
-# Return to app directory and install the project
-WORKDIR /app
-RUN uv sync --frozen --no-dev --no-editable --extra postgresql
-
-# Expose ports
 EXPOSE 7860
 
-# Start the backend server
-CMD ["uv", "run", "langflow", "run", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["langflow", "run", "--host", "0.0.0.0", "--port", "7860"]
\ No newline at end of file
diff --git a/docker-compose-cpu.yml b/docker-compose-cpu.yml
index 9c121f89..570bc3b8 100644
--- a/docker-compose-cpu.yml
+++ b/docker-compose-cpu.yml
@@ -40,10 +40,10 @@ services:
 
   openrag-backend:
     image: phact/openrag-backend:${OPENRAG_VERSION:-latest}
-    #build:
-    #context: .
-    #dockerfile: Dockerfile.backend
-    container_name: openrag-backend
+    # build:
+    #   context: .
+    #   dockerfile: Dockerfile.backend
+    # container_name: openrag-backend
     depends_on:
       - langflow
     environment:
@@ -55,6 +55,7 @@ services:
       - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
       - LANGFLOW_CHAT_FLOW_ID=${LANGFLOW_CHAT_FLOW_ID}
       - LANGFLOW_INGEST_FLOW_ID=${LANGFLOW_INGEST_FLOW_ID}
+      - LANGFLOW_URL_INGEST_FLOW_ID=${LANGFLOW_URL_INGEST_FLOW_ID}
       - DISABLE_INGEST_WITH_LANGFLOW=${DISABLE_INGEST_WITH_LANGFLOW:-false}
       - NUDGES_FLOW_ID=${NUDGES_FLOW_ID}
       - OPENSEARCH_PORT=9200
@@ -77,9 +78,9 @@ services:
 
   openrag-frontend:
     image: phact/openrag-frontend:${OPENRAG_VERSION:-latest}
-    #build:
-    #context: .
-    #dockerfile: Dockerfile.frontend
+    # build:
+    #   context: .
+    #   dockerfile: Dockerfile.frontend
     container_name: openrag-frontend
     depends_on:
       - openrag-backend
@@ -92,6 +93,9 @@ services:
     volumes:
       - ./flows:/app/flows:Z
     image: phact/openrag-langflow:${LANGFLOW_VERSION:-latest}
+    # build:
+    #   context: .
+    #   dockerfile: Dockerfile.langflow
     container_name: langflow
     ports:
       - "7860:7860"
@@ -99,15 +103,23 @@ services:
       - OPENAI_API_KEY=${OPENAI_API_KEY}
       - LANGFLOW_LOAD_FLOWS_PATH=/app/flows
       - LANGFLOW_SECRET_KEY=${LANGFLOW_SECRET_KEY}
-      - JWT="dummy"
+      - JWT=None  
+      - OWNER=None
+      - OWNER_NAME=None
+      - OWNER_EMAIL=None
+      - CONNECTOR_TYPE=system
       - OPENRAG-QUERY-FILTER="{}"
       - OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
-      - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD
+      - FILENAME=None
+      - MIMETYPE=None
+      - FILESIZE=0
+      - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD,OWNER,OWNER_NAME,OWNER_EMAIL,CONNECTOR_TYPE,FILENAME,MIMETYPE,FILESIZE
       - LANGFLOW_LOG_LEVEL=DEBUG
       - LANGFLOW_AUTO_LOGIN=${LANGFLOW_AUTO_LOGIN}
       - LANGFLOW_SUPERUSER=${LANGFLOW_SUPERUSER}
       - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
       - LANGFLOW_NEW_USER_IS_ACTIVE=${LANGFLOW_NEW_USER_IS_ACTIVE}
       - LANGFLOW_ENABLE_SUPERUSER_CLI=${LANGFLOW_ENABLE_SUPERUSER_CLI}
-      - DEFAULT_FOLDER_NAME="OpenRAG"
+      # - DEFAULT_FOLDER_NAME=OpenRAG
       - HIDE_GETTING_STARTED_PROGRESS=true
+
diff --git a/docker-compose.yml b/docker-compose.yml
index 64226fd5..b97f7cca 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -43,7 +43,7 @@ services:
     # build:
     #   context: .
     #   dockerfile: Dockerfile.backend
-    container_name: openrag-backend
+    # container_name: openrag-backend
     depends_on:
       - langflow
     environment:
@@ -54,6 +54,7 @@ services:
       - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
       - LANGFLOW_CHAT_FLOW_ID=${LANGFLOW_CHAT_FLOW_ID}
       - LANGFLOW_INGEST_FLOW_ID=${LANGFLOW_INGEST_FLOW_ID}
+      - LANGFLOW_URL_INGEST_FLOW_ID=${LANGFLOW_URL_INGEST_FLOW_ID}
       - DISABLE_INGEST_WITH_LANGFLOW=${DISABLE_INGEST_WITH_LANGFLOW:-false}
       - NUDGES_FLOW_ID=${NUDGES_FLOW_ID}
       - OPENSEARCH_PORT=9200
@@ -80,7 +81,7 @@ services:
     # build:
     #   context: .
     #   dockerfile: Dockerfile.frontend
-    #   #dockerfile: Dockerfile.frontend
+      #dockerfile: Dockerfile.frontend
     container_name: openrag-frontend
     depends_on:
       - openrag-backend
@@ -109,13 +110,16 @@ services:
       - OWNER_EMAIL=None
       - CONNECTOR_TYPE=system
       - OPENRAG-QUERY-FILTER="{}"
+      - FILENAME=None
+      - MIMETYPE=None
+      - FILESIZE=0
       - OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
-      - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD,OWNER,OWNER_NAME,OWNER_EMAIL,CONNECTOR_TYPE
+      - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD,OWNER,OWNER_NAME,OWNER_EMAIL,CONNECTOR_TYPE,FILENAME,MIMETYPE,FILESIZE
       - LANGFLOW_LOG_LEVEL=DEBUG
       - LANGFLOW_AUTO_LOGIN=${LANGFLOW_AUTO_LOGIN}
       - LANGFLOW_SUPERUSER=${LANGFLOW_SUPERUSER}
       - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
       - LANGFLOW_NEW_USER_IS_ACTIVE=${LANGFLOW_NEW_USER_IS_ACTIVE}
       - LANGFLOW_ENABLE_SUPERUSER_CLI=${LANGFLOW_ENABLE_SUPERUSER_CLI}
-      - DEFAULT_FOLDER_NAME="OpenRAG"
+      # - DEFAULT_FOLDER_NAME=OpenRAG
       - HIDE_GETTING_STARTED_PROGRESS=true
diff --git a/flows/ingestion_flow.json b/flows/ingestion_flow.json
index 12cf5b63..911c3e38 100644
--- a/flows/ingestion_flow.json
+++ b/flows/ingestion_flow.json
@@ -30,36 +30,6 @@
         "target": "OpenSearchHybrid-Ve6bS",
         "targetHandle": "{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}"
       },
-      {
-        "animated": false,
-        "className": "",
-        "data": {
-          "sourceHandle": {
-            "dataType": "File",
-            "id": "File-PSU37",
-            "name": "message",
-            "output_types": [
-              "Message"
-            ]
-          },
-          "targetHandle": {
-            "fieldName": "data_inputs",
-            "id": "SplitText-QIKhg",
-            "inputTypes": [
-              "Data",
-              "DataFrame",
-              "Message"
-            ],
-            "type": "other"
-          }
-        },
-        "id": "xy-edge__File-PSU37{œdataTypeœ:œFileœ,œidœ:œFile-PSU37œ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-SplitText-QIKhg{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-QIKhgœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
-        "selected": false,
-        "source": "File-PSU37",
-        "sourceHandle": "{œdataTypeœ:œFileœ,œidœ:œFile-PSU37œ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}",
-        "target": "SplitText-QIKhg",
-        "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-QIKhgœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}"
-      },
       {
         "animated": false,
         "className": "",
@@ -206,7 +176,7 @@
       },
       {
         "animated": false,
-        "className": "not-running",
+        "className": "",
         "data": {
           "sourceHandle": {
             "dataType": "AdvancedDynamicFormBuilder",
@@ -231,6 +201,149 @@
         "sourceHandle": "{œdataTypeœ:œAdvancedDynamicFormBuilderœ,œidœ:œAdvancedDynamicFormBuilder-81Exwœ,œnameœ:œform_dataœ,œoutput_typesœ:[œDataœ]}",
         "target": "OpenSearchHybrid-Ve6bS",
         "targetHandle": "{œfieldNameœ:œdocs_metadataœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œDataœ],œtypeœ:œtableœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "DoclingRemote",
+            "id": "DoclingRemote-Dp3PX",
+            "name": "dataframe",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "data_inputs",
+            "id": "ExportDoclingDocument-zZdRg",
+            "inputTypes": [
+              "Data",
+              "DataFrame"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__DoclingRemote-Dp3PX{œdataTypeœ:œDoclingRemoteœ,œidœ:œDoclingRemote-Dp3PXœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-ExportDoclingDocument-zZdRg{œfieldNameœ:œdata_inputsœ,œidœ:œExportDoclingDocument-zZdRgœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "DoclingRemote-Dp3PX",
+        "sourceHandle": "{œdataTypeœ:œDoclingRemoteœ,œidœ:œDoclingRemote-Dp3PXœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "ExportDoclingDocument-zZdRg",
+        "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œExportDoclingDocument-zZdRgœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "ExportDoclingDocument",
+            "id": "ExportDoclingDocument-zZdRg",
+            "name": "dataframe",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "df",
+            "id": "DataFrameOperations-1BWXB",
+            "inputTypes": [
+              "DataFrame"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__ExportDoclingDocument-zZdRg{œdataTypeœ:œExportDoclingDocumentœ,œidœ:œExportDoclingDocument-zZdRgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-DataFrameOperations-1BWXB{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-1BWXBœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "ExportDoclingDocument-zZdRg",
+        "sourceHandle": "{œdataTypeœ:œExportDoclingDocumentœ,œidœ:œExportDoclingDocument-zZdRgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "DataFrameOperations-1BWXB",
+        "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-1BWXBœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "DataFrameOperations",
+            "id": "DataFrameOperations-N80fC",
+            "name": "output",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "data_inputs",
+            "id": "SplitText-QIKhg",
+            "inputTypes": [
+              "Data",
+              "DataFrame",
+              "Message"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__DataFrameOperations-N80fC{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-N80fCœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}-SplitText-QIKhg{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-QIKhgœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "DataFrameOperations-N80fC",
+        "sourceHandle": "{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-N80fCœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "SplitText-QIKhg",
+        "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-QIKhgœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "DataFrameOperations",
+            "id": "DataFrameOperations-1BWXB",
+            "name": "output",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "df",
+            "id": "DataFrameOperations-9vMrp",
+            "inputTypes": [
+              "DataFrame"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__DataFrameOperations-1BWXB{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-1BWXBœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}-DataFrameOperations-9vMrp{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-9vMrpœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "DataFrameOperations-1BWXB",
+        "sourceHandle": "{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-1BWXBœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "DataFrameOperations-9vMrp",
+        "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-9vMrpœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "DataFrameOperations",
+            "id": "DataFrameOperations-9vMrp",
+            "name": "output",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "df",
+            "id": "DataFrameOperations-N80fC",
+            "inputTypes": [
+              "DataFrame"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__DataFrameOperations-9vMrp{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-9vMrpœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}-DataFrameOperations-N80fC{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-N80fCœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "DataFrameOperations-9vMrp",
+        "sourceHandle": "{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-9vMrpœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "DataFrameOperations-N80fC",
+        "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-N80fCœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}"
       }
     ],
     "nodes": [
@@ -261,7 +374,7 @@
             "frozen": false,
             "icon": "scissors-line-dashed",
             "legacy": false,
-            "lf_version": "1.6.0",
+            "lf_version": "1.6.3.dev0",
             "metadata": {
               "code_hash": "f2867efda61f",
               "dependencies": {
@@ -466,8 +579,8 @@
           "width": 320
         },
         "position": {
-          "x": 1729.1788373023007,
-          "y": 1330.8003441546418
+          "x": 1704.25352249077,
+          "y": 1199.364065218893
         },
         "positionAbsolute": {
           "x": 1683.4543896546102,
@@ -477,481 +590,6 @@
         "type": "genericNode",
         "width": 320
       },
-      {
-        "data": {
-          "id": "File-PSU37",
-          "node": {
-            "base_classes": [
-              "Message"
-            ],
-            "beta": false,
-            "conditional_paths": [],
-            "custom_fields": {},
-            "description": "Loads content from one or more files.",
-            "display_name": "File",
-            "documentation": "https://docs.langflow.org/components-data#file",
-            "edited": true,
-            "field_order": [
-              "path",
-              "file_path",
-              "separator",
-              "silent_errors",
-              "delete_server_file_after_processing",
-              "ignore_unsupported_extensions",
-              "ignore_unspecified_files",
-              "advanced_mode",
-              "pipeline",
-              "ocr_engine",
-              "md_image_placeholder",
-              "md_page_break_placeholder",
-              "doc_key",
-              "use_multithreading",
-              "concurrency_multithreading",
-              "markdown"
-            ],
-            "frozen": false,
-            "icon": "file-text",
-            "last_updated": "2025-09-26T14:37:42.811Z",
-            "legacy": false,
-            "lf_version": "1.6.0",
-            "metadata": {
-              "code_hash": "9a1d497f4f91",
-              "dependencies": {
-                "dependencies": [
-                  {
-                    "name": "lfx",
-                    "version": null
-                  }
-                ],
-                "total_dependencies": 1
-              },
-              "module": "custom_components.file"
-            },
-            "minimized": false,
-            "output_types": [],
-            "outputs": [
-              {
-                "allows_loop": false,
-                "cache": true,
-                "display_name": "Raw Content",
-                "group_outputs": false,
-                "hidden": null,
-                "method": "load_files_message",
-                "name": "message",
-                "options": null,
-                "required_inputs": null,
-                "selected": "Message",
-                "tool_mode": true,
-                "types": [
-                  "Message"
-                ],
-                "value": "__UNDEFINED__"
-              }
-            ],
-            "pinned": false,
-            "template": {
-              "_type": "Component",
-              "advanced_mode": {
-                "_input_type": "BoolInput",
-                "advanced": false,
-                "display_name": "Advanced Parser",
-                "dynamic": false,
-                "info": "Enable advanced document processing and export with Docling for PDFs, images, and office documents. Available only for single file processing.Note that advanced document processing can consume significant resources.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "advanced_mode",
-                "placeholder": "",
-                "real_time_refresh": true,
-                "required": false,
-                "show": false,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "bool",
-                "value": false
-              },
-              "code": {
-                "advanced": true,
-                "dynamic": true,
-                "fileTypes": [],
-                "file_path": "",
-                "info": "",
-                "list": false,
-                "load_from_db": false,
-                "multiline": true,
-                "name": "code",
-                "password": false,
-                "placeholder": "",
-                "required": true,
-                "show": true,
-                "title_case": false,
-                "type": "code",
-                "value": "\"\"\"Enhanced file component with Docling support and process isolation.\n\nNotes:\n-----\n- ALL Docling parsing/export runs in a separate OS process to prevent memory\n  growth and native library state from impacting the main Langflow process.\n- Standard text/structured parsing continues to use existing BaseFileComponent\n  utilities (and optional threading via `parallel_load_data`).\n\"\"\"\n\nfrom __future__ import annotations\n\nimport json\nimport subprocess\nimport sys\nimport textwrap\nfrom copy import deepcopy\nfrom typing import Any\n\nfrom lfx.base.data.base_file import BaseFileComponent\nfrom lfx.base.data.utils import TEXT_FILE_TYPES, parallel_load_data, parse_text_file_to_data\nfrom lfx.inputs.inputs import DropdownInput, MessageTextInput, StrInput\nfrom lfx.io import BoolInput, FileInput, IntInput, Output\nfrom lfx.schema import DataFrame  # noqa: TC001\nfrom lfx.schema.data import Data\nfrom lfx.schema.message import Message\n\n\nclass FileComponent(BaseFileComponent):\n    \"\"\"File component with optional Docling processing (isolated in a subprocess).\"\"\"\n\n    display_name = \"File\"\n    description = \"Loads content from one or more files.\"\n    documentation: str = \"https://docs.langflow.org/components-data#file\"\n    icon = \"file-text\"\n    name = \"File\"\n\n    # Docling-supported/compatible extensions; TEXT_FILE_TYPES are supported by the base loader.\n    VALID_EXTENSIONS = [\n        *TEXT_FILE_TYPES,\n        \"adoc\",\n        \"asciidoc\",\n        \"asc\",\n        \"bmp\",\n        \"dotx\",\n        \"dotm\",\n        \"docm\",\n        \"jpeg\",\n        \"png\",\n        \"potx\",\n        \"ppsx\",\n        \"pptm\",\n        \"potm\",\n        \"ppsm\",\n        \"pptx\",\n        \"tiff\",\n        \"xls\",\n        \"xlsx\",\n        \"xhtml\",\n        \"webp\",\n    ]\n\n    # Fixed export settings used when markdown export is requested.\n    EXPORT_FORMAT = \"Markdown\"\n    IMAGE_MODE = \"placeholder\"\n\n    _base_inputs = deepcopy(BaseFileComponent.get_base_inputs())\n\n    for input_item in _base_inputs:\n        if isinstance(input_item, FileInput) and input_item.name == \"path\":\n            input_item.real_time_refresh = True\n            break\n\n    inputs = [\n        *_base_inputs,\n        BoolInput(\n            name=\"advanced_mode\",\n            display_name=\"Advanced Parser\",\n            value=False,\n            real_time_refresh=True,\n            info=(\n                \"Enable advanced document processing and export with Docling for PDFs, images, and office documents. \"\n                \"Available only for single file processing.\"\n                \"Note that advanced document processing can consume significant resources.\"\n            ),\n            show=False,\n        ),\n        DropdownInput(\n            name=\"pipeline\",\n            display_name=\"Pipeline\",\n            info=\"Docling pipeline to use\",\n            options=[\"standard\", \"vlm\"],\n            value=\"standard\",\n            advanced=True,\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"ocr_engine\",\n            display_name=\"OCR Engine\",\n            info=\"OCR engine to use. Only available when pipeline is set to 'standard'.\",\n            options=[\"None\", \"easyocr\"],\n            value=\"easyocr\",\n            show=False,\n            advanced=True,\n        ),\n        StrInput(\n            name=\"md_image_placeholder\",\n            display_name=\"Image placeholder\",\n            info=\"Specify the image placeholder for markdown exports.\",\n            value=\"<!-- image -->\",\n            advanced=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"md_page_break_placeholder\",\n            display_name=\"Page break placeholder\",\n            info=\"Add this placeholder between pages in the markdown output.\",\n            value=\"\",\n            advanced=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"doc_key\",\n            display_name=\"Doc Key\",\n            info=\"The key to use for the DoclingDocument column.\",\n            value=\"doc\",\n            advanced=True,\n            show=False,\n        ),\n        # Deprecated input retained for backward-compatibility.\n        BoolInput(\n            name=\"use_multithreading\",\n            display_name=\"[Deprecated] Use Multithreading\",\n            advanced=True,\n            value=True,\n            info=\"Set 'Processing Concurrency' greater than 1 to enable multithreading.\",\n        ),\n        IntInput(\n            name=\"concurrency_multithreading\",\n            display_name=\"Processing Concurrency\",\n            advanced=True,\n            info=\"When multiple files are being processed, the number of files to process concurrently.\",\n            value=1,\n        ),\n        BoolInput(\n            name=\"markdown\",\n            display_name=\"Markdown Export\",\n            info=\"Export processed documents to Markdown format. Only available when advanced mode is enabled.\",\n            value=False,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\"),\n    ]\n\n    # ------------------------------ UI helpers --------------------------------------\n\n    def _path_value(self, template: dict) -> list[str]:\n        \"\"\"Return the list of currently selected file paths from the template.\"\"\"\n        return template.get(\"path\", {}).get(\"file_path\", [])\n\n    def update_build_config(\n        self,\n        build_config: dict[str, Any],\n        field_value: Any,\n        field_name: str | None = None,\n    ) -> dict[str, Any]:\n        \"\"\"Show/hide Advanced Parser and related fields based on selection context.\"\"\"\n        if field_name == \"path\":\n            paths = self._path_value(build_config)\n            file_path = paths[0] if paths else \"\"\n            file_count = len(field_value) if field_value else 0\n\n            # Advanced mode only for single (non-tabular) file\n            allow_advanced = file_count == 1 and not file_path.endswith((\".csv\", \".xlsx\", \".parquet\"))\n            build_config[\"advanced_mode\"][\"show\"] = allow_advanced\n            if not allow_advanced:\n                build_config[\"advanced_mode\"][\"value\"] = False\n                for f in (\"pipeline\", \"ocr_engine\", \"doc_key\", \"md_image_placeholder\", \"md_page_break_placeholder\"):\n                    if f in build_config:\n                        build_config[f][\"show\"] = False\n\n        # Docling Processing\n        elif field_name == \"advanced_mode\":\n            for f in (\"pipeline\", \"ocr_engine\", \"doc_key\", \"md_image_placeholder\", \"md_page_break_placeholder\"):\n                if f in build_config:\n                    build_config[f][\"show\"] = bool(field_value)\n\n        elif field_name == \"pipeline\":\n            if field_value == \"standard\":\n                build_config[\"ocr_engine\"][\"show\"] = True\n                build_config[\"ocr_engine\"][\"value\"] = \"easyocr\"\n            else:\n                build_config[\"ocr_engine\"][\"show\"] = False\n                build_config[\"ocr_engine\"][\"value\"] = \"None\"\n\n        return build_config\n\n    def update_outputs(self, frontend_node: dict[str, Any], field_name: str, field_value: Any) -> dict[str, Any]:  # noqa: ARG002\n        \"\"\"Dynamically show outputs based on file count/type and advanced mode.\"\"\"\n        if field_name not in [\"path\", \"advanced_mode\", \"pipeline\"]:\n            return frontend_node\n\n        template = frontend_node.get(\"template\", {})\n        paths = self._path_value(template)\n        if not paths:\n            return frontend_node\n\n        frontend_node[\"outputs\"] = []\n        if len(paths) == 1:\n            file_path = paths[0] if field_name == \"path\" else frontend_node[\"template\"][\"path\"][\"file_path\"][0]\n            if file_path.endswith((\".csv\", \".xlsx\", \".parquet\")):\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Structured Content\", name=\"dataframe\", method=\"load_files_structured\"),\n                )\n            elif file_path.endswith(\".json\"):\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Structured Content\", name=\"json\", method=\"load_files_json\"),\n                )\n\n            advanced_mode = frontend_node.get(\"template\", {}).get(\"advanced_mode\", {}).get(\"value\", False)\n            if advanced_mode:\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Structured Output\", name=\"advanced_dataframe\", method=\"load_files_dataframe\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Markdown\", name=\"advanced_markdown\", method=\"load_files_markdown\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"File Path\", name=\"path\", method=\"load_files_path\"),\n                )\n            else:\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"File Path\", name=\"path\", method=\"load_files_path\"),\n                )\n        else:\n            # Multiple files => DataFrame output; advanced parser disabled\n            frontend_node[\"outputs\"].append(Output(display_name=\"Files\", name=\"dataframe\", method=\"load_files\"))\n\n        return frontend_node\n\n    # ------------------------------ Core processing ----------------------------------\n\n    def _is_docling_compatible(self, file_path: str) -> bool:\n        \"\"\"Lightweight extension gate for Docling-compatible types.\"\"\"\n        docling_exts = (\n            \".adoc\",\n            \".asciidoc\",\n            \".asc\",\n            \".bmp\",\n            \".csv\",\n            \".dotx\",\n            \".dotm\",\n            \".docm\",\n            \".docx\",\n            \".htm\",\n            \".html\",\n            \".jpeg\",\n            \".json\",\n            \".md\",\n            \".pdf\",\n            \".png\",\n            \".potx\",\n            \".ppsx\",\n            \".pptm\",\n            \".potm\",\n            \".ppsm\",\n            \".pptx\",\n            \".tiff\",\n            \".txt\",\n            \".xls\",\n            \".xlsx\",\n            \".xhtml\",\n            \".xml\",\n            \".webp\",\n        )\n        return file_path.lower().endswith(docling_exts)\n\n    def _process_docling_in_subprocess(self, file_path: str) -> Data | None:\n        \"\"\"Run Docling in a separate OS process and map the result to a Data object.\n\n        We avoid multiprocessing pickling by launching `python -c \"<script>\"` and\n        passing JSON config via stdin. The child prints a JSON result to stdout.\n        \"\"\"\n        if not file_path:\n            return None\n\n        args: dict[str, Any] = {\n            \"file_path\": file_path,\n            \"markdown\": bool(self.markdown),\n            \"image_mode\": str(self.IMAGE_MODE),\n            \"md_image_placeholder\": str(self.md_image_placeholder),\n            \"md_page_break_placeholder\": str(self.md_page_break_placeholder),\n            \"pipeline\": str(self.pipeline),\n            \"ocr_engine\": (\n                self.ocr_engine if self.ocr_engine and self.ocr_engine != \"None\" and self.pipeline != \"vlm\" else None\n            ),\n        }\n\n        self.log(f\"Starting Docling subprocess for file: {file_path}\")\n        self.log(args)\n\n        # Child script for isolating the docling processing\n        child_script = textwrap.dedent(\n            r\"\"\"\n            import json, sys\n\n            def try_imports():\n                # Strategy 1: latest layout\n                try:\n                    from docling.datamodel.base_models import ConversionStatus, InputFormat  # type: ignore\n                    from docling.document_converter import DocumentConverter  # type: ignore\n                    from docling_core.types.doc import ImageRefMode  # type: ignore\n                    return ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, \"latest\"\n                except Exception:\n                    pass\n                # Strategy 2: alternative layout\n                try:\n                    from docling.document_converter import DocumentConverter  # type: ignore\n                    try:\n                        from docling_core.types import ConversionStatus, InputFormat  # type: ignore\n                    except Exception:\n                        try:\n                            from docling.datamodel import ConversionStatus, InputFormat  # type: ignore\n                        except Exception:\n                            class ConversionStatus: SUCCESS = \"success\"\n                            class InputFormat:\n                                PDF=\"pdf\"; IMAGE=\"image\"\n                    try:\n                        from docling_core.types.doc import ImageRefMode  # type: ignore\n                    except Exception:\n                        class ImageRefMode:\n                            PLACEHOLDER=\"placeholder\"; EMBEDDED=\"embedded\"\n                    return ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, \"alternative\"\n                except Exception:\n                    pass\n                # Strategy 3: basic converter only\n                try:\n                    from docling.document_converter import DocumentConverter  # type: ignore\n                    class ConversionStatus: SUCCESS = \"success\"\n                    class InputFormat:\n                        PDF=\"pdf\"; IMAGE=\"image\"\n                    class ImageRefMode:\n                        PLACEHOLDER=\"placeholder\"; EMBEDDED=\"embedded\"\n                    return ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, \"basic\"\n                except Exception as e:\n                    raise ImportError(f\"Docling imports failed: {e}\") from e\n\n            def create_converter(strategy, input_format, DocumentConverter, pipeline, ocr_engine):\n                # --- Standard PDF/IMAGE pipeline (your existing behavior), with optional OCR ---\n                if pipeline == \"standard\":\n                    try:\n                        from docling.datamodel.pipeline_options import PdfPipelineOptions  # type: ignore\n                        from docling.document_converter import PdfFormatOption  # type: ignore\n\n                        pipe = PdfPipelineOptions()\n                        pipe.do_ocr = False\n\n                        if ocr_engine:\n                            try:\n                                from docling.models.factories import get_ocr_factory  # type: ignore\n                                pipe.do_ocr = True\n                                fac = get_ocr_factory(allow_external_plugins=False)\n                                pipe.ocr_options = fac.create_options(kind=ocr_engine)\n                            except Exception:\n                                # If OCR setup fails, disable it\n                                pipe.do_ocr = False\n\n                        fmt = {}\n                        if hasattr(input_format, \"PDF\"):\n                            fmt[getattr(input_format, \"PDF\")] = PdfFormatOption(pipeline_options=pipe)\n                        if hasattr(input_format, \"IMAGE\"):\n                            fmt[getattr(input_format, \"IMAGE\")] = PdfFormatOption(pipeline_options=pipe)\n\n                        return DocumentConverter(format_options=fmt)\n                    except Exception:\n                        return DocumentConverter()\n\n                # --- Vision-Language Model (VLM) pipeline ---\n                if pipeline == \"vlm\":\n                    try:\n                        from docling.pipeline.vlm_pipeline import VlmPipeline\n                        from docling.document_converter import PdfFormatOption  # type: ignore\n\n                        vl_pipe = VlmPipelineOptions()\n\n                        # VLM paths generally don't need OCR; keep OCR off by default here.\n                        fmt = {}\n                        if hasattr(input_format, \"PDF\"):\n                            fmt[getattr(input_format, \"PDF\")] = PdfFormatOption(pipeline_cls=VlmPipeline)\n                        if hasattr(input_format, \"IMAGE\"):\n                            fmt[getattr(input_format, \"IMAGE\")] = PdfFormatOption(pipeline_cls=VlmPipeline)\n\n                        return DocumentConverter(format_options=fmt)\n                    except Exception:\n                        return DocumentConverter()\n\n                # --- Fallback: default converter with no special options ---\n                return DocumentConverter()\n\n            def export_markdown(document, ImageRefMode, image_mode, img_ph, pg_ph):\n                try:\n                    mode = getattr(ImageRefMode, image_mode.upper(), image_mode)\n                    return document.export_to_markdown(\n                        image_mode=mode,\n                        image_placeholder=img_ph,\n                        page_break_placeholder=pg_ph,\n                    )\n                except Exception:\n                    try:\n                        return document.export_to_text()\n                    except Exception:\n                        return str(document)\n\n            def to_rows(doc_dict):\n                rows = []\n                for t in doc_dict.get(\"texts\", []):\n                    prov = t.get(\"prov\") or []\n                    page_no = None\n                    if prov and isinstance(prov, list) and isinstance(prov[0], dict):\n                        page_no = prov[0].get(\"page_no\")\n                    rows.append({\n                        \"page_no\": page_no,\n                        \"label\": t.get(\"label\"),\n                        \"text\": t.get(\"text\"),\n                        \"level\": t.get(\"level\"),\n                    })\n                return rows\n\n            def main():\n                cfg = json.loads(sys.stdin.read())\n                file_path = cfg[\"file_path\"]\n                markdown = cfg[\"markdown\"]\n                image_mode = cfg[\"image_mode\"]\n                img_ph = cfg[\"md_image_placeholder\"]\n                pg_ph = cfg[\"md_page_break_placeholder\"]\n                pipeline = cfg[\"pipeline\"]\n                ocr_engine = cfg.get(\"ocr_engine\")\n                meta = {\"file_path\": file_path}\n\n                try:\n                    ConversionStatus, InputFormat, DocumentConverter, ImageRefMode, strategy = try_imports()\n                    converter = create_converter(strategy, InputFormat, DocumentConverter, pipeline, ocr_engine)\n                    try:\n                        res = converter.convert(file_path)\n                    except Exception as e:\n                        print(json.dumps({\"ok\": False, \"error\": f\"Docling conversion error: {e}\", \"meta\": meta}))\n                        return\n\n                    ok = False\n                    if hasattr(res, \"status\"):\n                        try:\n                            ok = (res.status == ConversionStatus.SUCCESS) or (str(res.status).lower() == \"success\")\n                        except Exception:\n                            ok = (str(res.status).lower() == \"success\")\n                    if not ok and hasattr(res, \"document\"):\n                        ok = getattr(res, \"document\", None) is not None\n                    if not ok:\n                        print(json.dumps({\"ok\": False, \"error\": \"Docling conversion failed\", \"meta\": meta}))\n                        return\n\n                    doc = getattr(res, \"document\", None)\n                    if doc is None:\n                        print(json.dumps({\"ok\": False, \"error\": \"Docling produced no document\", \"meta\": meta}))\n                        return\n\n                    if markdown:\n                        text = export_markdown(doc, ImageRefMode, image_mode, img_ph, pg_ph)\n                        print(json.dumps({\"ok\": True, \"mode\": \"markdown\", \"text\": text, \"meta\": meta}))\n                        return\n\n                    # structured\n                    try:\n                        doc_dict = doc.export_to_dict()\n                    except Exception as e:\n                        print(json.dumps({\"ok\": False, \"error\": f\"Docling export_to_dict failed: {e}\", \"meta\": meta}))\n                        return\n\n                    rows = to_rows(doc_dict)\n                    print(json.dumps({\"ok\": True, \"mode\": \"structured\", \"doc\": rows, \"meta\": meta}))\n                except Exception as e:\n                    print(\n                        json.dumps({\n                            \"ok\": False,\n                            \"error\": f\"Docling processing error: {e}\",\n                            \"meta\": {\"file_path\": file_path},\n                        })\n                    )\n\n            if __name__ == \"__main__\":\n                main()\n            \"\"\"\n        )\n\n        # Validate file_path to avoid command injection or unsafe input\n        if not isinstance(args[\"file_path\"], str) or any(c in args[\"file_path\"] for c in [\";\", \"|\", \"&\", \"$\", \"`\"]):\n            return Data(data={\"error\": \"Unsafe file path detected.\", \"file_path\": args[\"file_path\"]})\n\n        proc = subprocess.run(  # noqa: S603\n            [sys.executable, \"-u\", \"-c\", child_script],\n            input=json.dumps(args).encode(\"utf-8\"),\n            capture_output=True,\n            check=False,\n        )\n\n        if not proc.stdout:\n            err_msg = proc.stderr.decode(\"utf-8\", errors=\"replace\") or \"no output from child process\"\n            return Data(data={\"error\": f\"Docling subprocess error: {err_msg}\", \"file_path\": file_path})\n\n        try:\n            result = json.loads(proc.stdout.decode(\"utf-8\"))\n        except Exception as e:  # noqa: BLE001\n            err_msg = proc.stderr.decode(\"utf-8\", errors=\"replace\")\n            return Data(\n                data={\"error\": f\"Invalid JSON from Docling subprocess: {e}. stderr={err_msg}\", \"file_path\": file_path},\n            )\n\n        if not result.get(\"ok\"):\n            return Data(data={\"error\": result.get(\"error\", \"Unknown Docling error\"), **result.get(\"meta\", {})})\n\n        meta = result.get(\"meta\", {})\n        if result.get(\"mode\") == \"markdown\":\n            exported_content = str(result.get(\"text\", \"\"))\n            return Data(\n                text=exported_content,\n                data={\"exported_content\": exported_content, \"export_format\": self.EXPORT_FORMAT, **meta},\n            )\n\n        rows = list(result.get(\"doc\", []))\n        return Data(data={\"doc\": rows, \"export_format\": self.EXPORT_FORMAT, **meta})\n\n    def process_files(\n        self,\n        file_list: list[BaseFileComponent.BaseFile],\n    ) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Process input files.\n\n        - Single file + advanced_mode => Docling in a separate process.\n        - Otherwise => standard parsing in current process (optionally threaded).\n        \"\"\"\n        if not file_list:\n            msg = \"No files to process.\"\n            raise ValueError(msg)\n\n        def process_file_standard(file_path: str, *, silent_errors: bool = False) -> Data | None:\n            try:\n                return parse_text_file_to_data(file_path, silent_errors=silent_errors)\n            except FileNotFoundError as e:\n                self.log(f\"File not found: {file_path}. Error: {e}\")\n                if not silent_errors:\n                    raise\n                return None\n            except Exception as e:\n                self.log(f\"Unexpected error processing {file_path}: {e}\")\n                if not silent_errors:\n                    raise\n                return None\n\n        # Advanced path: only for a single Docling-compatible file\n        if len(file_list) == 1:\n            file_path = str(file_list[0].path)\n            if self.advanced_mode and self._is_docling_compatible(file_path):\n                advanced_data: Data | None = self._process_docling_in_subprocess(file_path)\n\n                # --- UNNEST: expand each element in `doc` to its own Data row\n                payload = getattr(advanced_data, \"data\", {}) or {}\n                doc_rows = payload.get(\"doc\")\n                if isinstance(doc_rows, list):\n                    rows: list[Data | None] = [\n                        Data(\n                            data={\n                                \"file_path\": file_path,\n                                **(item if isinstance(item, dict) else {\"value\": item}),\n                            },\n                        )\n                        for item in doc_rows\n                    ]\n                    return self.rollup_data(file_list, rows)\n\n                # If not structured, keep as-is (e.g., markdown export or error dict)\n                return self.rollup_data(file_list, [advanced_data])\n\n        # Standard multi-file (or single non-advanced) path\n        concurrency = 1 if not self.use_multithreading else max(1, self.concurrency_multithreading)\n        file_paths = [str(f.path) for f in file_list]\n        self.log(f\"Starting parallel processing of {len(file_paths)} files with concurrency: {concurrency}.\")\n        my_data = parallel_load_data(\n            file_paths,\n            silent_errors=self.silent_errors,\n            load_function=process_file_standard,\n            max_concurrency=concurrency,\n        )\n        return self.rollup_data(file_list, my_data)\n\n    # ------------------------------ Output helpers -----------------------------------\n\n    def load_files_helper(self) -> DataFrame:\n        result = self.load_files()\n\n        # Error condition - raise error if no text and an error is present\n        if not hasattr(result, \"text\"):\n            if hasattr(result, \"error\"):\n                raise ValueError(result.error[0])\n            msg = \"No content generated.\"\n            raise ValueError(msg)\n\n        return result\n\n    def load_files_dataframe(self) -> DataFrame:\n        \"\"\"Load files using advanced Docling processing and export to DataFrame format.\"\"\"\n        self.markdown = False\n        return self.load_files_helper()\n\n    def load_files_markdown(self) -> Message:\n        \"\"\"Load files using advanced Docling processing and export to Markdown format.\"\"\"\n        self.markdown = True\n        result = self.load_files_helper()\n        return Message(text=str(result.text[0]))\n"
-              },
-              "concurrency_multithreading": {
-                "_input_type": "IntInput",
-                "advanced": true,
-                "display_name": "Processing Concurrency",
-                "dynamic": false,
-                "info": "When multiple files are being processed, the number of files to process concurrently.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "concurrency_multithreading",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "int",
-                "value": 1
-              },
-              "delete_server_file_after_processing": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "Delete Server File After Processing",
-                "dynamic": false,
-                "info": "If true, the Server File Path will be deleted after processing.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "delete_server_file_after_processing",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "bool",
-                "value": true
-              },
-              "doc_key": {
-                "_input_type": "MessageTextInput",
-                "advanced": true,
-                "display_name": "Doc Key",
-                "dynamic": false,
-                "info": "The key to use for the DoclingDocument column.",
-                "input_types": [
-                  "Message"
-                ],
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "doc_key",
-                "placeholder": "",
-                "required": false,
-                "show": false,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_input": true,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": "doc"
-              },
-              "file_path": {
-                "_input_type": "HandleInput",
-                "advanced": true,
-                "display_name": "Server File Path",
-                "dynamic": false,
-                "info": "Data object with a 'file_path' property pointing to server file or a Message object with a path to the file. Supercedes 'Path' but supports same file types.",
-                "input_types": [
-                  "Data",
-                  "Message"
-                ],
-                "list": true,
-                "list_add_label": "Add More",
-                "name": "file_path",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "trace_as_metadata": true,
-                "type": "other",
-                "value": ""
-              },
-              "ignore_unspecified_files": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "Ignore Unspecified Files",
-                "dynamic": false,
-                "info": "If true, Data with no 'file_path' property will be ignored.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "ignore_unspecified_files",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "bool",
-                "value": false
-              },
-              "ignore_unsupported_extensions": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "Ignore Unsupported Extensions",
-                "dynamic": false,
-                "info": "If true, files with unsupported extensions will not be processed.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "ignore_unsupported_extensions",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "bool",
-                "value": true
-              },
-              "markdown": {
-                "_input_type": "BoolInput",
-                "advanced": false,
-                "display_name": "Markdown Export",
-                "dynamic": false,
-                "info": "Export processed documents to Markdown format. Only available when advanced mode is enabled.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "markdown",
-                "placeholder": "",
-                "required": false,
-                "show": false,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "bool",
-                "value": false
-              },
-              "md_image_placeholder": {
-                "_input_type": "StrInput",
-                "advanced": true,
-                "display_name": "Image placeholder",
-                "dynamic": false,
-                "info": "Specify the image placeholder for markdown exports.",
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "md_image_placeholder",
-                "placeholder": "",
-                "required": false,
-                "show": false,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": "<!-- image -->"
-              },
-              "md_page_break_placeholder": {
-                "_input_type": "StrInput",
-                "advanced": true,
-                "display_name": "Page break placeholder",
-                "dynamic": false,
-                "info": "Add this placeholder between pages in the markdown output.",
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "md_page_break_placeholder",
-                "placeholder": "",
-                "required": false,
-                "show": false,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": ""
-              },
-              "ocr_engine": {
-                "_input_type": "DropdownInput",
-                "advanced": true,
-                "combobox": false,
-                "dialog_inputs": {},
-                "display_name": "OCR Engine",
-                "dynamic": false,
-                "external_options": {},
-                "info": "OCR engine to use. Only available when pipeline is set to 'standard'.",
-                "load_from_db": false,
-                "name": "ocr_engine",
-                "options": [
-                  "None",
-                  "easyocr"
-                ],
-                "options_metadata": [],
-                "placeholder": "",
-                "required": false,
-                "show": false,
-                "title_case": false,
-                "toggle": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": ""
-              },
-              "path": {
-                "_input_type": "FileInput",
-                "advanced": false,
-                "display_name": "Files",
-                "dynamic": false,
-                "fileTypes": [
-                  "csv",
-                  "json",
-                  "pdf",
-                  "txt",
-                  "md",
-                  "mdx",
-                  "yaml",
-                  "yml",
-                  "xml",
-                  "html",
-                  "htm",
-                  "docx",
-                  "py",
-                  "sh",
-                  "sql",
-                  "js",
-                  "ts",
-                  "tsx",
-                  "adoc",
-                  "asciidoc",
-                  "asc",
-                  "bmp",
-                  "dotx",
-                  "dotm",
-                  "docm",
-                  "jpeg",
-                  "png",
-                  "potx",
-                  "ppsx",
-                  "pptm",
-                  "potm",
-                  "ppsm",
-                  "pptx",
-                  "tiff",
-                  "xls",
-                  "xlsx",
-                  "xhtml",
-                  "webp",
-                  "zip",
-                  "tar",
-                  "tgz",
-                  "bz2",
-                  "gz"
-                ],
-                "file_path": [],
-                "info": "Supported file extensions: csv, json, pdf, txt, md, mdx, yaml, yml, xml, html, htm, docx, py, sh, sql, js, ts, tsx, adoc, asciidoc, asc, bmp, dotx, dotm, docm, jpeg, png, potx, ppsx, pptm, potm, ppsm, pptx, tiff, xls, xlsx, xhtml, webp; optionally bundled in file extensions: zip, tar, tgz, bz2, gz",
-                "list": true,
-                "list_add_label": "Add More",
-                "name": "path",
-                "placeholder": "",
-                "real_time_refresh": true,
-                "required": false,
-                "show": true,
-                "temp_file": false,
-                "title_case": false,
-                "trace_as_metadata": true,
-                "type": "file",
-                "value": ""
-              },
-              "pipeline": {
-                "_input_type": "DropdownInput",
-                "advanced": true,
-                "combobox": false,
-                "dialog_inputs": {},
-                "display_name": "Pipeline",
-                "dynamic": false,
-                "external_options": {},
-                "info": "Docling pipeline to use",
-                "name": "pipeline",
-                "options": [
-                  "standard",
-                  "vlm"
-                ],
-                "options_metadata": [],
-                "placeholder": "",
-                "real_time_refresh": true,
-                "required": false,
-                "show": false,
-                "title_case": false,
-                "toggle": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": "standard"
-              },
-              "separator": {
-                "_input_type": "StrInput",
-                "advanced": true,
-                "display_name": "Separator",
-                "dynamic": false,
-                "info": "Specify the separator to use between multiple outputs in Message format.",
-                "list": false,
-                "list_add_label": "Add More",
-                "load_from_db": false,
-                "name": "separator",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "str",
-                "value": "\n\n"
-              },
-              "silent_errors": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "Silent Errors",
-                "dynamic": false,
-                "info": "If true, errors will not raise an exception.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "silent_errors",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "bool",
-                "value": false
-              },
-              "use_multithreading": {
-                "_input_type": "BoolInput",
-                "advanced": true,
-                "display_name": "[Deprecated] Use Multithreading",
-                "dynamic": false,
-                "info": "Set 'Processing Concurrency' greater than 1 to enable multithreading.",
-                "list": false,
-                "list_add_label": "Add More",
-                "name": "use_multithreading",
-                "placeholder": "",
-                "required": false,
-                "show": true,
-                "title_case": false,
-                "tool_mode": false,
-                "trace_as_metadata": true,
-                "type": "bool",
-                "value": true
-              }
-            },
-            "tool_mode": false
-          },
-          "selected_output": "message",
-          "showNode": true,
-          "type": "File"
-        },
-        "dragging": false,
-        "id": "File-PSU37",
-        "measured": {
-          "height": 214,
-          "width": 320
-        },
-        "position": {
-          "x": 1270.0395728258152,
-          "y": 1372.889208749833
-        },
-        "selected": false,
-        "type": "genericNode"
-      },
       {
         "data": {
           "id": "OpenSearchHybrid-Ve6bS",
@@ -995,6 +633,7 @@
             "frozen": false,
             "icon": "OpenSearch",
             "legacy": false,
+            "lf_version": "1.6.3.dev0",
             "metadata": {
               "code_hash": "c81b23acb81a",
               "dependencies": {
@@ -1606,9 +1245,9 @@
             ],
             "frozen": false,
             "icon": "binary",
-            "last_updated": "2025-09-26T14:37:42.699Z",
+            "last_updated": "2025-10-04T02:17:01.272Z",
             "legacy": false,
-            "lf_version": "1.6.0",
+            "lf_version": "1.6.3.dev0",
             "metadata": {
               "code_hash": "8607e963fdef",
               "dependencies": {
@@ -1911,9 +1550,9 @@
             ],
             "frozen": false,
             "icon": "braces",
-            "last_updated": "2025-09-26T14:37:42.700Z",
+            "last_updated": "2025-10-04T02:17:01.273Z",
             "legacy": false,
-            "lf_version": "1.6.0",
+            "lf_version": "1.6.3.dev0",
             "metadata": {},
             "minimized": false,
             "output_types": [],
@@ -2229,7 +1868,7 @@
             "frozen": false,
             "icon": "type",
             "legacy": false,
-            "lf_version": "1.6.0",
+            "lf_version": "1.6.3.dev0",
             "metadata": {},
             "minimized": false,
             "output_types": [],
@@ -2303,8 +1942,8 @@
           "width": 320
         },
         "position": {
-          "x": 714.0622664079099,
-          "y": 1763.5050239191407
+          "x": 717.1931358375118,
+          "y": 1935.3672380902274
         },
         "selected": false,
         "type": "genericNode"
@@ -2329,7 +1968,7 @@
             "frozen": false,
             "icon": "type",
             "legacy": false,
-            "lf_version": "1.6.0",
+            "lf_version": "1.6.3.dev0",
             "metadata": {},
             "minimized": false,
             "output_types": [],
@@ -2403,10 +2042,10 @@
           "width": 320
         },
         "position": {
-          "x": 714.4587372144712,
-          "y": 2004.1002386954729
+          "x": 715.4359658918343,
+          "y": 2198.0228056169435
         },
-        "selected": true,
+        "selected": false,
         "type": "genericNode"
       },
       {
@@ -2429,7 +2068,7 @@
             "frozen": false,
             "icon": "type",
             "legacy": false,
-            "lf_version": "1.6.0",
+            "lf_version": "1.6.3.dev0",
             "metadata": {},
             "minimized": false,
             "output_types": [],
@@ -2503,8 +2142,8 @@
           "width": 320
         },
         "position": {
-          "x": 709.8548852366719,
-          "y": 2250.972699431992
+          "x": 714.0740919106219,
+          "y": 2445.0562064336955
         },
         "selected": false,
         "type": "genericNode"
@@ -2529,7 +2168,7 @@
             "frozen": false,
             "icon": "type",
             "legacy": false,
-            "lf_version": "1.6.0",
+            "lf_version": "1.6.3.dev0",
             "metadata": {},
             "minimized": false,
             "output_types": [],
@@ -2604,23 +2243,1905 @@
         },
         "position": {
           "x": 712.1292482141275,
-          "y": 2505.6122587806585
+          "y": 2691.2573524344616
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "DoclingRemote-Dp3PX",
+          "node": {
+            "base_classes": [
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Uses Docling to process input documents connecting to your instance of Docling Serve.",
+            "display_name": "Docling Serve",
+            "documentation": "https://docling-project.github.io/docling/",
+            "edited": false,
+            "field_order": [
+              "path",
+              "file_path",
+              "separator",
+              "silent_errors",
+              "delete_server_file_after_processing",
+              "ignore_unsupported_extensions",
+              "ignore_unspecified_files",
+              "api_url",
+              "max_concurrency",
+              "max_poll_timeout",
+              "api_headers",
+              "docling_serve_opts"
+            ],
+            "frozen": false,
+            "icon": "Docling",
+            "legacy": false,
+            "lf_version": "1.6.3.dev0",
+            "metadata": {
+              "code_hash": "26eeb513dded",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "httpx",
+                    "version": "0.28.1"
+                  },
+                  {
+                    "name": "docling_core",
+                    "version": "2.48.4"
+                  },
+                  {
+                    "name": "pydantic",
+                    "version": "2.10.6"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": "0.1.12.dev31"
+                  }
+                ],
+                "total_dependencies": 4
+              },
+              "module": "lfx.components.docling.docling_remote.DoclingRemoteComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Files",
+                "group_outputs": false,
+                "method": "load_files",
+                "name": "dataframe",
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "api_headers": {
+                "_input_type": "NestedDictInput",
+                "advanced": true,
+                "display_name": "HTTP headers",
+                "dynamic": false,
+                "info": "Optional dictionary of additional headers required for connecting to Docling Serve.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "api_headers",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "NestedDict",
+                "value": {}
+              },
+              "api_url": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Server address",
+                "dynamic": false,
+                "info": "URL of the Docling Serve instance.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "api_url",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "http://localhost:5001"
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "import base64\nimport time\nfrom concurrent.futures import Future, ThreadPoolExecutor\nfrom pathlib import Path\nfrom typing import Any\n\nimport httpx\nfrom docling_core.types.doc import DoclingDocument\nfrom pydantic import ValidationError\n\nfrom lfx.base.data import BaseFileComponent\nfrom lfx.inputs import IntInput, NestedDictInput, StrInput\nfrom lfx.inputs.inputs import FloatInput\nfrom lfx.schema import Data\nfrom lfx.utils.util import transform_localhost_url\n\n\nclass DoclingRemoteComponent(BaseFileComponent):\n    display_name = \"Docling Serve\"\n    description = \"Uses Docling to process input documents connecting to your instance of Docling Serve.\"\n    documentation = \"https://docling-project.github.io/docling/\"\n    trace_type = \"tool\"\n    icon = \"Docling\"\n    name = \"DoclingRemote\"\n\n    MAX_500_RETRIES = 5\n\n    # https://docling-project.github.io/docling/usage/supported_formats/\n    VALID_EXTENSIONS = [\n        \"adoc\",\n        \"asciidoc\",\n        \"asc\",\n        \"bmp\",\n        \"csv\",\n        \"dotx\",\n        \"dotm\",\n        \"docm\",\n        \"docx\",\n        \"htm\",\n        \"html\",\n        \"jpeg\",\n        \"json\",\n        \"md\",\n        \"pdf\",\n        \"png\",\n        \"potx\",\n        \"ppsx\",\n        \"pptm\",\n        \"potm\",\n        \"ppsm\",\n        \"pptx\",\n        \"tiff\",\n        \"txt\",\n        \"xls\",\n        \"xlsx\",\n        \"xhtml\",\n        \"xml\",\n        \"webp\",\n    ]\n\n    inputs = [\n        *BaseFileComponent.get_base_inputs(),\n        StrInput(\n            name=\"api_url\",\n            display_name=\"Server address\",\n            info=\"URL of the Docling Serve instance.\",\n            required=True,\n        ),\n        IntInput(\n            name=\"max_concurrency\",\n            display_name=\"Concurrency\",\n            info=\"Maximum number of concurrent requests for the server.\",\n            advanced=True,\n            value=2,\n        ),\n        FloatInput(\n            name=\"max_poll_timeout\",\n            display_name=\"Maximum poll time\",\n            info=\"Maximum waiting time for the document conversion to complete.\",\n            advanced=True,\n            value=3600,\n        ),\n        NestedDictInput(\n            name=\"api_headers\",\n            display_name=\"HTTP headers\",\n            advanced=True,\n            required=False,\n            info=(\"Optional dictionary of additional headers required for connecting to Docling Serve.\"),\n        ),\n        NestedDictInput(\n            name=\"docling_serve_opts\",\n            display_name=\"Docling options\",\n            advanced=True,\n            required=False,\n            info=(\n                \"Optional dictionary of additional options. \"\n                \"See https://github.com/docling-project/docling-serve/blob/main/docs/usage.md for more information.\"\n            ),\n        ),\n    ]\n\n    outputs = [\n        *BaseFileComponent.get_base_outputs(),\n    ]\n\n    def process_files(self, file_list: list[BaseFileComponent.BaseFile]) -> list[BaseFileComponent.BaseFile]:\n        # Transform localhost URLs to container-accessible hosts when running in a container\n        transformed_url = transform_localhost_url(self.api_url)\n        base_url = f\"{transformed_url}/v1\"\n\n        def _convert_document(client: httpx.Client, file_path: Path, options: dict[str, Any]) -> Data | None:\n            encoded_doc = base64.b64encode(file_path.read_bytes()).decode()\n            payload = {\n                \"options\": options,\n                \"sources\": [{\"kind\": \"file\", \"base64_string\": encoded_doc, \"filename\": file_path.name}],\n            }\n\n            response = client.post(f\"{base_url}/convert/source/async\", json=payload)\n            response.raise_for_status()\n            task = response.json()\n\n            http_failures = 0\n            retry_status_start = 500\n            retry_status_end = 600\n            start_wait_time = time.monotonic()\n            while task[\"task_status\"] not in (\"success\", \"failure\"):\n                # Check if processing exceeds the maximum poll timeout\n                processing_time = time.monotonic() - start_wait_time\n                if processing_time >= self.max_poll_timeout:\n                    msg = (\n                        f\"Processing time {processing_time=} exceeds the maximum poll timeout {self.max_poll_timeout=}.\"\n                        \"Please increase the max_poll_timeout parameter or review why the processing \"\n                        \"takes long on the server.\"\n                    )\n                    self.log(msg)\n                    raise RuntimeError(msg)\n\n                # Call for a new status update\n                time.sleep(2)\n                response = client.get(f\"{base_url}/status/poll/{task['task_id']}\")\n\n                # Check if the status call gets into 5xx errors and retry\n                if retry_status_start <= response.status_code < retry_status_end:\n                    http_failures += 1\n                    if http_failures > self.MAX_500_RETRIES:\n                        self.log(f\"The status requests got a http response {response.status_code} too many times.\")\n                        return None\n                    continue\n\n                # Update task status\n                task = response.json()\n\n            result_resp = client.get(f\"{base_url}/result/{task['task_id']}\")\n            result_resp.raise_for_status()\n            result = result_resp.json()\n\n            if \"json_content\" not in result[\"document\"] or result[\"document\"][\"json_content\"] is None:\n                self.log(\"No JSON DoclingDocument found in the result.\")\n                return None\n\n            try:\n                doc = DoclingDocument.model_validate(result[\"document\"][\"json_content\"])\n                return Data(data={\"doc\": doc, \"file_path\": str(file_path)})\n            except ValidationError as e:\n                self.log(f\"Error validating the document. {e}\")\n                return None\n\n        docling_options = {\n            \"to_formats\": [\"json\"],\n            \"image_export_mode\": \"placeholder\",\n            **(self.docling_serve_opts or {}),\n        }\n\n        processed_data: list[Data | None] = []\n        with (\n            httpx.Client(headers=self.api_headers) as client,\n            ThreadPoolExecutor(max_workers=self.max_concurrency) as executor,\n        ):\n            futures: list[tuple[int, Future]] = []\n            for i, file in enumerate(file_list):\n                if file.path is None:\n                    processed_data.append(None)\n                    continue\n\n                futures.append((i, executor.submit(_convert_document, client, file.path, docling_options)))\n\n            for _index, future in futures:\n                try:\n                    result_data = future.result()\n                    processed_data.append(result_data)\n                except (httpx.HTTPStatusError, httpx.RequestError, KeyError, ValueError) as exc:\n                    self.log(f\"Docling remote processing failed: {exc}\")\n                    raise\n\n        return self.rollup_data(file_list, processed_data)\n"
+              },
+              "delete_server_file_after_processing": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Delete Server File After Processing",
+                "dynamic": false,
+                "info": "If true, the Server File Path will be deleted after processing.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "delete_server_file_after_processing",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "docling_serve_opts": {
+                "_input_type": "NestedDictInput",
+                "advanced": false,
+                "display_name": "Docling options",
+                "dynamic": false,
+                "info": "Optional dictionary of additional options. See https://github.com/docling-project/docling-serve/blob/main/docs/usage.md for more information.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "docling_serve_opts",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "NestedDict",
+                "value": {
+                  "do_ocr": false
+                }
+              },
+              "file_path": {
+                "_input_type": "HandleInput",
+                "advanced": true,
+                "display_name": "Server File Path",
+                "dynamic": false,
+                "info": "Data object with a 'file_path' property pointing to server file or a Message object with a path to the file. Supercedes 'Path' but supports same file types.",
+                "input_types": [
+                  "Data",
+                  "Message"
+                ],
+                "list": true,
+                "list_add_label": "Add More",
+                "name": "file_path",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "ignore_unspecified_files": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Ignore Unspecified Files",
+                "dynamic": false,
+                "info": "If true, Data with no 'file_path' property will be ignored.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ignore_unspecified_files",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": false
+              },
+              "ignore_unsupported_extensions": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Ignore Unsupported Extensions",
+                "dynamic": false,
+                "info": "If true, files with unsupported extensions will not be processed.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ignore_unsupported_extensions",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "max_concurrency": {
+                "_input_type": "IntInput",
+                "advanced": false,
+                "display_name": "Concurrency",
+                "dynamic": false,
+                "info": "Maximum number of concurrent requests for the server.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "max_concurrency",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 2
+              },
+              "max_poll_timeout": {
+                "_input_type": "FloatInput",
+                "advanced": true,
+                "display_name": "Maximum poll time",
+                "dynamic": false,
+                "info": "Maximum waiting time for the document conversion to complete.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "max_poll_timeout",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "float",
+                "value": 3600
+              },
+              "path": {
+                "_input_type": "FileInput",
+                "advanced": false,
+                "display_name": "Files",
+                "dynamic": false,
+                "fileTypes": [
+                  "adoc",
+                  "asciidoc",
+                  "asc",
+                  "bmp",
+                  "csv",
+                  "dotx",
+                  "dotm",
+                  "docm",
+                  "docx",
+                  "htm",
+                  "html",
+                  "jpeg",
+                  "json",
+                  "md",
+                  "pdf",
+                  "png",
+                  "potx",
+                  "ppsx",
+                  "pptm",
+                  "potm",
+                  "ppsm",
+                  "pptx",
+                  "tiff",
+                  "txt",
+                  "xls",
+                  "xlsx",
+                  "xhtml",
+                  "xml",
+                  "webp",
+                  "zip",
+                  "tar",
+                  "tgz",
+                  "bz2",
+                  "gz"
+                ],
+                "file_path": [],
+                "info": "Supported file extensions: adoc, asciidoc, asc, bmp, csv, dotx, dotm, docm, docx, htm, html, jpeg, json, md, pdf, png, potx, ppsx, pptm, potm, ppsm, pptx, tiff, txt, xls, xlsx, xhtml, xml, webp; optionally bundled in file extensions: zip, tar, tgz, bz2, gz",
+                "list": true,
+                "list_add_label": "Add More",
+                "name": "path",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "temp_file": false,
+                "title_case": false,
+                "trace_as_metadata": true,
+                "type": "file",
+                "value": ""
+              },
+              "separator": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "Separator",
+                "dynamic": false,
+                "info": "Specify the separator to use between multiple outputs in Message format.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "separator",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "\n\n"
+              },
+              "silent_errors": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Silent Errors",
+                "dynamic": false,
+                "info": "If true, errors will not raise an exception.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "silent_errors",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": false
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "DoclingRemote"
+        },
+        "dragging": false,
+        "id": "DoclingRemote-Dp3PX",
+        "measured": {
+          "height": 475,
+          "width": 320
+        },
+        "position": {
+          "x": -248.47065093890868,
+          "y": 1040.3002495758292
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "ExportDoclingDocument-zZdRg",
+          "node": {
+            "base_classes": [
+              "Data",
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Export DoclingDocument to markdown, html or other formats.",
+            "display_name": "Export DoclingDocument",
+            "documentation": "https://docling-project.github.io/docling/",
+            "edited": false,
+            "field_order": [
+              "data_inputs",
+              "export_format",
+              "image_mode",
+              "md_image_placeholder",
+              "md_page_break_placeholder",
+              "doc_key"
+            ],
+            "frozen": false,
+            "icon": "Docling",
+            "last_updated": "2025-10-04T01:42:10.290Z",
+            "legacy": false,
+            "lf_version": "1.6.3.dev0",
+            "metadata": {
+              "code_hash": "4de16ddd37ac",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "docling_core",
+                    "version": "2.48.4"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": "0.1.12.dev31"
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "lfx.components.docling.export_docling_document.ExportDoclingDocumentComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Exported data",
+                "group_outputs": false,
+                "method": "export_document",
+                "name": "data",
+                "options": null,
+                "required_inputs": null,
+                "selected": "Data",
+                "tool_mode": true,
+                "types": [
+                  "Data"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "group_outputs": false,
+                "method": "as_dataframe",
+                "name": "dataframe",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "from typing import Any\n\nfrom docling_core.types.doc import ImageRefMode\n\nfrom lfx.base.data.docling_utils import extract_docling_documents\nfrom lfx.custom import Component\nfrom lfx.io import DropdownInput, HandleInput, MessageTextInput, Output, StrInput\nfrom lfx.schema import Data, DataFrame\n\n\nclass ExportDoclingDocumentComponent(Component):\n    display_name: str = \"Export DoclingDocument\"\n    description: str = \"Export DoclingDocument to markdown, html or other formats.\"\n    documentation = \"https://docling-project.github.io/docling/\"\n    icon = \"Docling\"\n    name = \"ExportDoclingDocument\"\n\n    inputs = [\n        HandleInput(\n            name=\"data_inputs\",\n            display_name=\"Data or DataFrame\",\n            info=\"The data with documents to export.\",\n            input_types=[\"Data\", \"DataFrame\"],\n            required=True,\n        ),\n        DropdownInput(\n            name=\"export_format\",\n            display_name=\"Export format\",\n            options=[\"Markdown\", \"HTML\", \"Plaintext\", \"DocTags\"],\n            info=\"Select the export format to convert the input.\",\n            value=\"Markdown\",\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"image_mode\",\n            display_name=\"Image export mode\",\n            options=[\"placeholder\", \"embedded\"],\n            info=(\n                \"Specify how images are exported in the output. Placeholder will replace the images with a string, \"\n                \"whereas Embedded will include them as base64 encoded images.\"\n            ),\n            value=\"placeholder\",\n        ),\n        StrInput(\n            name=\"md_image_placeholder\",\n            display_name=\"Image placeholder\",\n            info=\"Specify the image placeholder for markdown exports.\",\n            value=\"<!-- image -->\",\n            advanced=True,\n        ),\n        StrInput(\n            name=\"md_page_break_placeholder\",\n            display_name=\"Page break placeholder\",\n            info=\"Add this placeholder betweek pages in the markdown output.\",\n            value=\"\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"doc_key\",\n            display_name=\"Doc Key\",\n            info=\"The key to use for the DoclingDocument column.\",\n            value=\"doc\",\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Exported data\", name=\"data\", method=\"export_document\"),\n        Output(display_name=\"DataFrame\", name=\"dataframe\", method=\"as_dataframe\"),\n    ]\n\n    def update_build_config(self, build_config: dict, field_value: Any, field_name: str | None = None) -> dict:\n        if field_name == \"export_format\" and field_value == \"Markdown\":\n            build_config[\"md_image_placeholder\"][\"show\"] = True\n            build_config[\"md_page_break_placeholder\"][\"show\"] = True\n            build_config[\"image_mode\"][\"show\"] = True\n        elif field_name == \"export_format\" and field_value == \"HTML\":\n            build_config[\"md_image_placeholder\"][\"show\"] = False\n            build_config[\"md_page_break_placeholder\"][\"show\"] = False\n            build_config[\"image_mode\"][\"show\"] = True\n        elif field_name == \"export_format\" and field_value in {\"Plaintext\", \"DocTags\"}:\n            build_config[\"md_image_placeholder\"][\"show\"] = False\n            build_config[\"md_page_break_placeholder\"][\"show\"] = False\n            build_config[\"image_mode\"][\"show\"] = False\n\n        return build_config\n\n    def export_document(self) -> list[Data]:\n        documents = extract_docling_documents(self.data_inputs, self.doc_key)\n\n        results: list[Data] = []\n        try:\n            image_mode = ImageRefMode(self.image_mode)\n            for doc in documents:\n                content = \"\"\n                if self.export_format == \"Markdown\":\n                    content = doc.export_to_markdown(\n                        image_mode=image_mode,\n                        image_placeholder=self.md_image_placeholder,\n                        page_break_placeholder=self.md_page_break_placeholder,\n                    )\n                elif self.export_format == \"HTML\":\n                    content = doc.export_to_html(image_mode=image_mode)\n                elif self.export_format == \"Plaintext\":\n                    content = doc.export_to_text()\n                elif self.export_format == \"DocTags\":\n                    content = doc.export_to_doctags()\n\n                results.append(Data(text=content))\n        except Exception as e:\n            msg = f\"Error splitting text: {e}\"\n            raise TypeError(msg) from e\n\n        return results\n\n    def as_dataframe(self) -> DataFrame:\n        return DataFrame(self.export_document())\n"
+              },
+              "data_inputs": {
+                "_input_type": "HandleInput",
+                "advanced": false,
+                "display_name": "Data or DataFrame",
+                "dynamic": false,
+                "info": "The data with documents to export.",
+                "input_types": [
+                  "Data",
+                  "DataFrame"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "data_inputs",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "doc_key": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "Doc Key",
+                "dynamic": false,
+                "info": "The key to use for the DoclingDocument column.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "doc_key",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "doc"
+              },
+              "export_format": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Export format",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Select the export format to convert the input.",
+                "name": "export_format",
+                "options": [
+                  "Markdown",
+                  "HTML",
+                  "Plaintext",
+                  "DocTags"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "real_time_refresh": true,
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "Markdown"
+              },
+              "image_mode": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Image export mode",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Specify how images are exported in the output. Placeholder will replace the images with a string, whereas Embedded will include them as base64 encoded images.",
+                "name": "image_mode",
+                "options": [
+                  "placeholder",
+                  "embedded"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "placeholder"
+              },
+              "md_image_placeholder": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "Image placeholder",
+                "dynamic": false,
+                "info": "Specify the image placeholder for markdown exports.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "md_image_placeholder",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "<!-- image -->"
+              },
+              "md_page_break_placeholder": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "Page break placeholder",
+                "dynamic": false,
+                "info": "Add this placeholder betweek pages in the markdown output.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "md_page_break_placeholder",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              }
+            },
+            "tool_mode": false
+          },
+          "selected_output": "dataframe",
+          "showNode": true,
+          "type": "ExportDoclingDocument"
+        },
+        "dragging": false,
+        "id": "ExportDoclingDocument-zZdRg",
+        "measured": {
+          "height": 347,
+          "width": 320
+        },
+        "position": {
+          "x": 134.00431977210877,
+          "y": 1065.2709317561028
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "DataFrameOperations-1BWXB",
+          "node": {
+            "base_classes": [
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Perform various operations on a DataFrame.",
+            "display_name": "DataFrame Operations",
+            "documentation": "https://docs.langflow.org/components-processing#dataframe-operations",
+            "edited": false,
+            "field_order": [
+              "df",
+              "operation",
+              "column_name",
+              "filter_value",
+              "filter_operator",
+              "ascending",
+              "new_column_name",
+              "new_column_value",
+              "columns_to_select",
+              "num_rows",
+              "replace_value",
+              "replacement_value"
+            ],
+            "frozen": false,
+            "icon": "table",
+            "last_updated": "2025-10-04T02:17:01.354Z",
+            "legacy": false,
+            "lf_version": "1.6.3.dev0",
+            "metadata": {
+              "code_hash": "b4d6b19b6eef",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "pandas",
+                    "version": "2.2.3"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": "0.1.12.dev31"
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "lfx.components.processing.dataframe_operations.DataFrameOperationsComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "group_outputs": false,
+                "method": "perform_operation",
+                "name": "output",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "ascending": {
+                "_input_type": "BoolInput",
+                "advanced": false,
+                "display_name": "Sort Ascending",
+                "dynamic": true,
+                "info": "Whether to sort in ascending order.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ascending",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "import pandas as pd\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import BoolInput, DataFrameInput, DropdownInput, IntInput, MessageTextInput, Output, StrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DataFrameOperationsComponent(Component):\n    display_name = \"DataFrame Operations\"\n    description = \"Perform various operations on a DataFrame.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#dataframe-operations\"\n    icon = \"table\"\n    name = \"DataFrameOperations\"\n\n    OPERATION_CHOICES = [\n        \"Add Column\",\n        \"Drop Column\",\n        \"Filter\",\n        \"Head\",\n        \"Rename Column\",\n        \"Replace Value\",\n        \"Select Columns\",\n        \"Sort\",\n        \"Tail\",\n        \"Drop Duplicates\",\n    ]\n\n    inputs = [\n        DataFrameInput(\n            name=\"df\",\n            display_name=\"DataFrame\",\n            info=\"The input DataFrame to operate on.\",\n            required=True,\n        ),\n        SortableListInput(\n            name=\"operation\",\n            display_name=\"Operation\",\n            placeholder=\"Select Operation\",\n            info=\"Select the DataFrame operation to perform.\",\n            options=[\n                {\"name\": \"Add Column\", \"icon\": \"plus\"},\n                {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n                {\"name\": \"Filter\", \"icon\": \"filter\"},\n                {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n                {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n                {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n                {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n                {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n                {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n                {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n            ],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        StrInput(\n            name=\"column_name\",\n            display_name=\"Column Name\",\n            info=\"The column name to use for the operation.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"filter_value\",\n            display_name=\"Filter Value\",\n            info=\"The value to filter rows by.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"filter_operator\",\n            display_name=\"Filter Operator\",\n            options=[\n                \"equals\",\n                \"not equals\",\n                \"contains\",\n                \"not contains\",\n                \"starts with\",\n                \"ends with\",\n                \"greater than\",\n                \"less than\",\n            ],\n            value=\"equals\",\n            info=\"The operator to apply for filtering rows.\",\n            advanced=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"ascending\",\n            display_name=\"Sort Ascending\",\n            info=\"Whether to sort in ascending order.\",\n            dynamic=True,\n            show=False,\n            value=True,\n        ),\n        StrInput(\n            name=\"new_column_name\",\n            display_name=\"New Column Name\",\n            info=\"The new column name when renaming or adding a column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"new_column_value\",\n            display_name=\"New Column Value\",\n            info=\"The value to populate the new column with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"columns_to_select\",\n            display_name=\"Columns to Select\",\n            dynamic=True,\n            is_list=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"num_rows\",\n            display_name=\"Number of Rows\",\n            info=\"Number of rows to return (for head/tail).\",\n            dynamic=True,\n            show=False,\n            value=5,\n        ),\n        MessageTextInput(\n            name=\"replace_value\",\n            display_name=\"Value to Replace\",\n            info=\"The value to replace in the column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"replacement_value\",\n            display_name=\"Replacement Value\",\n            info=\"The value to replace with.\",\n            dynamic=True,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(\n            display_name=\"DataFrame\",\n            name=\"output\",\n            method=\"perform_operation\",\n            info=\"The resulting DataFrame after the operation.\",\n        )\n    ]\n\n    def update_build_config(self, build_config, field_value, field_name=None):\n        dynamic_fields = [\n            \"column_name\",\n            \"filter_value\",\n            \"filter_operator\",\n            \"ascending\",\n            \"new_column_name\",\n            \"new_column_value\",\n            \"columns_to_select\",\n            \"num_rows\",\n            \"replace_value\",\n            \"replacement_value\",\n        ]\n        for field in dynamic_fields:\n            build_config[field][\"show\"] = False\n\n        if field_name == \"operation\":\n            # Handle SortableListInput format\n            if isinstance(field_value, list):\n                operation_name = field_value[0].get(\"name\", \"\") if field_value else \"\"\n            else:\n                operation_name = field_value or \"\"\n\n            # If no operation selected, all dynamic fields stay hidden (already set to False above)\n            if not operation_name:\n                return build_config\n\n            if operation_name == \"Filter\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"filter_value\"][\"show\"] = True\n                build_config[\"filter_operator\"][\"show\"] = True\n            elif operation_name == \"Sort\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"ascending\"][\"show\"] = True\n            elif operation_name == \"Drop Column\":\n                build_config[\"column_name\"][\"show\"] = True\n            elif operation_name == \"Rename Column\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"new_column_name\"][\"show\"] = True\n            elif operation_name == \"Add Column\":\n                build_config[\"new_column_name\"][\"show\"] = True\n                build_config[\"new_column_value\"][\"show\"] = True\n            elif operation_name == \"Select Columns\":\n                build_config[\"columns_to_select\"][\"show\"] = True\n            elif operation_name in {\"Head\", \"Tail\"}:\n                build_config[\"num_rows\"][\"show\"] = True\n            elif operation_name == \"Replace Value\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"replace_value\"][\"show\"] = True\n                build_config[\"replacement_value\"][\"show\"] = True\n            elif operation_name == \"Drop Duplicates\":\n                build_config[\"column_name\"][\"show\"] = True\n\n        return build_config\n\n    def perform_operation(self) -> DataFrame:\n        df_copy = self.df.copy()\n\n        # Handle SortableListInput format for operation\n        operation_input = getattr(self, \"operation\", [])\n        if isinstance(operation_input, list) and len(operation_input) > 0:\n            op = operation_input[0].get(\"name\", \"\")\n        else:\n            op = \"\"\n\n        # If no operation selected, return original DataFrame\n        if not op:\n            return df_copy\n\n        if op == \"Filter\":\n            return self.filter_rows_by_value(df_copy)\n        if op == \"Sort\":\n            return self.sort_by_column(df_copy)\n        if op == \"Drop Column\":\n            return self.drop_column(df_copy)\n        if op == \"Rename Column\":\n            return self.rename_column(df_copy)\n        if op == \"Add Column\":\n            return self.add_column(df_copy)\n        if op == \"Select Columns\":\n            return self.select_columns(df_copy)\n        if op == \"Head\":\n            return self.head(df_copy)\n        if op == \"Tail\":\n            return self.tail(df_copy)\n        if op == \"Replace Value\":\n            return self.replace_values(df_copy)\n        if op == \"Drop Duplicates\":\n            return self.drop_duplicates(df_copy)\n        msg = f\"Unsupported operation: {op}\"\n        logger.error(msg)\n        raise ValueError(msg)\n\n    def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        filter_value = self.filter_value\n\n        # Handle regular DropdownInput format (just a string value)\n        operator = getattr(self, \"filter_operator\", \"equals\")  # Default to equals for backward compatibility\n\n        if operator == \"equals\":\n            mask = column == filter_value\n        elif operator == \"not equals\":\n            mask = column != filter_value\n        elif operator == \"contains\":\n            mask = column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"not contains\":\n            mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"starts with\":\n            mask = column.astype(str).str.startswith(str(filter_value), na=False)\n        elif operator == \"ends with\":\n            mask = column.astype(str).str.endswith(str(filter_value), na=False)\n        elif operator == \"greater than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column > numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) > str(filter_value)\n        elif operator == \"less than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column < numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) < str(filter_value)\n        else:\n            mask = column == filter_value  # Fallback to equals\n\n        return DataFrame(df[mask])\n\n    def sort_by_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n    def drop_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop(columns=[self.column_name]))\n\n    def rename_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n    def add_column(self, df: DataFrame) -> DataFrame:\n        df[self.new_column_name] = [self.new_column_value] * len(df)\n        return DataFrame(df)\n\n    def select_columns(self, df: DataFrame) -> DataFrame:\n        columns = [col.strip() for col in self.columns_to_select]\n        return DataFrame(df[columns])\n\n    def head(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.head(self.num_rows))\n\n    def tail(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.tail(self.num_rows))\n\n    def replace_values(self, df: DataFrame) -> DataFrame:\n        df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n        return DataFrame(df)\n\n    def drop_duplicates(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop_duplicates(subset=self.column_name))\n"
+              },
+              "column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Column Name",
+                "dynamic": true,
+                "info": "The column name to use for the operation.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "column_name",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "columns_to_select": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Columns to Select",
+                "dynamic": true,
+                "info": "",
+                "list": true,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "columns_to_select",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "df": {
+                "_input_type": "DataFrameInput",
+                "advanced": false,
+                "display_name": "DataFrame",
+                "dynamic": false,
+                "info": "The input DataFrame to operate on.",
+                "input_types": [
+                  "DataFrame"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "df",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "filter_operator": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Filter Operator",
+                "dynamic": true,
+                "external_options": {},
+                "info": "The operator to apply for filtering rows.",
+                "name": "filter_operator",
+                "options": [
+                  "equals",
+                  "not equals",
+                  "contains",
+                  "not contains",
+                  "starts with",
+                  "ends with",
+                  "greater than",
+                  "less than"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "equals"
+              },
+              "filter_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Filter Value",
+                "dynamic": true,
+                "info": "The value to filter rows by.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "filter_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "new_column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "New Column Name",
+                "dynamic": true,
+                "info": "The new column name when renaming or adding a column.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "new_column_name",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "filename"
+              },
+              "new_column_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "New Column Value",
+                "dynamic": true,
+                "info": "The value to populate the new column with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": true,
+                "name": "new_column_value",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "FILENAME"
+              },
+              "num_rows": {
+                "_input_type": "IntInput",
+                "advanced": false,
+                "display_name": "Number of Rows",
+                "dynamic": true,
+                "info": "Number of rows to return (for head/tail).",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "num_rows",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 5
+              },
+              "operation": {
+                "_input_type": "SortableListInput",
+                "advanced": false,
+                "display_name": "Operation",
+                "dynamic": false,
+                "info": "Select the DataFrame operation to perform.",
+                "limit": 1,
+                "name": "operation",
+                "options": [
+                  {
+                    "icon": "plus",
+                    "name": "Add Column"
+                  },
+                  {
+                    "icon": "minus",
+                    "name": "Drop Column"
+                  },
+                  {
+                    "icon": "filter",
+                    "name": "Filter"
+                  },
+                  {
+                    "icon": "arrow-up",
+                    "name": "Head"
+                  },
+                  {
+                    "icon": "pencil",
+                    "name": "Rename Column"
+                  },
+                  {
+                    "icon": "replace",
+                    "name": "Replace Value"
+                  },
+                  {
+                    "icon": "columns",
+                    "name": "Select Columns"
+                  },
+                  {
+                    "icon": "arrow-up-down",
+                    "name": "Sort"
+                  },
+                  {
+                    "icon": "arrow-down",
+                    "name": "Tail"
+                  },
+                  {
+                    "icon": "copy-x",
+                    "name": "Drop Duplicates"
+                  }
+                ],
+                "placeholder": "Select Operation",
+                "real_time_refresh": true,
+                "required": false,
+                "search_category": [],
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "sortableList",
+                "value": [
+                  {
+                    "chosen": false,
+                    "icon": "plus",
+                    "name": "Add Column",
+                    "selected": false
+                  }
+                ]
+              },
+              "replace_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Value to Replace",
+                "dynamic": true,
+                "info": "The value to replace in the column.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replace_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "replacement_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Replacement Value",
+                "dynamic": true,
+                "info": "The value to replace with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replacement_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "DataFrameOperations"
+        },
+        "dragging": false,
+        "id": "DataFrameOperations-1BWXB",
+        "measured": {
+          "height": 399,
+          "width": 320
+        },
+        "position": {
+          "x": 513.7675419899799,
+          "y": 1088.8324804581666
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "DataFrameOperations-N80fC",
+          "node": {
+            "base_classes": [
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Perform various operations on a DataFrame.",
+            "display_name": "DataFrame Operations",
+            "documentation": "https://docs.langflow.org/components-processing#dataframe-operations",
+            "edited": false,
+            "field_order": [
+              "df",
+              "operation",
+              "column_name",
+              "filter_value",
+              "filter_operator",
+              "ascending",
+              "new_column_name",
+              "new_column_value",
+              "columns_to_select",
+              "num_rows",
+              "replace_value",
+              "replacement_value"
+            ],
+            "frozen": false,
+            "icon": "table",
+            "last_updated": "2025-10-04T02:17:01.355Z",
+            "legacy": false,
+            "lf_version": "1.6.3.dev0",
+            "metadata": {
+              "code_hash": "b4d6b19b6eef",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "pandas",
+                    "version": "2.2.3"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": "0.1.12.dev31"
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "lfx.components.processing.dataframe_operations.DataFrameOperationsComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "group_outputs": false,
+                "method": "perform_operation",
+                "name": "output",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "ascending": {
+                "_input_type": "BoolInput",
+                "advanced": false,
+                "display_name": "Sort Ascending",
+                "dynamic": true,
+                "info": "Whether to sort in ascending order.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ascending",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "import pandas as pd\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import BoolInput, DataFrameInput, DropdownInput, IntInput, MessageTextInput, Output, StrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DataFrameOperationsComponent(Component):\n    display_name = \"DataFrame Operations\"\n    description = \"Perform various operations on a DataFrame.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#dataframe-operations\"\n    icon = \"table\"\n    name = \"DataFrameOperations\"\n\n    OPERATION_CHOICES = [\n        \"Add Column\",\n        \"Drop Column\",\n        \"Filter\",\n        \"Head\",\n        \"Rename Column\",\n        \"Replace Value\",\n        \"Select Columns\",\n        \"Sort\",\n        \"Tail\",\n        \"Drop Duplicates\",\n    ]\n\n    inputs = [\n        DataFrameInput(\n            name=\"df\",\n            display_name=\"DataFrame\",\n            info=\"The input DataFrame to operate on.\",\n            required=True,\n        ),\n        SortableListInput(\n            name=\"operation\",\n            display_name=\"Operation\",\n            placeholder=\"Select Operation\",\n            info=\"Select the DataFrame operation to perform.\",\n            options=[\n                {\"name\": \"Add Column\", \"icon\": \"plus\"},\n                {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n                {\"name\": \"Filter\", \"icon\": \"filter\"},\n                {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n                {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n                {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n                {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n                {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n                {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n                {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n            ],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        StrInput(\n            name=\"column_name\",\n            display_name=\"Column Name\",\n            info=\"The column name to use for the operation.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"filter_value\",\n            display_name=\"Filter Value\",\n            info=\"The value to filter rows by.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"filter_operator\",\n            display_name=\"Filter Operator\",\n            options=[\n                \"equals\",\n                \"not equals\",\n                \"contains\",\n                \"not contains\",\n                \"starts with\",\n                \"ends with\",\n                \"greater than\",\n                \"less than\",\n            ],\n            value=\"equals\",\n            info=\"The operator to apply for filtering rows.\",\n            advanced=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"ascending\",\n            display_name=\"Sort Ascending\",\n            info=\"Whether to sort in ascending order.\",\n            dynamic=True,\n            show=False,\n            value=True,\n        ),\n        StrInput(\n            name=\"new_column_name\",\n            display_name=\"New Column Name\",\n            info=\"The new column name when renaming or adding a column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"new_column_value\",\n            display_name=\"New Column Value\",\n            info=\"The value to populate the new column with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"columns_to_select\",\n            display_name=\"Columns to Select\",\n            dynamic=True,\n            is_list=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"num_rows\",\n            display_name=\"Number of Rows\",\n            info=\"Number of rows to return (for head/tail).\",\n            dynamic=True,\n            show=False,\n            value=5,\n        ),\n        MessageTextInput(\n            name=\"replace_value\",\n            display_name=\"Value to Replace\",\n            info=\"The value to replace in the column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"replacement_value\",\n            display_name=\"Replacement Value\",\n            info=\"The value to replace with.\",\n            dynamic=True,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(\n            display_name=\"DataFrame\",\n            name=\"output\",\n            method=\"perform_operation\",\n            info=\"The resulting DataFrame after the operation.\",\n        )\n    ]\n\n    def update_build_config(self, build_config, field_value, field_name=None):\n        dynamic_fields = [\n            \"column_name\",\n            \"filter_value\",\n            \"filter_operator\",\n            \"ascending\",\n            \"new_column_name\",\n            \"new_column_value\",\n            \"columns_to_select\",\n            \"num_rows\",\n            \"replace_value\",\n            \"replacement_value\",\n        ]\n        for field in dynamic_fields:\n            build_config[field][\"show\"] = False\n\n        if field_name == \"operation\":\n            # Handle SortableListInput format\n            if isinstance(field_value, list):\n                operation_name = field_value[0].get(\"name\", \"\") if field_value else \"\"\n            else:\n                operation_name = field_value or \"\"\n\n            # If no operation selected, all dynamic fields stay hidden (already set to False above)\n            if not operation_name:\n                return build_config\n\n            if operation_name == \"Filter\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"filter_value\"][\"show\"] = True\n                build_config[\"filter_operator\"][\"show\"] = True\n            elif operation_name == \"Sort\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"ascending\"][\"show\"] = True\n            elif operation_name == \"Drop Column\":\n                build_config[\"column_name\"][\"show\"] = True\n            elif operation_name == \"Rename Column\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"new_column_name\"][\"show\"] = True\n            elif operation_name == \"Add Column\":\n                build_config[\"new_column_name\"][\"show\"] = True\n                build_config[\"new_column_value\"][\"show\"] = True\n            elif operation_name == \"Select Columns\":\n                build_config[\"columns_to_select\"][\"show\"] = True\n            elif operation_name in {\"Head\", \"Tail\"}:\n                build_config[\"num_rows\"][\"show\"] = True\n            elif operation_name == \"Replace Value\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"replace_value\"][\"show\"] = True\n                build_config[\"replacement_value\"][\"show\"] = True\n            elif operation_name == \"Drop Duplicates\":\n                build_config[\"column_name\"][\"show\"] = True\n\n        return build_config\n\n    def perform_operation(self) -> DataFrame:\n        df_copy = self.df.copy()\n\n        # Handle SortableListInput format for operation\n        operation_input = getattr(self, \"operation\", [])\n        if isinstance(operation_input, list) and len(operation_input) > 0:\n            op = operation_input[0].get(\"name\", \"\")\n        else:\n            op = \"\"\n\n        # If no operation selected, return original DataFrame\n        if not op:\n            return df_copy\n\n        if op == \"Filter\":\n            return self.filter_rows_by_value(df_copy)\n        if op == \"Sort\":\n            return self.sort_by_column(df_copy)\n        if op == \"Drop Column\":\n            return self.drop_column(df_copy)\n        if op == \"Rename Column\":\n            return self.rename_column(df_copy)\n        if op == \"Add Column\":\n            return self.add_column(df_copy)\n        if op == \"Select Columns\":\n            return self.select_columns(df_copy)\n        if op == \"Head\":\n            return self.head(df_copy)\n        if op == \"Tail\":\n            return self.tail(df_copy)\n        if op == \"Replace Value\":\n            return self.replace_values(df_copy)\n        if op == \"Drop Duplicates\":\n            return self.drop_duplicates(df_copy)\n        msg = f\"Unsupported operation: {op}\"\n        logger.error(msg)\n        raise ValueError(msg)\n\n    def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        filter_value = self.filter_value\n\n        # Handle regular DropdownInput format (just a string value)\n        operator = getattr(self, \"filter_operator\", \"equals\")  # Default to equals for backward compatibility\n\n        if operator == \"equals\":\n            mask = column == filter_value\n        elif operator == \"not equals\":\n            mask = column != filter_value\n        elif operator == \"contains\":\n            mask = column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"not contains\":\n            mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"starts with\":\n            mask = column.astype(str).str.startswith(str(filter_value), na=False)\n        elif operator == \"ends with\":\n            mask = column.astype(str).str.endswith(str(filter_value), na=False)\n        elif operator == \"greater than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column > numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) > str(filter_value)\n        elif operator == \"less than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column < numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) < str(filter_value)\n        else:\n            mask = column == filter_value  # Fallback to equals\n\n        return DataFrame(df[mask])\n\n    def sort_by_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n    def drop_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop(columns=[self.column_name]))\n\n    def rename_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n    def add_column(self, df: DataFrame) -> DataFrame:\n        df[self.new_column_name] = [self.new_column_value] * len(df)\n        return DataFrame(df)\n\n    def select_columns(self, df: DataFrame) -> DataFrame:\n        columns = [col.strip() for col in self.columns_to_select]\n        return DataFrame(df[columns])\n\n    def head(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.head(self.num_rows))\n\n    def tail(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.tail(self.num_rows))\n\n    def replace_values(self, df: DataFrame) -> DataFrame:\n        df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n        return DataFrame(df)\n\n    def drop_duplicates(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop_duplicates(subset=self.column_name))\n"
+              },
+              "column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Column Name",
+                "dynamic": true,
+                "info": "The column name to use for the operation.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "column_name",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "columns_to_select": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Columns to Select",
+                "dynamic": true,
+                "info": "",
+                "list": true,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "columns_to_select",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "df": {
+                "_input_type": "DataFrameInput",
+                "advanced": false,
+                "display_name": "DataFrame",
+                "dynamic": false,
+                "info": "The input DataFrame to operate on.",
+                "input_types": [
+                  "DataFrame"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "df",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "filter_operator": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Filter Operator",
+                "dynamic": true,
+                "external_options": {},
+                "info": "The operator to apply for filtering rows.",
+                "name": "filter_operator",
+                "options": [
+                  "equals",
+                  "not equals",
+                  "contains",
+                  "not contains",
+                  "starts with",
+                  "ends with",
+                  "greater than",
+                  "less than"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "equals"
+              },
+              "filter_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Filter Value",
+                "dynamic": true,
+                "info": "The value to filter rows by.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "filter_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "new_column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "New Column Name",
+                "dynamic": true,
+                "info": "The new column name when renaming or adding a column.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "new_column_name",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "mimetype"
+              },
+              "new_column_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "New Column Value",
+                "dynamic": true,
+                "info": "The value to populate the new column with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": true,
+                "name": "new_column_value",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "MIMETYPE"
+              },
+              "num_rows": {
+                "_input_type": "IntInput",
+                "advanced": false,
+                "display_name": "Number of Rows",
+                "dynamic": true,
+                "info": "Number of rows to return (for head/tail).",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "num_rows",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 5
+              },
+              "operation": {
+                "_input_type": "SortableListInput",
+                "advanced": false,
+                "display_name": "Operation",
+                "dynamic": false,
+                "info": "Select the DataFrame operation to perform.",
+                "limit": 1,
+                "name": "operation",
+                "options": [
+                  {
+                    "icon": "plus",
+                    "name": "Add Column"
+                  },
+                  {
+                    "icon": "minus",
+                    "name": "Drop Column"
+                  },
+                  {
+                    "icon": "filter",
+                    "name": "Filter"
+                  },
+                  {
+                    "icon": "arrow-up",
+                    "name": "Head"
+                  },
+                  {
+                    "icon": "pencil",
+                    "name": "Rename Column"
+                  },
+                  {
+                    "icon": "replace",
+                    "name": "Replace Value"
+                  },
+                  {
+                    "icon": "columns",
+                    "name": "Select Columns"
+                  },
+                  {
+                    "icon": "arrow-up-down",
+                    "name": "Sort"
+                  },
+                  {
+                    "icon": "arrow-down",
+                    "name": "Tail"
+                  },
+                  {
+                    "icon": "copy-x",
+                    "name": "Drop Duplicates"
+                  }
+                ],
+                "placeholder": "Select Operation",
+                "real_time_refresh": true,
+                "required": false,
+                "search_category": [],
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "sortableList",
+                "value": [
+                  {
+                    "chosen": false,
+                    "icon": "plus",
+                    "name": "Add Column",
+                    "selected": false
+                  }
+                ]
+              },
+              "replace_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Value to Replace",
+                "dynamic": true,
+                "info": "The value to replace in the column.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replace_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "replacement_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Replacement Value",
+                "dynamic": true,
+                "info": "The value to replace with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replacement_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "DataFrameOperations"
+        },
+        "dragging": false,
+        "id": "DataFrameOperations-N80fC",
+        "measured": {
+          "height": 399,
+          "width": 320
+        },
+        "position": {
+          "x": 1314.7870797625949,
+          "y": 1135.9990962860586
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "DataFrameOperations-9vMrp",
+          "node": {
+            "base_classes": [
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Perform various operations on a DataFrame.",
+            "display_name": "DataFrame Operations",
+            "documentation": "https://docs.langflow.org/components-processing#dataframe-operations",
+            "edited": false,
+            "field_order": [
+              "df",
+              "operation",
+              "column_name",
+              "filter_value",
+              "filter_operator",
+              "ascending",
+              "new_column_name",
+              "new_column_value",
+              "columns_to_select",
+              "num_rows",
+              "replace_value",
+              "replacement_value"
+            ],
+            "frozen": false,
+            "icon": "table",
+            "last_updated": "2025-10-04T02:17:01.355Z",
+            "legacy": false,
+            "lf_version": "1.6.3.dev0",
+            "metadata": {
+              "code_hash": "b4d6b19b6eef",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "pandas",
+                    "version": "2.2.3"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": "0.1.12.dev31"
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "lfx.components.processing.dataframe_operations.DataFrameOperationsComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "group_outputs": false,
+                "method": "perform_operation",
+                "name": "output",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "ascending": {
+                "_input_type": "BoolInput",
+                "advanced": false,
+                "display_name": "Sort Ascending",
+                "dynamic": true,
+                "info": "Whether to sort in ascending order.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ascending",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "import pandas as pd\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import BoolInput, DataFrameInput, DropdownInput, IntInput, MessageTextInput, Output, StrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DataFrameOperationsComponent(Component):\n    display_name = \"DataFrame Operations\"\n    description = \"Perform various operations on a DataFrame.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#dataframe-operations\"\n    icon = \"table\"\n    name = \"DataFrameOperations\"\n\n    OPERATION_CHOICES = [\n        \"Add Column\",\n        \"Drop Column\",\n        \"Filter\",\n        \"Head\",\n        \"Rename Column\",\n        \"Replace Value\",\n        \"Select Columns\",\n        \"Sort\",\n        \"Tail\",\n        \"Drop Duplicates\",\n    ]\n\n    inputs = [\n        DataFrameInput(\n            name=\"df\",\n            display_name=\"DataFrame\",\n            info=\"The input DataFrame to operate on.\",\n            required=True,\n        ),\n        SortableListInput(\n            name=\"operation\",\n            display_name=\"Operation\",\n            placeholder=\"Select Operation\",\n            info=\"Select the DataFrame operation to perform.\",\n            options=[\n                {\"name\": \"Add Column\", \"icon\": \"plus\"},\n                {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n                {\"name\": \"Filter\", \"icon\": \"filter\"},\n                {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n                {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n                {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n                {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n                {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n                {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n                {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n            ],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        StrInput(\n            name=\"column_name\",\n            display_name=\"Column Name\",\n            info=\"The column name to use for the operation.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"filter_value\",\n            display_name=\"Filter Value\",\n            info=\"The value to filter rows by.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"filter_operator\",\n            display_name=\"Filter Operator\",\n            options=[\n                \"equals\",\n                \"not equals\",\n                \"contains\",\n                \"not contains\",\n                \"starts with\",\n                \"ends with\",\n                \"greater than\",\n                \"less than\",\n            ],\n            value=\"equals\",\n            info=\"The operator to apply for filtering rows.\",\n            advanced=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"ascending\",\n            display_name=\"Sort Ascending\",\n            info=\"Whether to sort in ascending order.\",\n            dynamic=True,\n            show=False,\n            value=True,\n        ),\n        StrInput(\n            name=\"new_column_name\",\n            display_name=\"New Column Name\",\n            info=\"The new column name when renaming or adding a column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"new_column_value\",\n            display_name=\"New Column Value\",\n            info=\"The value to populate the new column with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"columns_to_select\",\n            display_name=\"Columns to Select\",\n            dynamic=True,\n            is_list=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"num_rows\",\n            display_name=\"Number of Rows\",\n            info=\"Number of rows to return (for head/tail).\",\n            dynamic=True,\n            show=False,\n            value=5,\n        ),\n        MessageTextInput(\n            name=\"replace_value\",\n            display_name=\"Value to Replace\",\n            info=\"The value to replace in the column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"replacement_value\",\n            display_name=\"Replacement Value\",\n            info=\"The value to replace with.\",\n            dynamic=True,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(\n            display_name=\"DataFrame\",\n            name=\"output\",\n            method=\"perform_operation\",\n            info=\"The resulting DataFrame after the operation.\",\n        )\n    ]\n\n    def update_build_config(self, build_config, field_value, field_name=None):\n        dynamic_fields = [\n            \"column_name\",\n            \"filter_value\",\n            \"filter_operator\",\n            \"ascending\",\n            \"new_column_name\",\n            \"new_column_value\",\n            \"columns_to_select\",\n            \"num_rows\",\n            \"replace_value\",\n            \"replacement_value\",\n        ]\n        for field in dynamic_fields:\n            build_config[field][\"show\"] = False\n\n        if field_name == \"operation\":\n            # Handle SortableListInput format\n            if isinstance(field_value, list):\n                operation_name = field_value[0].get(\"name\", \"\") if field_value else \"\"\n            else:\n                operation_name = field_value or \"\"\n\n            # If no operation selected, all dynamic fields stay hidden (already set to False above)\n            if not operation_name:\n                return build_config\n\n            if operation_name == \"Filter\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"filter_value\"][\"show\"] = True\n                build_config[\"filter_operator\"][\"show\"] = True\n            elif operation_name == \"Sort\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"ascending\"][\"show\"] = True\n            elif operation_name == \"Drop Column\":\n                build_config[\"column_name\"][\"show\"] = True\n            elif operation_name == \"Rename Column\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"new_column_name\"][\"show\"] = True\n            elif operation_name == \"Add Column\":\n                build_config[\"new_column_name\"][\"show\"] = True\n                build_config[\"new_column_value\"][\"show\"] = True\n            elif operation_name == \"Select Columns\":\n                build_config[\"columns_to_select\"][\"show\"] = True\n            elif operation_name in {\"Head\", \"Tail\"}:\n                build_config[\"num_rows\"][\"show\"] = True\n            elif operation_name == \"Replace Value\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"replace_value\"][\"show\"] = True\n                build_config[\"replacement_value\"][\"show\"] = True\n            elif operation_name == \"Drop Duplicates\":\n                build_config[\"column_name\"][\"show\"] = True\n\n        return build_config\n\n    def perform_operation(self) -> DataFrame:\n        df_copy = self.df.copy()\n\n        # Handle SortableListInput format for operation\n        operation_input = getattr(self, \"operation\", [])\n        if isinstance(operation_input, list) and len(operation_input) > 0:\n            op = operation_input[0].get(\"name\", \"\")\n        else:\n            op = \"\"\n\n        # If no operation selected, return original DataFrame\n        if not op:\n            return df_copy\n\n        if op == \"Filter\":\n            return self.filter_rows_by_value(df_copy)\n        if op == \"Sort\":\n            return self.sort_by_column(df_copy)\n        if op == \"Drop Column\":\n            return self.drop_column(df_copy)\n        if op == \"Rename Column\":\n            return self.rename_column(df_copy)\n        if op == \"Add Column\":\n            return self.add_column(df_copy)\n        if op == \"Select Columns\":\n            return self.select_columns(df_copy)\n        if op == \"Head\":\n            return self.head(df_copy)\n        if op == \"Tail\":\n            return self.tail(df_copy)\n        if op == \"Replace Value\":\n            return self.replace_values(df_copy)\n        if op == \"Drop Duplicates\":\n            return self.drop_duplicates(df_copy)\n        msg = f\"Unsupported operation: {op}\"\n        logger.error(msg)\n        raise ValueError(msg)\n\n    def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        filter_value = self.filter_value\n\n        # Handle regular DropdownInput format (just a string value)\n        operator = getattr(self, \"filter_operator\", \"equals\")  # Default to equals for backward compatibility\n\n        if operator == \"equals\":\n            mask = column == filter_value\n        elif operator == \"not equals\":\n            mask = column != filter_value\n        elif operator == \"contains\":\n            mask = column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"not contains\":\n            mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"starts with\":\n            mask = column.astype(str).str.startswith(str(filter_value), na=False)\n        elif operator == \"ends with\":\n            mask = column.astype(str).str.endswith(str(filter_value), na=False)\n        elif operator == \"greater than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column > numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) > str(filter_value)\n        elif operator == \"less than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column < numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) < str(filter_value)\n        else:\n            mask = column == filter_value  # Fallback to equals\n\n        return DataFrame(df[mask])\n\n    def sort_by_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n    def drop_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop(columns=[self.column_name]))\n\n    def rename_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n    def add_column(self, df: DataFrame) -> DataFrame:\n        df[self.new_column_name] = [self.new_column_value] * len(df)\n        return DataFrame(df)\n\n    def select_columns(self, df: DataFrame) -> DataFrame:\n        columns = [col.strip() for col in self.columns_to_select]\n        return DataFrame(df[columns])\n\n    def head(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.head(self.num_rows))\n\n    def tail(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.tail(self.num_rows))\n\n    def replace_values(self, df: DataFrame) -> DataFrame:\n        df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n        return DataFrame(df)\n\n    def drop_duplicates(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop_duplicates(subset=self.column_name))\n"
+              },
+              "column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Column Name",
+                "dynamic": true,
+                "info": "The column name to use for the operation.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "column_name",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "columns_to_select": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Columns to Select",
+                "dynamic": true,
+                "info": "",
+                "list": true,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "columns_to_select",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "df": {
+                "_input_type": "DataFrameInput",
+                "advanced": false,
+                "display_name": "DataFrame",
+                "dynamic": false,
+                "info": "The input DataFrame to operate on.",
+                "input_types": [
+                  "DataFrame"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "df",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "filter_operator": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Filter Operator",
+                "dynamic": true,
+                "external_options": {},
+                "info": "The operator to apply for filtering rows.",
+                "name": "filter_operator",
+                "options": [
+                  "equals",
+                  "not equals",
+                  "contains",
+                  "not contains",
+                  "starts with",
+                  "ends with",
+                  "greater than",
+                  "less than"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "equals"
+              },
+              "filter_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Filter Value",
+                "dynamic": true,
+                "info": "The value to filter rows by.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "filter_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "new_column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "New Column Name",
+                "dynamic": true,
+                "info": "The new column name when renaming or adding a column.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "new_column_name",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "file_size"
+              },
+              "new_column_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "New Column Value",
+                "dynamic": true,
+                "info": "The value to populate the new column with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": true,
+                "name": "new_column_value",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "FILESIZE"
+              },
+              "num_rows": {
+                "_input_type": "IntInput",
+                "advanced": false,
+                "display_name": "Number of Rows",
+                "dynamic": true,
+                "info": "Number of rows to return (for head/tail).",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "num_rows",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 5
+              },
+              "operation": {
+                "_input_type": "SortableListInput",
+                "advanced": false,
+                "display_name": "Operation",
+                "dynamic": false,
+                "info": "Select the DataFrame operation to perform.",
+                "limit": 1,
+                "name": "operation",
+                "options": [
+                  {
+                    "icon": "plus",
+                    "name": "Add Column"
+                  },
+                  {
+                    "icon": "minus",
+                    "name": "Drop Column"
+                  },
+                  {
+                    "icon": "filter",
+                    "name": "Filter"
+                  },
+                  {
+                    "icon": "arrow-up",
+                    "name": "Head"
+                  },
+                  {
+                    "icon": "pencil",
+                    "name": "Rename Column"
+                  },
+                  {
+                    "icon": "replace",
+                    "name": "Replace Value"
+                  },
+                  {
+                    "icon": "columns",
+                    "name": "Select Columns"
+                  },
+                  {
+                    "icon": "arrow-up-down",
+                    "name": "Sort"
+                  },
+                  {
+                    "icon": "arrow-down",
+                    "name": "Tail"
+                  },
+                  {
+                    "icon": "copy-x",
+                    "name": "Drop Duplicates"
+                  }
+                ],
+                "placeholder": "Select Operation",
+                "real_time_refresh": true,
+                "required": false,
+                "search_category": [],
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "sortableList",
+                "value": [
+                  {
+                    "chosen": false,
+                    "icon": "plus",
+                    "name": "Add Column",
+                    "selected": false
+                  }
+                ]
+              },
+              "replace_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Value to Replace",
+                "dynamic": true,
+                "info": "The value to replace in the column.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replace_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "replacement_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Replacement Value",
+                "dynamic": true,
+                "info": "The value to replace with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replacement_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "DataFrameOperations"
+        },
+        "dragging": false,
+        "id": "DataFrameOperations-9vMrp",
+        "measured": {
+          "height": 399,
+          "width": 320
+        },
+        "position": {
+          "x": 956.3345099816677,
+          "y": 1077.3618931222093
         },
         "selected": false,
         "type": "genericNode"
       }
     ],
     "viewport": {
-      "x": -311.42857930212404,
-      "y": -532.9060284457172,
-      "zoom": 0.5361317364942912
+      "x": 227.3737875665738,
+      "y": -299.1651660660417,
+      "zoom": 0.43587407227641217
     }
   },
   "description": "Load your data for chat context with Retrieval Augmented Generation.",
   "endpoint_name": null,
   "id": "5488df7c-b93f-4f87-a446-b67028bc0813",
   "is_component": false,
-  "last_tested_version": "1.6.0",
+  "last_tested_version": "1.6.3.dev0",
   "name": "OpenSearch Ingestion Flow",
   "tags": [
     "openai",
diff --git a/flows/openrag_agent.json b/flows/openrag_agent.json
index 9e1f33cc..c08a305c 100644
--- a/flows/openrag_agent.json
+++ b/flows/openrag_agent.json
@@ -144,6 +144,8 @@
         "targetHandle": "{œfieldNameœ:œagent_llmœ,œidœ:œAgent-crjWfœ,œinputTypesœ:[œLanguageModelœ],œtypeœ:œstrœ}"
       },
       {
+        "animated": false,
+        "className": "",
         "data": {
           "sourceHandle": {
             "dataType": "TextInput",
@@ -163,6 +165,7 @@
           }
         },
         "id": "xy-edge__TextInput-aHsQb{œdataTypeœ:œTextInputœ,œidœ:œTextInput-aHsQbœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-OpenSearch-iYfjf{œfieldNameœ:œfilter_expressionœ,œidœ:œOpenSearch-iYfjfœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
+        "selected": false,
         "source": "TextInput-aHsQb",
         "sourceHandle": "{œdataTypeœ:œTextInputœ,œidœ:œTextInput-aHsQbœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}",
         "target": "OpenSearch-iYfjf",
@@ -727,7 +730,7 @@
             ],
             "frozen": false,
             "icon": "OpenSearch",
-            "last_updated": "2025-10-02T20:05:34.814Z",
+            "last_updated": "2025-10-04T05:41:33.344Z",
             "legacy": false,
             "lf_version": "1.6.0",
             "metadata": {
@@ -1381,7 +1384,7 @@
             ],
             "frozen": false,
             "icon": "binary",
-            "last_updated": "2025-10-02T20:05:34.815Z",
+            "last_updated": "2025-10-04T05:41:33.345Z",
             "legacy": false,
             "lf_version": "1.6.0",
             "metadata": {
@@ -1660,7 +1663,7 @@
         },
         "position": {
           "x": 727.4791597769406,
-          "y": 518.0820551650631
+          "y": 416.82609966052854
         },
         "selected": false,
         "type": "genericNode"
@@ -1706,7 +1709,7 @@
             ],
             "frozen": false,
             "icon": "bot",
-            "last_updated": "2025-10-02T20:05:34.872Z",
+            "last_updated": "2025-10-04T05:41:33.399Z",
             "legacy": false,
             "lf_version": "1.6.0",
             "metadata": {
@@ -2245,7 +2248,7 @@
             ],
             "frozen": false,
             "icon": "brain-circuit",
-            "last_updated": "2025-10-02T20:05:34.815Z",
+            "last_updated": "2025-10-04T05:41:33.347Z",
             "legacy": false,
             "lf_version": "1.6.0",
             "metadata": {
@@ -2551,17 +2554,17 @@
       }
     ],
     "viewport": {
-      "x": -237.0727605845459,
+      "x": -149.48015964664273,
       "y": 154.6885920024542,
       "zoom": 0.602433700773958
     }
   },
-  "description": "OpenRAG Open Search Agent",
+  "description": "OpenRAG OpenSearch Agent",
   "endpoint_name": null,
   "id": "1098eea1-6649-4e1d-aed1-b77249fb8dd0",
   "is_component": false,
-  "last_tested_version": "1.6.0",
-  "name": "OpenRAG Open Search Agent",
+  "last_tested_version": "1.6.3.dev0",
+  "name": "OpenRAG OpenSearch Agent",
   "tags": [
     "assistants",
     "agents"
diff --git a/flows/openrag_nudges.json b/flows/openrag_nudges.json
index 95ff9172..7ed390d7 100644
--- a/flows/openrag_nudges.json
+++ b/flows/openrag_nudges.json
@@ -2337,12 +2337,12 @@
       "zoom": 0.5380793988167256
     }
   },
-  "description": "OpenRAG Open Search Nudges generator, based on the Open Search documents and the chat history.",
+  "description": "OpenRAG OpenSearch Nudges generator, based on the OpenSearch documents and the chat history.",
   "endpoint_name": null,
   "id": "ebc01d31-1976-46ce-a385-b0240327226c",
   "is_component": false,
   "last_tested_version": "1.6.0",
-  "name": "OpenRAG Open Search Nudges",
+  "name": "OpenRAG OpenSearch Nudges",
   "tags": [
     "assistants",
     "agents"
diff --git a/flows/openrag_url_mcp.json b/flows/openrag_url_mcp.json
new file mode 100644
index 00000000..69dbc85d
--- /dev/null
+++ b/flows/openrag_url_mcp.json
@@ -0,0 +1,3616 @@
+{
+  "data": {
+    "edges": [
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "SplitText",
+            "id": "SplitText-QIKhg",
+            "name": "dataframe",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "ingest_data",
+            "id": "OpenSearchHybrid-Ve6bS",
+            "inputTypes": [
+              "Data",
+              "DataFrame"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__SplitText-QIKhg{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-QIKhgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-OpenSearchHybrid-Ve6bS{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "SplitText-QIKhg",
+        "sourceHandle": "{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-QIKhgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "OpenSearchHybrid-Ve6bS",
+        "targetHandle": "{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "ChatInput",
+            "id": "ChatInput-WLvBD",
+            "name": "message",
+            "output_types": [
+              "Message"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "urls",
+            "id": "URLComponent-lnA0q",
+            "inputTypes": [
+              "Message"
+            ],
+            "type": "str"
+          }
+        },
+        "id": "xy-edge__ChatInput-WLvBD{œdataTypeœ:œChatInputœ,œidœ:œChatInput-WLvBDœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-URLComponent-lnA0q{œfieldNameœ:œurlsœ,œidœ:œURLComponent-lnA0qœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
+        "selected": false,
+        "source": "ChatInput-WLvBD",
+        "sourceHandle": "{œdataTypeœ:œChatInputœ,œidœ:œChatInput-WLvBDœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}",
+        "target": "URLComponent-lnA0q",
+        "targetHandle": "{œfieldNameœ:œurlsœ,œidœ:œURLComponent-lnA0qœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "URLComponent",
+            "id": "URLComponent-lnA0q",
+            "name": "page_results",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "df",
+            "id": "DataFrameOperations-hqIoy",
+            "inputTypes": [
+              "DataFrame"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__URLComponent-lnA0q{œdataTypeœ:œURLComponentœ,œidœ:œURLComponent-lnA0qœ,œnameœ:œpage_resultsœ,œoutput_typesœ:[œDataFrameœ]}-DataFrameOperations-hqIoy{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-hqIoyœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "URLComponent-lnA0q",
+        "sourceHandle": "{œdataTypeœ:œURLComponentœ,œidœ:œURLComponent-lnA0qœ,œnameœ:œpage_resultsœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "DataFrameOperations-hqIoy",
+        "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-hqIoyœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "ChatInput",
+            "id": "ChatInput-WLvBD",
+            "name": "message",
+            "output_types": [
+              "Message"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "new_column_value",
+            "id": "DataFrameOperations-hqIoy",
+            "inputTypes": [
+              "Message"
+            ],
+            "type": "str"
+          }
+        },
+        "id": "xy-edge__ChatInput-WLvBD{œdataTypeœ:œChatInputœ,œidœ:œChatInput-WLvBDœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-DataFrameOperations-hqIoy{œfieldNameœ:œnew_column_valueœ,œidœ:œDataFrameOperations-hqIoyœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
+        "selected": false,
+        "source": "ChatInput-WLvBD",
+        "sourceHandle": "{œdataTypeœ:œChatInputœ,œidœ:œChatInput-WLvBDœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}",
+        "target": "DataFrameOperations-hqIoy",
+        "targetHandle": "{œfieldNameœ:œnew_column_valueœ,œidœ:œDataFrameOperations-hqIoyœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "DataFrameOperations",
+            "id": "DataFrameOperations-hqIoy",
+            "name": "output",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "df",
+            "id": "DataFrameOperations-A98BL",
+            "inputTypes": [
+              "DataFrame"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__DataFrameOperations-hqIoy{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-hqIoyœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}-DataFrameOperations-A98BL{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-A98BLœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "DataFrameOperations-hqIoy",
+        "sourceHandle": "{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-hqIoyœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "DataFrameOperations-A98BL",
+        "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-A98BLœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "DataFrameOperations",
+            "id": "DataFrameOperations-A98BL",
+            "name": "output",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "data_inputs",
+            "id": "SplitText-QIKhg",
+            "inputTypes": [
+              "Data",
+              "DataFrame",
+              "Message"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__DataFrameOperations-A98BL{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-A98BLœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}-SplitText-QIKhg{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-QIKhgœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "DataFrameOperations-A98BL",
+        "sourceHandle": "{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-A98BLœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "SplitText-QIKhg",
+        "targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-QIKhgœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "SplitText",
+            "id": "SplitText-QIKhg",
+            "name": "dataframe",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "df",
+            "id": "DataFrameOperations-RhKoe",
+            "inputTypes": [
+              "DataFrame"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__SplitText-QIKhg{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-QIKhgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-DataFrameOperations-RhKoe{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-RhKoeœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "SplitText-QIKhg",
+        "sourceHandle": "{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-QIKhgœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "DataFrameOperations-RhKoe",
+        "targetHandle": "{œfieldNameœ:œdfœ,œidœ:œDataFrameOperations-RhKoeœ,œinputTypesœ:[œDataFrameœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "className": "",
+        "data": {
+          "sourceHandle": {
+            "dataType": "DataFrameOperations",
+            "id": "DataFrameOperations-RhKoe",
+            "name": "output",
+            "output_types": [
+              "DataFrame"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "input_value",
+            "id": "ChatOutput-Q1dhr",
+            "inputTypes": [
+              "Data",
+              "DataFrame",
+              "Message"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__DataFrameOperations-RhKoe{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-RhKoeœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}-ChatOutput-Q1dhr{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-Q1dhrœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "DataFrameOperations-RhKoe",
+        "sourceHandle": "{œdataTypeœ:œDataFrameOperationsœ,œidœ:œDataFrameOperations-RhKoeœ,œnameœ:œoutputœ,œoutput_typesœ:[œDataFrameœ]}",
+        "target": "ChatOutput-Q1dhr",
+        "targetHandle": "{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-Q1dhrœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}"
+      },
+      {
+        "animated": false,
+        "data": {
+          "sourceHandle": {
+            "dataType": "EmbeddingModel",
+            "id": "EmbeddingModel-eC65s",
+            "name": "embeddings",
+            "output_types": [
+              "Embeddings"
+            ]
+          },
+          "targetHandle": {
+            "fieldName": "embedding",
+            "id": "OpenSearchHybrid-Ve6bS",
+            "inputTypes": [
+              "Embeddings"
+            ],
+            "type": "other"
+          }
+        },
+        "id": "xy-edge__EmbeddingModel-eC65s{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-eC65sœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-OpenSearchHybrid-Ve6bS{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
+        "selected": false,
+        "source": "EmbeddingModel-eC65s",
+        "sourceHandle": "{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-eC65sœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}",
+        "target": "OpenSearchHybrid-Ve6bS",
+        "targetHandle": "{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}"
+      }
+    ],
+    "nodes": [
+      {
+        "data": {
+          "description": "Split text into chunks based on specified criteria.",
+          "display_name": "Split Text",
+          "id": "SplitText-QIKhg",
+          "node": {
+            "base_classes": [
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Split text into chunks based on specified criteria.",
+            "display_name": "Split Text",
+            "documentation": "https://docs.langflow.org/components-processing#split-text",
+            "edited": true,
+            "field_order": [
+              "data_inputs",
+              "chunk_overlap",
+              "chunk_size",
+              "separator",
+              "text_key",
+              "keep_separator"
+            ],
+            "frozen": false,
+            "icon": "scissors-line-dashed",
+            "legacy": false,
+            "lf_version": "1.6.0",
+            "metadata": {
+              "code_hash": "f2867efda61f",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "langchain_text_splitters",
+                    "version": "0.3.9"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "custom_components.split_text"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Chunks",
+                "group_outputs": false,
+                "hidden": null,
+                "method": "split_text",
+                "name": "dataframe",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "chunk_overlap": {
+                "_input_type": "IntInput",
+                "advanced": false,
+                "display_name": "Chunk Overlap",
+                "dynamic": false,
+                "info": "Number of characters to overlap between chunks.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "chunk_overlap",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 200
+              },
+              "chunk_size": {
+                "_input_type": "IntInput",
+                "advanced": false,
+                "display_name": "Chunk Size",
+                "dynamic": false,
+                "info": "The maximum length of each chunk. Text is first split by separator, then chunks are merged up to this size. Individual splits larger than this won't be further divided.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "chunk_size",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 1000
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "from langchain_text_splitters import CharacterTextSplitter\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.io import DropdownInput, HandleInput, IntInput, MessageTextInput, Output\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.utils.util import unescape_string\n\n\nclass SplitTextComponent(Component):\n    display_name: str = \"Split Text\"\n    description: str = \"Split text into chunks based on specified criteria.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#split-text\"\n    icon = \"scissors-line-dashed\"\n    name = \"SplitText\"\n\n    inputs = [\n        HandleInput(\n            name=\"data_inputs\",\n            display_name=\"Input\",\n            info=\"The data with texts to split in chunks.\",\n            input_types=[\"Data\", \"DataFrame\", \"Message\"],\n            required=True,\n        ),\n        IntInput(\n            name=\"chunk_overlap\",\n            display_name=\"Chunk Overlap\",\n            info=\"Number of characters to overlap between chunks.\",\n            value=200,\n        ),\n        IntInput(\n            name=\"chunk_size\",\n            display_name=\"Chunk Size\",\n            info=(\n                \"The maximum length of each chunk. Text is first split by separator, \"\n                \"then chunks are merged up to this size. \"\n                \"Individual splits larger than this won't be further divided.\"\n            ),\n            value=1000,\n        ),\n        MessageTextInput(\n            name=\"separator\",\n            display_name=\"Separator\",\n            info=(\n                \"The character to split on. Use \\\\n for newline. \"\n                \"Examples: \\\\n\\\\n for paragraphs, \\\\n for lines, . for sentences\"\n            ),\n            value=\"\\n\",\n        ),\n        MessageTextInput(\n            name=\"text_key\",\n            display_name=\"Text Key\",\n            info=\"The key to use for the text column.\",\n            value=\"text\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"keep_separator\",\n            display_name=\"Keep Separator\",\n            info=\"Whether to keep the separator in the output chunks and where to place it.\",\n            options=[\"False\", \"True\", \"Start\", \"End\"],\n            value=\"False\",\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Chunks\", name=\"dataframe\", method=\"split_text\"),\n    ]\n\n    def _docs_to_data(self, docs) -> list[Data]:\n        return [Data(text=doc.page_content, data=doc.metadata) for doc in docs]\n\n    def _fix_separator(self, separator: str) -> str:\n        \"\"\"Fix common separator issues and convert to proper format.\"\"\"\n        if separator == \"/n\":\n            return \"\\n\"\n        if separator == \"/t\":\n            return \"\\t\"\n        return separator\n\n    def split_text_base(self):\n        separator = self._fix_separator(self.separator)\n        separator = unescape_string(separator)\n\n        if isinstance(self.data_inputs, DataFrame):\n            if not len(self.data_inputs):\n                msg = \"DataFrame is empty\"\n                raise TypeError(msg)\n\n            self.data_inputs.text_key = self.text_key\n            try:\n                documents = self.data_inputs.to_lc_documents()\n            except Exception as e:\n                msg = f\"Error converting DataFrame to documents: {e}\"\n                raise TypeError(msg) from e\n        elif isinstance(self.data_inputs, Message):\n            self.data_inputs = [self.data_inputs.to_data()]\n            return self.split_text_base()\n        else:\n            if not self.data_inputs:\n                msg = \"No data inputs provided\"\n                raise TypeError(msg)\n\n            documents = []\n            if isinstance(self.data_inputs, Data):\n                self.data_inputs.text_key = self.text_key\n                documents = [self.data_inputs.to_lc_document()]\n            else:\n                try:\n                    documents = [input_.to_lc_document() for input_ in self.data_inputs if isinstance(input_, Data)]\n                    if not documents:\n                        msg = f\"No valid Data inputs found in {type(self.data_inputs)}\"\n                        raise TypeError(msg)\n                except AttributeError as e:\n                    msg = f\"Invalid input type in collection: {e}\"\n                    raise TypeError(msg) from e\n        try:\n            # Convert string 'False'/'True' to boolean\n            keep_sep = self.keep_separator\n            if isinstance(keep_sep, str):\n                if keep_sep.lower() == \"false\":\n                    keep_sep = False\n                elif keep_sep.lower() == \"true\":\n                    keep_sep = True\n                # 'start' and 'end' are kept as strings\n\n            splitter = CharacterTextSplitter(\n                chunk_overlap=self.chunk_overlap,\n                chunk_size=self.chunk_size,\n                separator=separator,\n                keep_separator=keep_sep,\n            )\n            return splitter.split_documents(documents)\n        except Exception as e:\n            msg = f\"Error splitting text: {e}\"\n            raise TypeError(msg) from e\n\n    def split_text(self) -> DataFrame:\n        return DataFrame(self._docs_to_data(self.split_text_base()))\n"
+              },
+              "data_inputs": {
+                "_input_type": "HandleInput",
+                "advanced": false,
+                "display_name": "Input",
+                "dynamic": false,
+                "info": "The data with texts to split in chunks.",
+                "input_types": [
+                  "Data",
+                  "DataFrame",
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "data_inputs",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "keep_separator": {
+                "_input_type": "DropdownInput",
+                "advanced": true,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Keep Separator",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Whether to keep the separator in the output chunks and where to place it.",
+                "name": "keep_separator",
+                "options": [
+                  "False",
+                  "True",
+                  "Start",
+                  "End"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "False"
+              },
+              "separator": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Separator",
+                "dynamic": false,
+                "info": "The character to split on. Use \\n for newline. Examples: \\n\\n for paragraphs, \\n for lines, . for sentences",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "separator",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "\n"
+              },
+              "text_key": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "Text Key",
+                "dynamic": false,
+                "info": "The key to use for the text column.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "text_key",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "text"
+              }
+            },
+            "tool_mode": false
+          },
+          "selected_output": "chunks",
+          "type": "SplitText"
+        },
+        "dragging": false,
+        "height": 475,
+        "id": "SplitText-QIKhg",
+        "measured": {
+          "height": 475,
+          "width": 320
+        },
+        "position": {
+          "x": 2299.485091096586,
+          "y": 1430.4506304359015
+        },
+        "positionAbsolute": {
+          "x": 1683.4543896546102,
+          "y": 1350.7871623588553
+        },
+        "selected": false,
+        "type": "genericNode",
+        "width": 320
+      },
+      {
+        "data": {
+          "id": "OpenSearchHybrid-Ve6bS",
+          "node": {
+            "base_classes": [
+              "Data",
+              "DataFrame",
+              "VectorStore"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Store and search documents using OpenSearch with hybrid semantic and keyword search capabilities.",
+            "display_name": "OpenSearch",
+            "documentation": "",
+            "edited": true,
+            "field_order": [
+              "docs_metadata",
+              "opensearch_url",
+              "index_name",
+              "engine",
+              "space_type",
+              "ef_construction",
+              "m",
+              "ingest_data",
+              "search_query",
+              "should_cache_vector_store",
+              "embedding",
+              "vector_field",
+              "number_of_results",
+              "filter_expression",
+              "auth_mode",
+              "username",
+              "password",
+              "jwt_token",
+              "jwt_header",
+              "bearer_prefix",
+              "use_ssl",
+              "verify_certs"
+            ],
+            "frozen": false,
+            "icon": "OpenSearch",
+            "legacy": false,
+            "lf_version": "1.6.0",
+            "metadata": {
+              "code_hash": "08d808984c3d",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "opensearchpy",
+                    "version": "2.8.0"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "custom_components.opensearch"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Search Results",
+                "group_outputs": false,
+                "hidden": null,
+                "method": "search_documents",
+                "name": "search_results",
+                "options": null,
+                "required_inputs": null,
+                "tool_mode": true,
+                "types": [
+                  "Data"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "group_outputs": false,
+                "hidden": null,
+                "method": "as_dataframe",
+                "name": "dataframe",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Vector Store Connection",
+                "group_outputs": false,
+                "hidden": false,
+                "method": "as_vector_store",
+                "name": "vectorstoreconnection",
+                "options": null,
+                "required_inputs": null,
+                "tool_mode": true,
+                "types": [
+                  "VectorStore"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "auth_mode": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Authentication Mode",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Authentication method: 'basic' for username/password authentication, or 'jwt' for JSON Web Token (Bearer) authentication.",
+                "load_from_db": false,
+                "name": "auth_mode",
+                "options": [
+                  "basic",
+                  "jwt"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "real_time_refresh": true,
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "jwt"
+              },
+              "bearer_prefix": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Prefix 'Bearer '",
+                "dynamic": false,
+                "info": "",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "bearer_prefix",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "from __future__ import annotations\n\nimport json\nimport uuid\nfrom typing import Any\n\nfrom opensearchpy import OpenSearch, helpers\n\nfrom lfx.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom lfx.base.vectorstores.vector_store_connection_decorator import vector_store_connection\nfrom lfx.io import BoolInput, DropdownInput, HandleInput, IntInput, MultilineInput, SecretStrInput, StrInput, TableInput\nfrom lfx.log import logger\nfrom lfx.schema.data import Data\n\n\n@vector_store_connection\nclass OpenSearchVectorStoreComponent(LCVectorStoreComponent):\n    \"\"\"OpenSearch Vector Store Component with Hybrid Search Capabilities.\n\n    This component provides vector storage and retrieval using OpenSearch, combining semantic\n    similarity search (KNN) with keyword-based search for optimal results. It supports document\n    ingestion, vector embeddings, and advanced filtering with authentication options.\n\n    Features:\n    - Vector storage with configurable engines (jvector, nmslib, faiss, lucene)\n    - Hybrid search combining KNN vector similarity and keyword matching\n    - Flexible authentication (Basic auth, JWT tokens)\n    - Advanced filtering and aggregations\n    - Metadata injection during document ingestion\n    \"\"\"\n\n    display_name: str = \"OpenSearch\"\n    icon: str = \"OpenSearch\"\n    description: str = (\n        \"Store and search documents using OpenSearch with hybrid semantic and keyword search capabilities.\"\n    )\n\n    # Keys we consider baseline\n    default_keys: list[str] = [\n        \"opensearch_url\",\n        \"index_name\",\n        *[i.name for i in LCVectorStoreComponent.inputs],  # search_query, add_documents, etc.\n        \"embedding\",\n        \"vector_field\",\n        \"number_of_results\",\n        \"auth_mode\",\n        \"username\",\n        \"password\",\n        \"jwt_token\",\n        \"jwt_header\",\n        \"bearer_prefix\",\n        \"use_ssl\",\n        \"verify_certs\",\n        \"filter_expression\",\n        \"engine\",\n        \"space_type\",\n        \"ef_construction\",\n        \"m\",\n        \"docs_metadata\",\n    ]\n\n    inputs = [\n        TableInput(\n            name=\"docs_metadata\",\n            display_name=\"Document Metadata\",\n            info=(\n                \"Additional metadata key-value pairs to be added to all ingested documents. \"\n                \"Useful for tagging documents with source information, categories, or other custom attributes.\"\n            ),\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Key\",\n                    \"type\": \"str\",\n                    \"description\": \"Key name\",\n\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"type\": \"str\",\n                    \"description\": \"Value of the metadata\",\n                     \"load_from_db\": True\n                },\n            ],\n            value=[],\n            # advanced=True,\n            input_types=[\"Data\"]\n        ),\n        StrInput(\n            name=\"opensearch_url\",\n            display_name=\"OpenSearch URL\",\n            value=\"http://localhost:9200\",\n            info=(\n                \"The connection URL for your OpenSearch cluster \"\n                \"(e.g., http://localhost:9200 for local development or your cloud endpoint).\"\n            ),\n        ),\n        StrInput(\n            name=\"index_name\",\n            display_name=\"Index Name\",\n            value=\"langflow\",\n            info=(\n                \"The OpenSearch index name where documents will be stored and searched. \"\n                \"Will be created automatically if it doesn't exist.\"\n            ),\n        ),\n        DropdownInput(\n            name=\"engine\",\n            display_name=\"Vector Engine\",\n            options=[\"jvector\", \"nmslib\", \"faiss\", \"lucene\"],\n            value=\"jvector\",\n            info=(\n                \"Vector search engine for similarity calculations. 'jvector' is recommended for most use cases. \"\n                \"Note: Amazon OpenSearch Serverless only supports 'nmslib' or 'faiss'.\"\n            ),\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"space_type\",\n            display_name=\"Distance Metric\",\n            options=[\"l2\", \"l1\", \"cosinesimil\", \"linf\", \"innerproduct\"],\n            value=\"l2\",\n            info=(\n                \"Distance metric for calculating vector similarity. 'l2' (Euclidean) is most common, \"\n                \"'cosinesimil' for cosine similarity, 'innerproduct' for dot product.\"\n            ),\n            advanced=True,\n        ),\n        IntInput(\n            name=\"ef_construction\",\n            display_name=\"EF Construction\",\n            value=512,\n            info=(\n                \"Size of the dynamic candidate list during index construction. \"\n                \"Higher values improve recall but increase indexing time and memory usage.\"\n            ),\n            advanced=True,\n        ),\n        IntInput(\n            name=\"m\",\n            display_name=\"M Parameter\",\n            value=16,\n            info=(\n                \"Number of bidirectional connections for each vector in the HNSW graph. \"\n                \"Higher values improve search quality but increase memory usage and indexing time.\"\n            ),\n            advanced=True,\n        ),\n        *LCVectorStoreComponent.inputs,  # includes search_query, add_documents, etc.\n        HandleInput(name=\"embedding\", display_name=\"Embedding\", input_types=[\"Embeddings\"]),\n        StrInput(\n            name=\"vector_field\",\n            display_name=\"Vector Field Name\",\n            value=\"chunk_embedding\",\n            advanced=True,\n            info=\"Name of the field in OpenSearch documents that stores the vector embeddings for similarity search.\",\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Default Result Limit\",\n            value=10,\n            advanced=True,\n            info=(\n                \"Default maximum number of search results to return when no limit is \"\n                \"specified in the filter expression.\"\n            ),\n        ),\n        MultilineInput(\n            name=\"filter_expression\",\n            display_name=\"Search Filters (JSON)\",\n            value=\"\",\n            info=(\n                \"Optional JSON configuration for search filtering, result limits, and score thresholds.\\n\\n\"\n                \"Format 1 - Explicit filters:\\n\"\n                '{\"filter\": [{\"term\": {\"filename\":\"doc.pdf\"}}, '\n                '{\"terms\":{\"owner\":[\"user1\",\"user2\"]}}], \"limit\": 10, \"score_threshold\": 1.6}\\n\\n'\n                \"Format 2 - Context-style mapping:\\n\"\n                '{\"data_sources\":[\"file.pdf\"], \"document_types\":[\"application/pdf\"], \"owners\":[\"user123\"]}\\n\\n'\n                \"Use __IMPOSSIBLE_VALUE__ as placeholder to ignore specific filters.\"\n            ),\n        ),\n        # ----- Auth controls (dynamic) -----\n        DropdownInput(\n            name=\"auth_mode\",\n            display_name=\"Authentication Mode\",\n            value=\"basic\",\n            options=[\"basic\", \"jwt\"],\n            info=(\n                \"Authentication method: 'basic' for username/password authentication, \"\n                \"or 'jwt' for JSON Web Token (Bearer) authentication.\"\n            ),\n            real_time_refresh=True,\n            advanced=False,\n        ),\n        StrInput(\n            name=\"username\",\n            display_name=\"Username\",\n            value=\"admin\",\n            show=False,\n        ),\n        SecretStrInput(\n            name=\"password\",\n            display_name=\"OpenSearch Password\",\n            value=\"admin\",\n            show=False,\n        ),\n        SecretStrInput(\n            name=\"jwt_token\",\n            display_name=\"JWT Token\",\n            value=\"JWT\",\n            load_from_db=False,\n            show=True,\n            info=(\n                \"Valid JSON Web Token for authentication. \"\n                \"Will be sent in the Authorization header (with optional 'Bearer ' prefix).\"\n            ),\n        ),\n        StrInput(\n            name=\"jwt_header\",\n            display_name=\"JWT Header Name\",\n            value=\"Authorization\",\n            show=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"bearer_prefix\",\n            display_name=\"Prefix 'Bearer '\",\n            value=True,\n            show=False,\n            advanced=True,\n        ),\n        # ----- TLS -----\n        BoolInput(\n            name=\"use_ssl\",\n            display_name=\"Use SSL/TLS\",\n            value=True,\n            advanced=True,\n            info=\"Enable SSL/TLS encryption for secure connections to OpenSearch.\",\n        ),\n        BoolInput(\n            name=\"verify_certs\",\n            display_name=\"Verify SSL Certificates\",\n            value=False,\n            advanced=True,\n            info=(\n                \"Verify SSL certificates when connecting. \"\n                \"Disable for self-signed certificates in development environments.\"\n            ),\n        ),\n    ]\n\n    # ---------- helper functions for index management ----------\n    def _default_text_mapping(\n        self,\n        dim: int,\n        engine: str = \"jvector\",\n        space_type: str = \"l2\",\n        ef_search: int = 512,\n        ef_construction: int = 100,\n        m: int = 16,\n        vector_field: str = \"vector_field\",\n    ) -> dict[str, Any]:\n        \"\"\"Create the default OpenSearch index mapping for vector search.\n\n        This method generates the index configuration with k-NN settings optimized\n        for approximate nearest neighbor search using the specified vector engine.\n\n        Args:\n            dim: Dimensionality of the vector embeddings\n            engine: Vector search engine (jvector, nmslib, faiss, lucene)\n            space_type: Distance metric for similarity calculation\n            ef_search: Size of dynamic list used during search\n            ef_construction: Size of dynamic list used during index construction\n            m: Number of bidirectional links for each vector\n            vector_field: Name of the field storing vector embeddings\n\n        Returns:\n            Dictionary containing OpenSearch index mapping configuration\n        \"\"\"\n        return {\n            \"settings\": {\"index\": {\"knn\": True, \"knn.algo_param.ef_search\": ef_search}},\n            \"mappings\": {\n                \"properties\": {\n                    vector_field: {\n                        \"type\": \"knn_vector\",\n                        \"dimension\": dim,\n                        \"method\": {\n                            \"name\": \"disk_ann\",\n                            \"space_type\": space_type,\n                            \"engine\": engine,\n                            \"parameters\": {\"ef_construction\": ef_construction, \"m\": m},\n                        },\n                    }\n                }\n            },\n        }\n\n    def _validate_aoss_with_engines(self, *, is_aoss: bool, engine: str) -> None:\n        \"\"\"Validate engine compatibility with Amazon OpenSearch Serverless (AOSS).\n\n        Amazon OpenSearch Serverless has restrictions on which vector engines\n        can be used. This method ensures the selected engine is compatible.\n\n        Args:\n            is_aoss: Whether the connection is to Amazon OpenSearch Serverless\n            engine: The selected vector search engine\n\n        Raises:\n            ValueError: If AOSS is used with an incompatible engine\n        \"\"\"\n        if is_aoss and engine not in {\"nmslib\", \"faiss\"}:\n            msg = \"Amazon OpenSearch Service Serverless only supports `nmslib` or `faiss` engines\"\n            raise ValueError(msg)\n\n    def _is_aoss_enabled(self, http_auth: Any) -> bool:\n        \"\"\"Determine if Amazon OpenSearch Serverless (AOSS) is being used.\n\n        Args:\n            http_auth: The HTTP authentication object\n\n        Returns:\n            True if AOSS is enabled, False otherwise\n        \"\"\"\n        return http_auth is not None and hasattr(http_auth, \"service\") and http_auth.service == \"aoss\"\n\n    def _bulk_ingest_embeddings(\n        self,\n        client: OpenSearch,\n        index_name: str,\n        embeddings: list[list[float]],\n        texts: list[str],\n        metadatas: list[dict] | None = None,\n        ids: list[str] | None = None,\n        vector_field: str = \"vector_field\",\n        text_field: str = \"text\",\n        mapping: dict | None = None,\n        max_chunk_bytes: int | None = 1 * 1024 * 1024,\n        *,\n        is_aoss: bool = False,\n    ) -> list[str]:\n        \"\"\"Efficiently ingest multiple documents with embeddings into OpenSearch.\n\n        This method uses bulk operations to insert documents with their vector\n        embeddings and metadata into the specified OpenSearch index.\n\n        Args:\n            client: OpenSearch client instance\n            index_name: Target index for document storage\n            embeddings: List of vector embeddings for each document\n            texts: List of document texts\n            metadatas: Optional metadata dictionaries for each document\n            ids: Optional document IDs (UUIDs generated if not provided)\n            vector_field: Field name for storing vector embeddings\n            text_field: Field name for storing document text\n            mapping: Optional index mapping configuration\n            max_chunk_bytes: Maximum size per bulk request chunk\n            is_aoss: Whether using Amazon OpenSearch Serverless\n\n        Returns:\n            List of document IDs that were successfully ingested\n        \"\"\"\n        if not mapping:\n            mapping = {}\n\n        requests = []\n        return_ids = []\n\n        for i, text in enumerate(texts):\n            metadata = metadatas[i] if metadatas else {}\n            _id = ids[i] if ids else str(uuid.uuid4())\n            request = {\n                \"_op_type\": \"index\",\n                \"_index\": index_name,\n                vector_field: embeddings[i],\n                text_field: text,\n                **metadata,\n            }\n            if is_aoss:\n                request[\"id\"] = _id\n            else:\n                request[\"_id\"] = _id\n            requests.append(request)\n            return_ids.append(_id)\n        if metadatas:\n            self.log(f\"Sample metadata: {metadatas[0] if metadatas else {}}\")\n        helpers.bulk(client, requests, max_chunk_bytes=max_chunk_bytes)\n        return return_ids\n\n    # ---------- auth / client ----------\n    def _build_auth_kwargs(self) -> dict[str, Any]:\n        \"\"\"Build authentication configuration for OpenSearch client.\n\n        Constructs the appropriate authentication parameters based on the\n        selected auth mode (basic username/password or JWT token).\n\n        Returns:\n            Dictionary containing authentication configuration\n\n        Raises:\n            ValueError: If required authentication parameters are missing\n        \"\"\"\n        mode = (self.auth_mode or \"basic\").strip().lower()\n        if mode == \"jwt\":\n            token = (self.jwt_token or \"\").strip()\n            if not token:\n                msg = \"Auth Mode is 'jwt' but no jwt_token was provided.\"\n                raise ValueError(msg)\n            header_name = (self.jwt_header or \"Authorization\").strip()\n            header_value = f\"Bearer {token}\" if self.bearer_prefix else token\n            return {\"headers\": {header_name: header_value}}\n        user = (self.username or \"\").strip()\n        pwd = (self.password or \"\").strip()\n        if not user or not pwd:\n            msg = \"Auth Mode is 'basic' but username/password are missing.\"\n            raise ValueError(msg)\n        return {\"http_auth\": (user, pwd)}\n\n    def build_client(self) -> OpenSearch:\n        \"\"\"Create and configure an OpenSearch client instance.\n\n        Returns:\n            Configured OpenSearch client ready for operations\n        \"\"\"\n        auth_kwargs = self._build_auth_kwargs()\n        return OpenSearch(\n            hosts=[self.opensearch_url],\n            use_ssl=self.use_ssl,\n            verify_certs=self.verify_certs,\n            ssl_assert_hostname=False,\n            ssl_show_warn=False,\n            **auth_kwargs,\n        )\n\n    @check_cached_vector_store\n    def build_vector_store(self) -> OpenSearch:\n        # Return raw OpenSearch client as our “vector store.”\n        self.log(self.ingest_data)\n        client = self.build_client()\n        self._add_documents_to_vector_store(client=client)\n        return client\n\n    # ---------- ingest ----------\n    def _add_documents_to_vector_store(self, client: OpenSearch) -> None:\n        \"\"\"Process and ingest documents into the OpenSearch vector store.\n\n        This method handles the complete document ingestion pipeline:\n        - Prepares document data and metadata\n        - Generates vector embeddings\n        - Creates appropriate index mappings\n        - Bulk inserts documents with vectors\n\n        Args:\n            client: OpenSearch client for performing operations\n        \"\"\"\n        # Convert DataFrame to Data if needed using parent's method\n        self.ingest_data = self._prepare_ingest_data()\n\n        docs = self.ingest_data or []\n        if not docs:\n            self.log(\"No documents to ingest.\")\n            return\n\n        # Extract texts and metadata from documents\n        texts = []\n        metadatas = []\n        # Process docs_metadata table input into a dict\n        additional_metadata = {}\n        if hasattr(self, \"docs_metadata\") and self.docs_metadata:\n            logger.info(f\"[LF] Docs metadata {self.docs_metadata}\")\n            if isinstance(self.docs_metadata[-1], Data):\n                logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n                self.docs_metadata = self.docs_metadata[-1].data\n                logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n                additional_metadata.update(self.docs_metadata)\n            else:\n                for item in self.docs_metadata:\n                    if isinstance(item, dict) and \"key\" in item and \"value\" in item:\n                        additional_metadata[item[\"key\"]] = item[\"value\"]\n        logger.info(f\"[LF] Additional metadata {additional_metadata}\")\n        for doc_obj in docs:\n            data_copy = json.loads(doc_obj.model_dump_json())\n            text = data_copy.pop(doc_obj.text_key, doc_obj.default_value)\n            texts.append(text)\n\n            # Merge additional metadata from table input\n            data_copy.update(additional_metadata)\n\n            metadatas.append(data_copy)\n        self.log(metadatas)\n        if not self.embedding:\n            msg = \"Embedding handle is required to embed documents.\"\n            raise ValueError(msg)\n\n        # Generate embeddings\n        vectors = self.embedding.embed_documents(texts)\n\n        if not vectors:\n            self.log(\"No vectors generated from documents.\")\n            return\n\n        # Get vector dimension for mapping\n        dim = len(vectors[0]) if vectors else 768  # default fallback\n\n        # Check for AOSS\n        auth_kwargs = self._build_auth_kwargs()\n        is_aoss = self._is_aoss_enabled(auth_kwargs.get(\"http_auth\"))\n\n        # Validate engine with AOSS\n        engine = getattr(self, \"engine\", \"jvector\")\n        self._validate_aoss_with_engines(is_aoss=is_aoss, engine=engine)\n\n        # Create mapping with proper KNN settings\n        space_type = getattr(self, \"space_type\", \"l2\")\n        ef_construction = getattr(self, \"ef_construction\", 512)\n        m = getattr(self, \"m\", 16)\n\n        mapping = self._default_text_mapping(\n            dim=dim,\n            engine=engine,\n            space_type=space_type,\n            ef_construction=ef_construction,\n            m=m,\n            vector_field=self.vector_field,\n        )\n\n        self.log(f\"Indexing {len(texts)} documents into '{self.index_name}' with proper KNN mapping...\")\n\n        # Use the LangChain-style bulk ingestion\n        return_ids = self._bulk_ingest_embeddings(\n            client=client,\n            index_name=self.index_name,\n            embeddings=vectors,\n            texts=texts,\n            metadatas=metadatas,\n            vector_field=self.vector_field,\n            text_field=\"text\",\n            mapping=mapping,\n            is_aoss=is_aoss,\n        )\n        self.log(metadatas)\n\n        self.log(f\"Successfully indexed {len(return_ids)} documents.\")\n\n    # ---------- helpers for filters ----------\n    def _is_placeholder_term(self, term_obj: dict) -> bool:\n        # term_obj like {\"filename\": \"__IMPOSSIBLE_VALUE__\"}\n        return any(v == \"__IMPOSSIBLE_VALUE__\" for v in term_obj.values())\n\n    def _coerce_filter_clauses(self, filter_obj: dict | None) -> list[dict]:\n        \"\"\"Convert filter expressions into OpenSearch-compatible filter clauses.\n\n        This method accepts two filter formats and converts them to standardized\n        OpenSearch query clauses:\n\n        Format A - Explicit filters:\n        {\"filter\": [{\"term\": {\"field\": \"value\"}}, {\"terms\": {\"field\": [\"val1\", \"val2\"]}}],\n         \"limit\": 10, \"score_threshold\": 1.5}\n\n        Format B - Context-style mapping:\n        {\"data_sources\": [\"file1.pdf\"], \"document_types\": [\"pdf\"], \"owners\": [\"user1\"]}\n\n        Args:\n            filter_obj: Filter configuration dictionary or None\n\n        Returns:\n            List of OpenSearch filter clauses (term/terms objects)\n            Placeholder values with \"__IMPOSSIBLE_VALUE__\" are ignored\n        \"\"\"\n        if not filter_obj:\n            return []\n\n        # If it is a string, try to parse it once\n        if isinstance(filter_obj, str):\n            try:\n                filter_obj = json.loads(filter_obj)\n            except json.JSONDecodeError:\n                # Not valid JSON - treat as no filters\n                return []\n\n        # Case A: already an explicit list/dict under \"filter\"\n        if \"filter\" in filter_obj:\n            raw = filter_obj[\"filter\"]\n            if isinstance(raw, dict):\n                raw = [raw]\n            explicit_clauses: list[dict] = []\n            for f in raw or []:\n                if \"term\" in f and isinstance(f[\"term\"], dict) and not self._is_placeholder_term(f[\"term\"]):\n                    explicit_clauses.append(f)\n                elif \"terms\" in f and isinstance(f[\"terms\"], dict):\n                    field, vals = next(iter(f[\"terms\"].items()))\n                    if isinstance(vals, list) and len(vals) > 0:\n                        explicit_clauses.append(f)\n            return explicit_clauses\n\n        # Case B: convert context-style maps into clauses\n        field_mapping = {\n            \"data_sources\": \"filename\",\n            \"document_types\": \"mimetype\",\n            \"owners\": \"owner\",\n        }\n        context_clauses: list[dict] = []\n        for k, values in filter_obj.items():\n            if not isinstance(values, list):\n                continue\n            field = field_mapping.get(k, k)\n            if len(values) == 0:\n                # Match-nothing placeholder (kept to mirror your tool semantics)\n                context_clauses.append({\"term\": {field: \"__IMPOSSIBLE_VALUE__\"}})\n            elif len(values) == 1:\n                if values[0] != \"__IMPOSSIBLE_VALUE__\":\n                    context_clauses.append({\"term\": {field: values[0]}})\n            else:\n                context_clauses.append({\"terms\": {field: values}})\n        return context_clauses\n\n    # ---------- search (single hybrid path matching your tool) ----------\n    def search(self, query: str | None = None) -> list[dict[str, Any]]:\n        \"\"\"Perform hybrid search combining vector similarity and keyword matching.\n\n        This method executes a sophisticated search that combines:\n        - K-nearest neighbor (KNN) vector similarity search (70% weight)\n        - Multi-field keyword search with fuzzy matching (30% weight)\n        - Optional filtering and score thresholds\n        - Aggregations for faceted search results\n\n        Args:\n            query: Search query string (used for both vector embedding and keyword search)\n\n        Returns:\n            List of search results with page_content, metadata, and relevance scores\n\n        Raises:\n            ValueError: If embedding component is not provided or filter JSON is invalid\n        \"\"\"\n        logger.info(self.ingest_data)\n        client = self.build_client()\n        q = (query or \"\").strip()\n\n        # Parse optional filter expression (can be either A or B shape; see _coerce_filter_clauses)\n        filter_obj = None\n        if getattr(self, \"filter_expression\", \"\") and self.filter_expression.strip():\n            try:\n                filter_obj = json.loads(self.filter_expression)\n            except json.JSONDecodeError as e:\n                msg = f\"Invalid filter_expression JSON: {e}\"\n                raise ValueError(msg) from e\n\n        if not self.embedding:\n            msg = \"Embedding is required to run hybrid search (KNN + keyword).\"\n            raise ValueError(msg)\n\n        # Embed the query\n        vec = self.embedding.embed_query(q)\n\n        # Build filter clauses (accept both shapes)\n        filter_clauses = self._coerce_filter_clauses(filter_obj)\n\n        # Respect the tool's limit/threshold defaults\n        limit = (filter_obj or {}).get(\"limit\", self.number_of_results)\n        score_threshold = (filter_obj or {}).get(\"score_threshold\", 0)\n\n        # Build the same hybrid body as your SearchService\n        body = {\n            \"query\": {\n                \"bool\": {\n                    \"should\": [\n                        {\n                            \"knn\": {\n                                self.vector_field: {\n                                    \"vector\": vec,\n                                    \"k\": 10,  # fixed to match the tool\n                                    \"boost\": 0.7,\n                                }\n                            }\n                        },\n                        {\n                            \"multi_match\": {\n                                \"query\": q,\n                                \"fields\": [\"text^2\", \"filename^1.5\"],\n                                \"type\": \"best_fields\",\n                                \"fuzziness\": \"AUTO\",\n                                \"boost\": 0.3,\n                            }\n                        },\n                    ],\n                    \"minimum_should_match\": 1,\n                }\n            },\n            \"aggs\": {\n                \"data_sources\": {\"terms\": {\"field\": \"filename\", \"size\": 20}},\n                \"document_types\": {\"terms\": {\"field\": \"mimetype\", \"size\": 10}},\n                \"owners\": {\"terms\": {\"field\": \"owner\", \"size\": 10}},\n            },\n            \"_source\": [\n                \"filename\",\n                \"mimetype\",\n                \"page\",\n                \"text\",\n                \"source_url\",\n                \"owner\",\n                \"allowed_users\",\n                \"allowed_groups\",\n            ],\n            \"size\": limit,\n        }\n        if filter_clauses:\n            body[\"query\"][\"bool\"][\"filter\"] = filter_clauses\n\n        if isinstance(score_threshold, (int, float)) and score_threshold > 0:\n            # top-level min_score (matches your tool)\n            body[\"min_score\"] = score_threshold\n\n        resp = client.search(index=self.index_name, body=body)\n        hits = resp.get(\"hits\", {}).get(\"hits\", [])\n        return [\n            {\n                \"page_content\": hit[\"_source\"].get(\"text\", \"\"),\n                \"metadata\": {k: v for k, v in hit[\"_source\"].items() if k != \"text\"},\n                \"score\": hit.get(\"_score\"),\n            }\n            for hit in hits\n        ]\n\n    def search_documents(self) -> list[Data]:\n        \"\"\"Search documents and return results as Data objects.\n\n        This is the main interface method that performs the search using the\n        configured search_query and returns results in Langflow's Data format.\n\n        Returns:\n            List of Data objects containing search results with text and metadata\n\n        Raises:\n            Exception: If search operation fails\n        \"\"\"\n        try:\n            raw = self.search(self.search_query or \"\")\n            return [Data(text=hit[\"page_content\"], **hit[\"metadata\"]) for hit in raw]\n            self.log(self.ingest_data)\n        except Exception as e:\n            self.log(f\"search_documents error: {e}\")\n            raise\n\n    # -------- dynamic UI handling (auth switch) --------\n    async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n        \"\"\"Dynamically update component configuration based on field changes.\n\n        This method handles real-time UI updates, particularly for authentication\n        mode changes that show/hide relevant input fields.\n\n        Args:\n            build_config: Current component configuration\n            field_value: New value for the changed field\n            field_name: Name of the field that changed\n\n        Returns:\n            Updated build configuration with appropriate field visibility\n        \"\"\"\n        try:\n            if field_name == \"auth_mode\":\n                mode = (field_value or \"basic\").strip().lower()\n                is_basic = mode == \"basic\"\n                is_jwt = mode == \"jwt\"\n\n                build_config[\"username\"][\"show\"] = is_basic\n                build_config[\"password\"][\"show\"] = is_basic\n\n                build_config[\"jwt_token\"][\"show\"] = is_jwt\n                build_config[\"jwt_header\"][\"show\"] = is_jwt\n                build_config[\"bearer_prefix\"][\"show\"] = is_jwt\n\n                build_config[\"username\"][\"required\"] = is_basic\n                build_config[\"password\"][\"required\"] = is_basic\n\n                build_config[\"jwt_token\"][\"required\"] = is_jwt\n                build_config[\"jwt_header\"][\"required\"] = is_jwt\n                build_config[\"bearer_prefix\"][\"required\"] = False\n\n                if is_basic:\n                    build_config[\"jwt_token\"][\"value\"] = \"\"\n\n                return build_config\n\n        except (KeyError, ValueError) as e:\n            self.log(f\"update_build_config error: {e}\")\n\n        return build_config\n"
+              },
+              "docs_metadata": {
+                "_input_type": "TableInput",
+                "advanced": false,
+                "display_name": "Document Metadata",
+                "dynamic": false,
+                "info": "Additional metadata key-value pairs to be added to all ingested documents. Useful for tagging documents with source information, categories, or other custom attributes.",
+                "input_types": [
+                  "Data"
+                ],
+                "is_list": true,
+                "list_add_label": "Add More",
+                "name": "docs_metadata",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "table_icon": "Table",
+                "table_schema": [
+                  {
+                    "description": "Key name",
+                    "display_name": "Key",
+                    "formatter": "text",
+                    "name": "key",
+                    "type": "str"
+                  },
+                  {
+                    "description": "Value of the metadata",
+                    "display_name": "Value",
+                    "formatter": "text",
+                    "load_from_db": true,
+                    "name": "value",
+                    "type": "str"
+                  }
+                ],
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "trigger_icon": "Table",
+                "trigger_text": "Open table",
+                "type": "table",
+                "value": [
+                  {
+                    "key": "owner_name",
+                    "value": "OWNER_NAME"
+                  },
+                  {
+                    "key": "owner",
+                    "value": "OWNER"
+                  },
+                  {
+                    "key": "owner_email",
+                    "value": "OWNER_EMAIL"
+                  }
+                ]
+              },
+              "ef_construction": {
+                "_input_type": "IntInput",
+                "advanced": true,
+                "display_name": "EF Construction",
+                "dynamic": false,
+                "info": "Size of the dynamic candidate list during index construction. Higher values improve recall but increase indexing time and memory usage.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ef_construction",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 512
+              },
+              "embedding": {
+                "_input_type": "HandleInput",
+                "advanced": false,
+                "display_name": "Embedding",
+                "dynamic": false,
+                "info": "",
+                "input_types": [
+                  "Embeddings"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "embedding",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "engine": {
+                "_input_type": "DropdownInput",
+                "advanced": true,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Vector Engine",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Vector search engine for similarity calculations. 'jvector' is recommended for most use cases. Note: Amazon OpenSearch Serverless only supports 'nmslib' or 'faiss'.",
+                "load_from_db": false,
+                "name": "engine",
+                "options": [
+                  "jvector",
+                  "nmslib",
+                  "faiss",
+                  "lucene"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "nmslib"
+              },
+              "filter_expression": {
+                "_input_type": "MultilineInput",
+                "advanced": false,
+                "copy_field": false,
+                "display_name": "Search Filters (JSON)",
+                "dynamic": false,
+                "info": "Optional JSON configuration for search filtering, result limits, and score thresholds.\n\nFormat 1 - Explicit filters:\n{\"filter\": [{\"term\": {\"filename\":\"doc.pdf\"}}, {\"terms\":{\"owner\":[\"user1\",\"user2\"]}}], \"limit\": 10, \"score_threshold\": 1.6}\n\nFormat 2 - Context-style mapping:\n{\"data_sources\":[\"file.pdf\"], \"document_types\":[\"application/pdf\"], \"owners\":[\"user123\"]}\n\nUse __IMPOSSIBLE_VALUE__ as placeholder to ignore specific filters.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "multiline": true,
+                "name": "filter_expression",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "index_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Index Name",
+                "dynamic": false,
+                "info": "The OpenSearch index name where documents will be stored and searched. Will be created automatically if it doesn't exist.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "index_name",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "documents"
+              },
+              "ingest_data": {
+                "_input_type": "HandleInput",
+                "advanced": false,
+                "display_name": "Ingest Data",
+                "dynamic": false,
+                "info": "",
+                "input_types": [
+                  "Data",
+                  "DataFrame"
+                ],
+                "list": true,
+                "list_add_label": "Add More",
+                "name": "ingest_data",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "jwt_header": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "JWT Header Name",
+                "dynamic": false,
+                "info": "",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "jwt_header",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "Authorization"
+              },
+              "jwt_token": {
+                "_input_type": "SecretStrInput",
+                "advanced": false,
+                "display_name": "JWT Token",
+                "dynamic": false,
+                "info": "Valid JSON Web Token for authentication. Will be sent in the Authorization header (with optional 'Bearer ' prefix).",
+                "input_types": [],
+                "load_from_db": true,
+                "name": "jwt_token",
+                "password": true,
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "type": "str",
+                "value": "JWT"
+              },
+              "m": {
+                "_input_type": "IntInput",
+                "advanced": true,
+                "display_name": "M Parameter",
+                "dynamic": false,
+                "info": "Number of bidirectional connections for each vector in the HNSW graph. Higher values improve search quality but increase memory usage and indexing time.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "m",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 16
+              },
+              "number_of_results": {
+                "_input_type": "IntInput",
+                "advanced": true,
+                "display_name": "Default Result Limit",
+                "dynamic": false,
+                "info": "Default maximum number of search results to return when no limit is specified in the filter expression.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "number_of_results",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 15
+              },
+              "opensearch_url": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "OpenSearch URL",
+                "dynamic": false,
+                "info": "The connection URL for your OpenSearch cluster (e.g., http://localhost:9200 for local development or your cloud endpoint).",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "opensearch_url",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "https://opensearch:9200"
+              },
+              "password": {
+                "_input_type": "SecretStrInput",
+                "advanced": false,
+                "display_name": "OpenSearch Password",
+                "dynamic": false,
+                "info": "",
+                "input_types": [],
+                "load_from_db": false,
+                "name": "password",
+                "password": true,
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "type": "str",
+                "value": ""
+              },
+              "search_query": {
+                "_input_type": "QueryInput",
+                "advanced": false,
+                "display_name": "Search Query",
+                "dynamic": false,
+                "info": "Enter a query to run a similarity search.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "search_query",
+                "placeholder": "Enter a query...",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": true,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "query",
+                "value": ""
+              },
+              "should_cache_vector_store": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Cache Vector Store",
+                "dynamic": false,
+                "info": "If True, the vector store will be cached for the current build of the component. This is useful for components that have multiple output methods and want to share the same vector store.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "should_cache_vector_store",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "space_type": {
+                "_input_type": "DropdownInput",
+                "advanced": true,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Distance Metric",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Distance metric for calculating vector similarity. 'l2' (Euclidean) is most common, 'cosinesimil' for cosine similarity, 'innerproduct' for dot product.",
+                "name": "space_type",
+                "options": [
+                  "l2",
+                  "l1",
+                  "cosinesimil",
+                  "linf",
+                  "innerproduct"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "l2"
+              },
+              "use_ssl": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Use SSL/TLS",
+                "dynamic": false,
+                "info": "Enable SSL/TLS encryption for secure connections to OpenSearch.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "use_ssl",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "username": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Username",
+                "dynamic": false,
+                "info": "",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "username",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "admin"
+              },
+              "vector_field": {
+                "_input_type": "StrInput",
+                "advanced": true,
+                "display_name": "Vector Field Name",
+                "dynamic": false,
+                "info": "Name of the field in OpenSearch documents that stores the vector embeddings for similarity search.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "vector_field",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "chunk_embedding"
+              },
+              "verify_certs": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Verify SSL Certificates",
+                "dynamic": false,
+                "info": "Verify SSL certificates when connecting. Disable for self-signed certificates in development environments.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "verify_certs",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": false
+              }
+            },
+            "tool_mode": false
+          },
+          "selected_output": "dataframe",
+          "showNode": true,
+          "type": "OpenSearchVectorStoreComponent"
+        },
+        "dragging": false,
+        "id": "OpenSearchHybrid-Ve6bS",
+        "measured": {
+          "height": 822,
+          "width": 320
+        },
+        "position": {
+          "x": 2694.183983837566,
+          "y": 1425.777807367294
+        },
+        "selected": true,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "URLComponent-lnA0q",
+          "node": {
+            "base_classes": [
+              "DataFrame",
+              "Message"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Fetch content from one or more web pages, following links recursively.",
+            "display_name": "URL",
+            "documentation": "https://docs.langflow.org/components-data#url",
+            "edited": true,
+            "field_order": [
+              "urls",
+              "max_depth",
+              "prevent_outside",
+              "use_async",
+              "format",
+              "timeout",
+              "headers",
+              "filter_text_html",
+              "continue_on_failure",
+              "check_response_status",
+              "autoset_encoding"
+            ],
+            "frozen": false,
+            "icon": "layout-template",
+            "legacy": false,
+            "lf_version": "1.6.0",
+            "metadata": {
+              "code_hash": "4c72ce0f2e34",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "requests",
+                    "version": "2.32.5"
+                  },
+                  {
+                    "name": "bs4",
+                    "version": "4.12.3"
+                  },
+                  {
+                    "name": "langchain_community",
+                    "version": "0.3.21"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 4
+              },
+              "module": "custom_components.url"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Extracted Pages",
+                "group_outputs": false,
+                "hidden": null,
+                "method": "fetch_content",
+                "name": "page_results",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              },
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Raw Content",
+                "group_outputs": false,
+                "hidden": null,
+                "method": "fetch_content_as_message",
+                "name": "raw_results",
+                "options": null,
+                "required_inputs": null,
+                "selected": "Message",
+                "tool_mode": false,
+                "types": [
+                  "Message"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "autoset_encoding": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Autoset Encoding",
+                "dynamic": false,
+                "info": "If enabled, automatically sets the encoding of the request.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "autoset_encoding",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "check_response_status": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Check Response Status",
+                "dynamic": false,
+                "info": "If enabled, checks the response status of the request.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "check_response_status",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": false
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "import importlib\nimport re\n\nimport requests\nfrom bs4 import BeautifulSoup\nfrom langchain_community.document_loaders import RecursiveUrlLoader\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.helpers.data import safe_convert\nfrom lfx.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SliderInput, TableInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.utils.request_utils import get_user_agent\n\n# Constants\nDEFAULT_TIMEOUT = 30\nDEFAULT_MAX_DEPTH = 1\nDEFAULT_FORMAT = \"Text\"\n\n\nURL_REGEX = re.compile(\n    r\"^(https?:\\/\\/)?\" r\"(www\\.)?\" r\"([a-zA-Z0-9.-]+)\" r\"(\\.[a-zA-Z]{2,})?\" r\"(:\\d+)?\" r\"(\\/[^\\s]*)?$\",\n    re.IGNORECASE,\n)\n\nUSER_AGENT = None\n# Check if langflow is installed using importlib.util.find_spec(name))\nif importlib.util.find_spec(\"langflow\"):\n    langflow_installed = True\n    USER_AGENT = get_user_agent()\nelse:\n    langflow_installed = False\n    USER_AGENT = \"lfx\"\n\n\nclass URLComponent(Component):\n    \"\"\"A component that loads and parses content from web pages recursively.\n\n    This component allows fetching content from one or more URLs, with options to:\n    - Control crawl depth\n    - Prevent crawling outside the root domain\n    - Use async loading for better performance\n    - Extract either raw HTML or clean text\n    - Configure request headers and timeouts\n    \"\"\"\n\n    display_name = \"URL\"\n    description = \"Fetch content from one or more web pages, following links recursively.\"\n    documentation: str = \"https://docs.langflow.org/components-data#url\"\n    icon = \"layout-template\"\n    name = \"URLComponent\"\n\n    inputs = [\n        MessageTextInput(\n            name=\"urls\",\n            display_name=\"URLs\",\n            info=\"Enter one or more URLs to crawl recursively, by clicking the '+' button.\",\n            is_list=True,\n            tool_mode=True,\n            placeholder=\"Enter a URL...\",\n            list_add_label=\"Add URL\",\n            input_types=[\"Message\"],\n        ),\n        SliderInput(\n            name=\"max_depth\",\n            display_name=\"Depth\",\n            info=(\n                \"Controls how many 'clicks' away from the initial page the crawler will go:\\n\"\n                \"- depth 1: only the initial page\\n\"\n                \"- depth 2: initial page + all pages linked directly from it\\n\"\n                \"- depth 3: initial page + direct links + links found on those direct link pages\\n\"\n                \"Note: This is about link traversal, not URL path depth.\"\n            ),\n            value=DEFAULT_MAX_DEPTH,\n            range_spec=RangeSpec(min=1, max=5, step=1),\n            required=False,\n            min_label=\" \",\n            max_label=\" \",\n            min_label_icon=\"None\",\n            max_label_icon=\"None\",\n            # slider_input=True\n        ),\n        BoolInput(\n            name=\"prevent_outside\",\n            display_name=\"Prevent Outside\",\n            info=(\n                \"If enabled, only crawls URLs within the same domain as the root URL. \"\n                \"This helps prevent the crawler from going to external websites.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"use_async\",\n            display_name=\"Use Async\",\n            info=(\n                \"If enabled, uses asynchronous loading which can be significantly faster \"\n                \"but might use more system resources.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"format\",\n            display_name=\"Output Format\",\n            info=\"Output Format. Use 'Text' to extract the text from the HTML or 'HTML' for the raw HTML content.\",\n            options=[\"Text\", \"HTML\"],\n            value=DEFAULT_FORMAT,\n            advanced=True,\n        ),\n        IntInput(\n            name=\"timeout\",\n            display_name=\"Timeout\",\n            info=\"Timeout for the request in seconds.\",\n            value=DEFAULT_TIMEOUT,\n            required=False,\n            advanced=True,\n        ),\n        TableInput(\n            name=\"headers\",\n            display_name=\"Headers\",\n            info=\"The headers to send with the request\",\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Header\",\n                    \"type\": \"str\",\n                    \"description\": \"Header name\",\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"type\": \"str\",\n                    \"description\": \"Header value\",\n                },\n            ],\n            value=[{\"key\": \"User-Agent\", \"value\": USER_AGENT}],\n            advanced=True,\n            input_types=[\"DataFrame\"],\n        ),\n        BoolInput(\n            name=\"filter_text_html\",\n            display_name=\"Filter Text/HTML\",\n            info=\"If enabled, filters out text/css content type from the results.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"continue_on_failure\",\n            display_name=\"Continue on Failure\",\n            info=\"If enabled, continues crawling even if some requests fail.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"check_response_status\",\n            display_name=\"Check Response Status\",\n            info=\"If enabled, checks the response status of the request.\",\n            value=False,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autoset_encoding\",\n            display_name=\"Autoset Encoding\",\n            info=\"If enabled, automatically sets the encoding of the request.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Extracted Pages\", name=\"page_results\", method=\"fetch_content\"),\n        Output(display_name=\"Raw Content\", name=\"raw_results\", method=\"fetch_content_as_message\", tool_mode=False),\n    ]\n\n    @staticmethod\n    def validate_url(url: str) -> bool:\n        \"\"\"Validates if the given string matches URL pattern.\n\n        Args:\n            url: The URL string to validate\n\n        Returns:\n            bool: True if the URL is valid, False otherwise\n        \"\"\"\n        return bool(URL_REGEX.match(url))\n\n    def ensure_url(self, url: str) -> str:\n        \"\"\"Ensures the given string is a valid URL.\n\n        Args:\n            url: The URL string to validate and normalize\n\n        Returns:\n            str: The normalized URL\n\n        Raises:\n            ValueError: If the URL is invalid\n        \"\"\"\n        url = url.strip()\n        if not url.startswith((\"http://\", \"https://\")):\n            url = \"https://\" + url\n\n        if not self.validate_url(url):\n            msg = f\"Invalid URL: {url}\"\n            raise ValueError(msg)\n\n        return url\n\n    def _create_loader(self, url: str) -> RecursiveUrlLoader:\n        \"\"\"Creates a RecursiveUrlLoader instance with the configured settings.\n\n        Args:\n            url: The URL to load\n\n        Returns:\n            RecursiveUrlLoader: Configured loader instance\n        \"\"\"\n        headers_dict = {header[\"key\"]: header[\"value\"] for header in self.headers if header[\"value\"] is not None}\n        extractor = (lambda x: x) if self.format == \"HTML\" else (lambda x: BeautifulSoup(x, \"lxml\").get_text())\n\n        return RecursiveUrlLoader(\n            url=url,\n            max_depth=self.max_depth,\n            prevent_outside=self.prevent_outside,\n            use_async=self.use_async,\n            extractor=extractor,\n            timeout=self.timeout,\n            headers=headers_dict,\n            check_response_status=self.check_response_status,\n            continue_on_failure=self.continue_on_failure,\n            base_url=url,  # Add base_url to ensure consistent domain crawling\n            autoset_encoding=self.autoset_encoding,  # Enable automatic encoding detection\n            exclude_dirs=[],  # Allow customization of excluded directories\n            link_regex=None,  # Allow customization of link filtering\n        )\n\n    def fetch_url_contents(self) -> list[dict]:\n        \"\"\"Load documents from the configured URLs.\n\n        Returns:\n            List[Data]: List of Data objects containing the fetched content\n\n        Raises:\n            ValueError: If no valid URLs are provided or if there's an error loading documents\n        \"\"\"\n        try:\n            urls = list({self.ensure_url(url) for url in self.urls if url.strip()})\n            logger.debug(f\"URLs: {urls}\")\n            if not urls:\n                msg = \"No valid URLs provided.\"\n                raise ValueError(msg)\n\n            all_docs = []\n            for url in urls:\n                logger.debug(f\"Loading documents from {url}\")\n\n                try:\n                    loader = self._create_loader(url)\n                    docs = loader.load()\n\n                    if not docs:\n                        logger.warning(f\"No documents found for {url}\")\n                        continue\n\n                    logger.debug(f\"Found {len(docs)} documents from {url}\")\n                    all_docs.extend(docs)\n\n                except requests.exceptions.RequestException as e:\n                    logger.exception(f\"Error loading documents from {url}: {e}\")\n                    continue\n\n            if not all_docs:\n                msg = \"No documents were successfully loaded from any URL\"\n                raise ValueError(msg)\n\n            # data = [Data(text=doc.page_content, **doc.metadata) for doc in all_docs]\n            data = [\n                {\n                    \"text\": safe_convert(doc.page_content, clean_data=True),\n                    \"url\": doc.metadata.get(\"source\", \"\"),\n                    \"title\": doc.metadata.get(\"title\", \"\"),\n                    \"description\": doc.metadata.get(\"description\", \"\"),\n                    \"content_type\": doc.metadata.get(\"content_type\", \"\"),\n                    \"language\": doc.metadata.get(\"language\", \"\"),\n                }\n                for doc in all_docs\n            ]\n        except Exception as e:\n            error_msg = e.message if hasattr(e, \"message\") else e\n            msg = f\"Error loading documents: {error_msg!s}\"\n            logger.exception(msg)\n            raise ValueError(msg) from e\n        return data\n\n    def fetch_content(self) -> DataFrame:\n        \"\"\"Convert the documents to a DataFrame.\"\"\"\n        return DataFrame(data=self.fetch_url_contents())\n\n    def fetch_content_as_message(self) -> Message:\n        \"\"\"Convert the documents to a Message.\"\"\"\n        url_contents = self.fetch_url_contents()\n        return Message(text=\"\\n\\n\".join([x[\"text\"] for x in url_contents]), data={\"data\": url_contents})\n"
+              },
+              "continue_on_failure": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Continue on Failure",
+                "dynamic": false,
+                "info": "If enabled, continues crawling even if some requests fail.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "continue_on_failure",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "filter_text_html": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Filter Text/HTML",
+                "dynamic": false,
+                "info": "If enabled, filters out text/css content type from the results.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "filter_text_html",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "format": {
+                "_input_type": "DropdownInput",
+                "advanced": true,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Output Format",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Output Format. Use 'Text' to extract the text from the HTML or 'HTML' for the raw HTML content.",
+                "name": "format",
+                "options": [
+                  "Text",
+                  "HTML"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "Text"
+              },
+              "headers": {
+                "_input_type": "TableInput",
+                "advanced": true,
+                "display_name": "Headers",
+                "dynamic": false,
+                "info": "The headers to send with the request",
+                "input_types": [
+                  "DataFrame"
+                ],
+                "is_list": true,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "headers",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "table_icon": "Table",
+                "table_schema": [
+                  {
+                    "description": "Header name",
+                    "display_name": "Header",
+                    "name": "key",
+                    "type": "str"
+                  },
+                  {
+                    "description": "Header value",
+                    "display_name": "Value",
+                    "name": "value",
+                    "type": "str"
+                  }
+                ],
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "trigger_icon": "Table",
+                "trigger_text": "Open table",
+                "type": "table",
+                "value": [
+                  {
+                    "key": "User-Agent",
+                    "value": "langflow"
+                  }
+                ]
+              },
+              "max_depth": {
+                "_input_type": "SliderInput",
+                "advanced": false,
+                "display_name": "Depth",
+                "dynamic": false,
+                "info": "Controls how many 'clicks' away from the initial page the crawler will go:\n- depth 1: only the initial page\n- depth 2: initial page + all pages linked directly from it\n- depth 3: initial page + direct links + links found on those direct link pages\nNote: This is about link traversal, not URL path depth.",
+                "max_label": " ",
+                "max_label_icon": "None",
+                "min_label": " ",
+                "min_label_icon": "None",
+                "name": "max_depth",
+                "placeholder": "",
+                "range_spec": {
+                  "max": 5,
+                  "min": 1,
+                  "step": 1,
+                  "step_type": "float"
+                },
+                "required": false,
+                "show": true,
+                "slider_buttons": false,
+                "slider_buttons_options": [],
+                "slider_input": false,
+                "title_case": false,
+                "tool_mode": false,
+                "type": "slider",
+                "value": 1
+              },
+              "prevent_outside": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Prevent Outside",
+                "dynamic": false,
+                "info": "If enabled, only crawls URLs within the same domain as the root URL. This helps prevent the crawler from going to external websites.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "prevent_outside",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "timeout": {
+                "_input_type": "IntInput",
+                "advanced": true,
+                "display_name": "Timeout",
+                "dynamic": false,
+                "info": "Timeout for the request in seconds.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "timeout",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 30
+              },
+              "urls": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "URLs",
+                "dynamic": false,
+                "info": "Enter one or more URLs to crawl recursively, by clicking the '+' button.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": true,
+                "list_add_label": "Add URL",
+                "load_from_db": false,
+                "name": "urls",
+                "placeholder": "Enter a URL...",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": true,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "use_async": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Use Async",
+                "dynamic": false,
+                "info": "If enabled, uses asynchronous loading which can be significantly faster but might use more system resources.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "use_async",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              }
+            },
+            "tool_mode": false
+          },
+          "selected_output": "page_results",
+          "showNode": true,
+          "type": "URLComponent"
+        },
+        "dragging": false,
+        "id": "URLComponent-lnA0q",
+        "measured": {
+          "height": 292,
+          "width": 320
+        },
+        "position": {
+          "x": 1249.8241608743583,
+          "y": 1270.7229143090308
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "description": "Get chat inputs from the Playground.",
+          "display_name": "Chat Input",
+          "id": "ChatInput-WLvBD",
+          "node": {
+            "base_classes": [
+              "Message"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Get chat inputs from the Playground.",
+            "display_name": "Chat Input",
+            "documentation": "https://docs.langflow.org/components-io#chat-input",
+            "edited": false,
+            "field_order": [
+              "input_value",
+              "should_store_message",
+              "sender",
+              "sender_name",
+              "session_id",
+              "files"
+            ],
+            "frozen": false,
+            "icon": "MessagesSquare",
+            "legacy": false,
+            "lf_version": "1.6.0",
+            "metadata": {
+              "code_hash": "f701f686b325",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 1
+              },
+              "module": "custom_components.chat_input"
+            },
+            "minimized": true,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Chat Message",
+                "group_outputs": false,
+                "method": "message_response",
+                "name": "message",
+                "options": null,
+                "required_inputs": null,
+                "selected": "Message",
+                "tool_mode": true,
+                "types": [
+                  "Message"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "from lfx.base.data.utils import IMG_FILE_TYPES, TEXT_FILE_TYPES\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.inputs.inputs import BoolInput\nfrom lfx.io import (\n    DropdownInput,\n    FileInput,\n    MessageTextInput,\n    MultilineInput,\n    Output,\n)\nfrom lfx.schema.message import Message\nfrom lfx.utils.constants import (\n    MESSAGE_SENDER_AI,\n    MESSAGE_SENDER_NAME_USER,\n    MESSAGE_SENDER_USER,\n)\n\n\nclass ChatInput(ChatComponent):\n    display_name = \"Chat Input\"\n    description = \"Get chat inputs from the Playground.\"\n    documentation: str = \"https://docs.langflow.org/components-io#chat-input\"\n    icon = \"MessagesSquare\"\n    name = \"ChatInput\"\n    minimized = True\n\n    inputs = [\n        MultilineInput(\n            name=\"input_value\",\n            display_name=\"Input Text\",\n            value=\"\",\n            info=\"Message to be passed as input.\",\n            input_types=[],\n        ),\n        BoolInput(\n            name=\"should_store_message\",\n            display_name=\"Store Messages\",\n            info=\"Store the message in the history.\",\n            value=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"sender\",\n            display_name=\"Sender Type\",\n            options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n            value=MESSAGE_SENDER_USER,\n            info=\"Type of sender.\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"sender_name\",\n            display_name=\"Sender Name\",\n            info=\"Name of the sender.\",\n            value=MESSAGE_SENDER_NAME_USER,\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"session_id\",\n            display_name=\"Session ID\",\n            info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n            advanced=True,\n        ),\n        FileInput(\n            name=\"files\",\n            display_name=\"Files\",\n            file_types=TEXT_FILE_TYPES + IMG_FILE_TYPES,\n            info=\"Files to be sent with the message.\",\n            advanced=True,\n            is_list=True,\n            temp_file=True,\n        ),\n    ]\n    outputs = [\n        Output(display_name=\"Chat Message\", name=\"message\", method=\"message_response\"),\n    ]\n\n    async def message_response(self) -> Message:\n        # Ensure files is a list and filter out empty/None values\n        files = self.files if self.files else []\n        if files and not isinstance(files, list):\n            files = [files]\n        # Filter out None/empty values\n        files = [f for f in files if f is not None and f != \"\"]\n\n        message = await Message.create(\n            text=self.input_value,\n            sender=self.sender,\n            sender_name=self.sender_name,\n            session_id=self.session_id,\n            files=files,\n        )\n        if self.session_id and isinstance(message, Message) and self.should_store_message:\n            stored_message = await self.send_message(\n                message,\n            )\n            self.message.value = stored_message\n            message = stored_message\n\n        self.status = message\n        return message\n"
+              },
+              "files": {
+                "_input_type": "FileInput",
+                "advanced": true,
+                "display_name": "Files",
+                "dynamic": false,
+                "fileTypes": [
+                  "csv",
+                  "json",
+                  "pdf",
+                  "txt",
+                  "md",
+                  "mdx",
+                  "yaml",
+                  "yml",
+                  "xml",
+                  "html",
+                  "htm",
+                  "docx",
+                  "py",
+                  "sh",
+                  "sql",
+                  "js",
+                  "ts",
+                  "tsx",
+                  "jpg",
+                  "jpeg",
+                  "png",
+                  "bmp",
+                  "image"
+                ],
+                "file_path": "",
+                "info": "Files to be sent with the message.",
+                "list": true,
+                "list_add_label": "Add More",
+                "name": "files",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "temp_file": true,
+                "title_case": false,
+                "trace_as_metadata": true,
+                "type": "file",
+                "value": ""
+              },
+              "input_value": {
+                "_input_type": "MultilineInput",
+                "advanced": false,
+                "copy_field": false,
+                "display_name": "Input Text",
+                "dynamic": false,
+                "info": "Message to be passed as input.",
+                "input_types": [],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "multiline": true,
+                "name": "input_value",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "www.langflow.org"
+              },
+              "sender": {
+                "_input_type": "DropdownInput",
+                "advanced": true,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Sender Type",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Type of sender.",
+                "name": "sender",
+                "options": [
+                  "Machine",
+                  "User"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "User"
+              },
+              "sender_name": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "Sender Name",
+                "dynamic": false,
+                "info": "Name of the sender.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "sender_name",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "User"
+              },
+              "session_id": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "Session ID",
+                "dynamic": false,
+                "info": "The session ID of the chat. If empty, the current session ID parameter will be used.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "session_id",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "should_store_message": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Store Messages",
+                "dynamic": false,
+                "info": "Store the message in the history.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "should_store_message",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "ChatInput"
+        },
+        "dragging": false,
+        "id": "ChatInput-WLvBD",
+        "measured": {
+          "height": 204,
+          "width": 320
+        },
+        "position": {
+          "x": 884.822226410103,
+          "y": 1554.894873551992
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "DataFrameOperations-hqIoy",
+          "node": {
+            "base_classes": [
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Perform various operations on a DataFrame.",
+            "display_name": "DataFrame Operations",
+            "documentation": "https://docs.langflow.org/components-processing#dataframe-operations",
+            "edited": false,
+            "field_order": [
+              "df",
+              "operation",
+              "column_name",
+              "filter_value",
+              "filter_operator",
+              "ascending",
+              "new_column_name",
+              "new_column_value",
+              "columns_to_select",
+              "num_rows",
+              "replace_value",
+              "replacement_value"
+            ],
+            "frozen": false,
+            "icon": "table",
+            "last_updated": "2025-10-03T20:31:36.023Z",
+            "legacy": false,
+            "lf_version": "1.6.0",
+            "metadata": {
+              "code_hash": "b4d6b19b6eef",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "pandas",
+                    "version": "2.2.3"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "lfx.components.processing.dataframe_operations.DataFrameOperationsComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "group_outputs": false,
+                "method": "perform_operation",
+                "name": "output",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "ascending": {
+                "_input_type": "BoolInput",
+                "advanced": false,
+                "display_name": "Sort Ascending",
+                "dynamic": true,
+                "info": "Whether to sort in ascending order.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ascending",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "import pandas as pd\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import BoolInput, DataFrameInput, DropdownInput, IntInput, MessageTextInput, Output, StrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DataFrameOperationsComponent(Component):\n    display_name = \"DataFrame Operations\"\n    description = \"Perform various operations on a DataFrame.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#dataframe-operations\"\n    icon = \"table\"\n    name = \"DataFrameOperations\"\n\n    OPERATION_CHOICES = [\n        \"Add Column\",\n        \"Drop Column\",\n        \"Filter\",\n        \"Head\",\n        \"Rename Column\",\n        \"Replace Value\",\n        \"Select Columns\",\n        \"Sort\",\n        \"Tail\",\n        \"Drop Duplicates\",\n    ]\n\n    inputs = [\n        DataFrameInput(\n            name=\"df\",\n            display_name=\"DataFrame\",\n            info=\"The input DataFrame to operate on.\",\n            required=True,\n        ),\n        SortableListInput(\n            name=\"operation\",\n            display_name=\"Operation\",\n            placeholder=\"Select Operation\",\n            info=\"Select the DataFrame operation to perform.\",\n            options=[\n                {\"name\": \"Add Column\", \"icon\": \"plus\"},\n                {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n                {\"name\": \"Filter\", \"icon\": \"filter\"},\n                {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n                {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n                {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n                {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n                {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n                {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n                {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n            ],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        StrInput(\n            name=\"column_name\",\n            display_name=\"Column Name\",\n            info=\"The column name to use for the operation.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"filter_value\",\n            display_name=\"Filter Value\",\n            info=\"The value to filter rows by.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"filter_operator\",\n            display_name=\"Filter Operator\",\n            options=[\n                \"equals\",\n                \"not equals\",\n                \"contains\",\n                \"not contains\",\n                \"starts with\",\n                \"ends with\",\n                \"greater than\",\n                \"less than\",\n            ],\n            value=\"equals\",\n            info=\"The operator to apply for filtering rows.\",\n            advanced=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"ascending\",\n            display_name=\"Sort Ascending\",\n            info=\"Whether to sort in ascending order.\",\n            dynamic=True,\n            show=False,\n            value=True,\n        ),\n        StrInput(\n            name=\"new_column_name\",\n            display_name=\"New Column Name\",\n            info=\"The new column name when renaming or adding a column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"new_column_value\",\n            display_name=\"New Column Value\",\n            info=\"The value to populate the new column with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"columns_to_select\",\n            display_name=\"Columns to Select\",\n            dynamic=True,\n            is_list=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"num_rows\",\n            display_name=\"Number of Rows\",\n            info=\"Number of rows to return (for head/tail).\",\n            dynamic=True,\n            show=False,\n            value=5,\n        ),\n        MessageTextInput(\n            name=\"replace_value\",\n            display_name=\"Value to Replace\",\n            info=\"The value to replace in the column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"replacement_value\",\n            display_name=\"Replacement Value\",\n            info=\"The value to replace with.\",\n            dynamic=True,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(\n            display_name=\"DataFrame\",\n            name=\"output\",\n            method=\"perform_operation\",\n            info=\"The resulting DataFrame after the operation.\",\n        )\n    ]\n\n    def update_build_config(self, build_config, field_value, field_name=None):\n        dynamic_fields = [\n            \"column_name\",\n            \"filter_value\",\n            \"filter_operator\",\n            \"ascending\",\n            \"new_column_name\",\n            \"new_column_value\",\n            \"columns_to_select\",\n            \"num_rows\",\n            \"replace_value\",\n            \"replacement_value\",\n        ]\n        for field in dynamic_fields:\n            build_config[field][\"show\"] = False\n\n        if field_name == \"operation\":\n            # Handle SortableListInput format\n            if isinstance(field_value, list):\n                operation_name = field_value[0].get(\"name\", \"\") if field_value else \"\"\n            else:\n                operation_name = field_value or \"\"\n\n            # If no operation selected, all dynamic fields stay hidden (already set to False above)\n            if not operation_name:\n                return build_config\n\n            if operation_name == \"Filter\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"filter_value\"][\"show\"] = True\n                build_config[\"filter_operator\"][\"show\"] = True\n            elif operation_name == \"Sort\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"ascending\"][\"show\"] = True\n            elif operation_name == \"Drop Column\":\n                build_config[\"column_name\"][\"show\"] = True\n            elif operation_name == \"Rename Column\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"new_column_name\"][\"show\"] = True\n            elif operation_name == \"Add Column\":\n                build_config[\"new_column_name\"][\"show\"] = True\n                build_config[\"new_column_value\"][\"show\"] = True\n            elif operation_name == \"Select Columns\":\n                build_config[\"columns_to_select\"][\"show\"] = True\n            elif operation_name in {\"Head\", \"Tail\"}:\n                build_config[\"num_rows\"][\"show\"] = True\n            elif operation_name == \"Replace Value\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"replace_value\"][\"show\"] = True\n                build_config[\"replacement_value\"][\"show\"] = True\n            elif operation_name == \"Drop Duplicates\":\n                build_config[\"column_name\"][\"show\"] = True\n\n        return build_config\n\n    def perform_operation(self) -> DataFrame:\n        df_copy = self.df.copy()\n\n        # Handle SortableListInput format for operation\n        operation_input = getattr(self, \"operation\", [])\n        if isinstance(operation_input, list) and len(operation_input) > 0:\n            op = operation_input[0].get(\"name\", \"\")\n        else:\n            op = \"\"\n\n        # If no operation selected, return original DataFrame\n        if not op:\n            return df_copy\n\n        if op == \"Filter\":\n            return self.filter_rows_by_value(df_copy)\n        if op == \"Sort\":\n            return self.sort_by_column(df_copy)\n        if op == \"Drop Column\":\n            return self.drop_column(df_copy)\n        if op == \"Rename Column\":\n            return self.rename_column(df_copy)\n        if op == \"Add Column\":\n            return self.add_column(df_copy)\n        if op == \"Select Columns\":\n            return self.select_columns(df_copy)\n        if op == \"Head\":\n            return self.head(df_copy)\n        if op == \"Tail\":\n            return self.tail(df_copy)\n        if op == \"Replace Value\":\n            return self.replace_values(df_copy)\n        if op == \"Drop Duplicates\":\n            return self.drop_duplicates(df_copy)\n        msg = f\"Unsupported operation: {op}\"\n        logger.error(msg)\n        raise ValueError(msg)\n\n    def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        filter_value = self.filter_value\n\n        # Handle regular DropdownInput format (just a string value)\n        operator = getattr(self, \"filter_operator\", \"equals\")  # Default to equals for backward compatibility\n\n        if operator == \"equals\":\n            mask = column == filter_value\n        elif operator == \"not equals\":\n            mask = column != filter_value\n        elif operator == \"contains\":\n            mask = column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"not contains\":\n            mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"starts with\":\n            mask = column.astype(str).str.startswith(str(filter_value), na=False)\n        elif operator == \"ends with\":\n            mask = column.astype(str).str.endswith(str(filter_value), na=False)\n        elif operator == \"greater than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column > numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) > str(filter_value)\n        elif operator == \"less than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column < numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) < str(filter_value)\n        else:\n            mask = column == filter_value  # Fallback to equals\n\n        return DataFrame(df[mask])\n\n    def sort_by_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n    def drop_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop(columns=[self.column_name]))\n\n    def rename_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n    def add_column(self, df: DataFrame) -> DataFrame:\n        df[self.new_column_name] = [self.new_column_value] * len(df)\n        return DataFrame(df)\n\n    def select_columns(self, df: DataFrame) -> DataFrame:\n        columns = [col.strip() for col in self.columns_to_select]\n        return DataFrame(df[columns])\n\n    def head(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.head(self.num_rows))\n\n    def tail(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.tail(self.num_rows))\n\n    def replace_values(self, df: DataFrame) -> DataFrame:\n        df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n        return DataFrame(df)\n\n    def drop_duplicates(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop_duplicates(subset=self.column_name))\n"
+              },
+              "column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Column Name",
+                "dynamic": true,
+                "info": "The column name to use for the operation.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "column_name",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "columns_to_select": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Columns to Select",
+                "dynamic": true,
+                "info": "",
+                "list": true,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "columns_to_select",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "df": {
+                "_input_type": "DataFrameInput",
+                "advanced": false,
+                "display_name": "DataFrame",
+                "dynamic": false,
+                "info": "The input DataFrame to operate on.",
+                "input_types": [
+                  "DataFrame"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "df",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "filter_operator": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Filter Operator",
+                "dynamic": true,
+                "external_options": {},
+                "info": "The operator to apply for filtering rows.",
+                "name": "filter_operator",
+                "options": [
+                  "equals",
+                  "not equals",
+                  "contains",
+                  "not contains",
+                  "starts with",
+                  "ends with",
+                  "greater than",
+                  "less than"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "equals"
+              },
+              "filter_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Filter Value",
+                "dynamic": true,
+                "info": "The value to filter rows by.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "filter_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "new_column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "New Column Name",
+                "dynamic": true,
+                "info": "The new column name when renaming or adding a column.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "new_column_name",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "filename"
+              },
+              "new_column_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "New Column Value",
+                "dynamic": true,
+                "info": "The value to populate the new column with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "new_column_value",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "num_rows": {
+                "_input_type": "IntInput",
+                "advanced": false,
+                "display_name": "Number of Rows",
+                "dynamic": true,
+                "info": "Number of rows to return (for head/tail).",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "num_rows",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 5
+              },
+              "operation": {
+                "_input_type": "SortableListInput",
+                "advanced": false,
+                "display_name": "Operation",
+                "dynamic": false,
+                "info": "Select the DataFrame operation to perform.",
+                "limit": 1,
+                "name": "operation",
+                "options": [
+                  {
+                    "icon": "plus",
+                    "name": "Add Column"
+                  },
+                  {
+                    "icon": "minus",
+                    "name": "Drop Column"
+                  },
+                  {
+                    "icon": "filter",
+                    "name": "Filter"
+                  },
+                  {
+                    "icon": "arrow-up",
+                    "name": "Head"
+                  },
+                  {
+                    "icon": "pencil",
+                    "name": "Rename Column"
+                  },
+                  {
+                    "icon": "replace",
+                    "name": "Replace Value"
+                  },
+                  {
+                    "icon": "columns",
+                    "name": "Select Columns"
+                  },
+                  {
+                    "icon": "arrow-up-down",
+                    "name": "Sort"
+                  },
+                  {
+                    "icon": "arrow-down",
+                    "name": "Tail"
+                  },
+                  {
+                    "icon": "copy-x",
+                    "name": "Drop Duplicates"
+                  }
+                ],
+                "placeholder": "Select Operation",
+                "real_time_refresh": true,
+                "required": false,
+                "search_category": [],
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "sortableList",
+                "value": [
+                  {
+                    "chosen": false,
+                    "icon": "plus",
+                    "name": "Add Column",
+                    "selected": false
+                  }
+                ]
+              },
+              "replace_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Value to Replace",
+                "dynamic": true,
+                "info": "The value to replace in the column.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replace_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "replacement_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Replacement Value",
+                "dynamic": true,
+                "info": "The value to replace with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replacement_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "DataFrameOperations"
+        },
+        "dragging": false,
+        "id": "DataFrameOperations-hqIoy",
+        "measured": {
+          "height": 399,
+          "width": 320
+        },
+        "position": {
+          "x": 1601.8752590736613,
+          "y": 1442.944202002645
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "DataFrameOperations-A98BL",
+          "node": {
+            "base_classes": [
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Perform various operations on a DataFrame.",
+            "display_name": "DataFrame Operations",
+            "documentation": "https://docs.langflow.org/components-processing#dataframe-operations",
+            "edited": false,
+            "field_order": [
+              "df",
+              "operation",
+              "column_name",
+              "filter_value",
+              "filter_operator",
+              "ascending",
+              "new_column_name",
+              "new_column_value",
+              "columns_to_select",
+              "num_rows",
+              "replace_value",
+              "replacement_value"
+            ],
+            "frozen": false,
+            "icon": "table",
+            "last_updated": "2025-10-03T20:31:36.025Z",
+            "legacy": false,
+            "lf_version": "1.6.0",
+            "metadata": {
+              "code_hash": "b4d6b19b6eef",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "pandas",
+                    "version": "2.2.3"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "lfx.components.processing.dataframe_operations.DataFrameOperationsComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "group_outputs": false,
+                "method": "perform_operation",
+                "name": "output",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "ascending": {
+                "_input_type": "BoolInput",
+                "advanced": false,
+                "display_name": "Sort Ascending",
+                "dynamic": true,
+                "info": "Whether to sort in ascending order.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ascending",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "import pandas as pd\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import BoolInput, DataFrameInput, DropdownInput, IntInput, MessageTextInput, Output, StrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DataFrameOperationsComponent(Component):\n    display_name = \"DataFrame Operations\"\n    description = \"Perform various operations on a DataFrame.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#dataframe-operations\"\n    icon = \"table\"\n    name = \"DataFrameOperations\"\n\n    OPERATION_CHOICES = [\n        \"Add Column\",\n        \"Drop Column\",\n        \"Filter\",\n        \"Head\",\n        \"Rename Column\",\n        \"Replace Value\",\n        \"Select Columns\",\n        \"Sort\",\n        \"Tail\",\n        \"Drop Duplicates\",\n    ]\n\n    inputs = [\n        DataFrameInput(\n            name=\"df\",\n            display_name=\"DataFrame\",\n            info=\"The input DataFrame to operate on.\",\n            required=True,\n        ),\n        SortableListInput(\n            name=\"operation\",\n            display_name=\"Operation\",\n            placeholder=\"Select Operation\",\n            info=\"Select the DataFrame operation to perform.\",\n            options=[\n                {\"name\": \"Add Column\", \"icon\": \"plus\"},\n                {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n                {\"name\": \"Filter\", \"icon\": \"filter\"},\n                {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n                {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n                {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n                {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n                {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n                {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n                {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n            ],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        StrInput(\n            name=\"column_name\",\n            display_name=\"Column Name\",\n            info=\"The column name to use for the operation.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"filter_value\",\n            display_name=\"Filter Value\",\n            info=\"The value to filter rows by.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"filter_operator\",\n            display_name=\"Filter Operator\",\n            options=[\n                \"equals\",\n                \"not equals\",\n                \"contains\",\n                \"not contains\",\n                \"starts with\",\n                \"ends with\",\n                \"greater than\",\n                \"less than\",\n            ],\n            value=\"equals\",\n            info=\"The operator to apply for filtering rows.\",\n            advanced=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"ascending\",\n            display_name=\"Sort Ascending\",\n            info=\"Whether to sort in ascending order.\",\n            dynamic=True,\n            show=False,\n            value=True,\n        ),\n        StrInput(\n            name=\"new_column_name\",\n            display_name=\"New Column Name\",\n            info=\"The new column name when renaming or adding a column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"new_column_value\",\n            display_name=\"New Column Value\",\n            info=\"The value to populate the new column with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"columns_to_select\",\n            display_name=\"Columns to Select\",\n            dynamic=True,\n            is_list=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"num_rows\",\n            display_name=\"Number of Rows\",\n            info=\"Number of rows to return (for head/tail).\",\n            dynamic=True,\n            show=False,\n            value=5,\n        ),\n        MessageTextInput(\n            name=\"replace_value\",\n            display_name=\"Value to Replace\",\n            info=\"The value to replace in the column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"replacement_value\",\n            display_name=\"Replacement Value\",\n            info=\"The value to replace with.\",\n            dynamic=True,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(\n            display_name=\"DataFrame\",\n            name=\"output\",\n            method=\"perform_operation\",\n            info=\"The resulting DataFrame after the operation.\",\n        )\n    ]\n\n    def update_build_config(self, build_config, field_value, field_name=None):\n        dynamic_fields = [\n            \"column_name\",\n            \"filter_value\",\n            \"filter_operator\",\n            \"ascending\",\n            \"new_column_name\",\n            \"new_column_value\",\n            \"columns_to_select\",\n            \"num_rows\",\n            \"replace_value\",\n            \"replacement_value\",\n        ]\n        for field in dynamic_fields:\n            build_config[field][\"show\"] = False\n\n        if field_name == \"operation\":\n            # Handle SortableListInput format\n            if isinstance(field_value, list):\n                operation_name = field_value[0].get(\"name\", \"\") if field_value else \"\"\n            else:\n                operation_name = field_value or \"\"\n\n            # If no operation selected, all dynamic fields stay hidden (already set to False above)\n            if not operation_name:\n                return build_config\n\n            if operation_name == \"Filter\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"filter_value\"][\"show\"] = True\n                build_config[\"filter_operator\"][\"show\"] = True\n            elif operation_name == \"Sort\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"ascending\"][\"show\"] = True\n            elif operation_name == \"Drop Column\":\n                build_config[\"column_name\"][\"show\"] = True\n            elif operation_name == \"Rename Column\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"new_column_name\"][\"show\"] = True\n            elif operation_name == \"Add Column\":\n                build_config[\"new_column_name\"][\"show\"] = True\n                build_config[\"new_column_value\"][\"show\"] = True\n            elif operation_name == \"Select Columns\":\n                build_config[\"columns_to_select\"][\"show\"] = True\n            elif operation_name in {\"Head\", \"Tail\"}:\n                build_config[\"num_rows\"][\"show\"] = True\n            elif operation_name == \"Replace Value\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"replace_value\"][\"show\"] = True\n                build_config[\"replacement_value\"][\"show\"] = True\n            elif operation_name == \"Drop Duplicates\":\n                build_config[\"column_name\"][\"show\"] = True\n\n        return build_config\n\n    def perform_operation(self) -> DataFrame:\n        df_copy = self.df.copy()\n\n        # Handle SortableListInput format for operation\n        operation_input = getattr(self, \"operation\", [])\n        if isinstance(operation_input, list) and len(operation_input) > 0:\n            op = operation_input[0].get(\"name\", \"\")\n        else:\n            op = \"\"\n\n        # If no operation selected, return original DataFrame\n        if not op:\n            return df_copy\n\n        if op == \"Filter\":\n            return self.filter_rows_by_value(df_copy)\n        if op == \"Sort\":\n            return self.sort_by_column(df_copy)\n        if op == \"Drop Column\":\n            return self.drop_column(df_copy)\n        if op == \"Rename Column\":\n            return self.rename_column(df_copy)\n        if op == \"Add Column\":\n            return self.add_column(df_copy)\n        if op == \"Select Columns\":\n            return self.select_columns(df_copy)\n        if op == \"Head\":\n            return self.head(df_copy)\n        if op == \"Tail\":\n            return self.tail(df_copy)\n        if op == \"Replace Value\":\n            return self.replace_values(df_copy)\n        if op == \"Drop Duplicates\":\n            return self.drop_duplicates(df_copy)\n        msg = f\"Unsupported operation: {op}\"\n        logger.error(msg)\n        raise ValueError(msg)\n\n    def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        filter_value = self.filter_value\n\n        # Handle regular DropdownInput format (just a string value)\n        operator = getattr(self, \"filter_operator\", \"equals\")  # Default to equals for backward compatibility\n\n        if operator == \"equals\":\n            mask = column == filter_value\n        elif operator == \"not equals\":\n            mask = column != filter_value\n        elif operator == \"contains\":\n            mask = column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"not contains\":\n            mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"starts with\":\n            mask = column.astype(str).str.startswith(str(filter_value), na=False)\n        elif operator == \"ends with\":\n            mask = column.astype(str).str.endswith(str(filter_value), na=False)\n        elif operator == \"greater than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column > numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) > str(filter_value)\n        elif operator == \"less than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column < numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) < str(filter_value)\n        else:\n            mask = column == filter_value  # Fallback to equals\n\n        return DataFrame(df[mask])\n\n    def sort_by_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n    def drop_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop(columns=[self.column_name]))\n\n    def rename_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n    def add_column(self, df: DataFrame) -> DataFrame:\n        df[self.new_column_name] = [self.new_column_value] * len(df)\n        return DataFrame(df)\n\n    def select_columns(self, df: DataFrame) -> DataFrame:\n        columns = [col.strip() for col in self.columns_to_select]\n        return DataFrame(df[columns])\n\n    def head(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.head(self.num_rows))\n\n    def tail(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.tail(self.num_rows))\n\n    def replace_values(self, df: DataFrame) -> DataFrame:\n        df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n        return DataFrame(df)\n\n    def drop_duplicates(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop_duplicates(subset=self.column_name))\n"
+              },
+              "column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Column Name",
+                "dynamic": true,
+                "info": "The column name to use for the operation.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "column_name",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "columns_to_select": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Columns to Select",
+                "dynamic": true,
+                "info": "",
+                "list": true,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "columns_to_select",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "df": {
+                "_input_type": "DataFrameInput",
+                "advanced": false,
+                "display_name": "DataFrame",
+                "dynamic": false,
+                "info": "The input DataFrame to operate on.",
+                "input_types": [
+                  "DataFrame"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "df",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "filter_operator": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Filter Operator",
+                "dynamic": true,
+                "external_options": {},
+                "info": "The operator to apply for filtering rows.",
+                "name": "filter_operator",
+                "options": [
+                  "equals",
+                  "not equals",
+                  "contains",
+                  "not contains",
+                  "starts with",
+                  "ends with",
+                  "greater than",
+                  "less than"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "equals"
+              },
+              "filter_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Filter Value",
+                "dynamic": true,
+                "info": "The value to filter rows by.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "filter_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "new_column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "New Column Name",
+                "dynamic": true,
+                "info": "The new column name when renaming or adding a column.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "new_column_name",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "mimetype"
+              },
+              "new_column_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "New Column Value",
+                "dynamic": true,
+                "info": "The value to populate the new column with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "new_column_value",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "text/html"
+              },
+              "num_rows": {
+                "_input_type": "IntInput",
+                "advanced": false,
+                "display_name": "Number of Rows",
+                "dynamic": true,
+                "info": "Number of rows to return (for head/tail).",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "num_rows",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 5
+              },
+              "operation": {
+                "_input_type": "SortableListInput",
+                "advanced": false,
+                "display_name": "Operation",
+                "dynamic": false,
+                "info": "Select the DataFrame operation to perform.",
+                "limit": 1,
+                "name": "operation",
+                "options": [
+                  {
+                    "icon": "plus",
+                    "name": "Add Column"
+                  },
+                  {
+                    "icon": "minus",
+                    "name": "Drop Column"
+                  },
+                  {
+                    "icon": "filter",
+                    "name": "Filter"
+                  },
+                  {
+                    "icon": "arrow-up",
+                    "name": "Head"
+                  },
+                  {
+                    "icon": "pencil",
+                    "name": "Rename Column"
+                  },
+                  {
+                    "icon": "replace",
+                    "name": "Replace Value"
+                  },
+                  {
+                    "icon": "columns",
+                    "name": "Select Columns"
+                  },
+                  {
+                    "icon": "arrow-up-down",
+                    "name": "Sort"
+                  },
+                  {
+                    "icon": "arrow-down",
+                    "name": "Tail"
+                  },
+                  {
+                    "icon": "copy-x",
+                    "name": "Drop Duplicates"
+                  }
+                ],
+                "placeholder": "Select Operation",
+                "real_time_refresh": true,
+                "required": false,
+                "search_category": [],
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "sortableList",
+                "value": [
+                  {
+                    "chosen": false,
+                    "icon": "plus",
+                    "name": "Add Column",
+                    "selected": false
+                  }
+                ]
+              },
+              "replace_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Value to Replace",
+                "dynamic": true,
+                "info": "The value to replace in the column.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replace_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "replacement_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Replacement Value",
+                "dynamic": true,
+                "info": "The value to replace with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replacement_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "DataFrameOperations"
+        },
+        "dragging": false,
+        "id": "DataFrameOperations-A98BL",
+        "measured": {
+          "height": 399,
+          "width": 320
+        },
+        "position": {
+          "x": 1946.8185577395595,
+          "y": 1432.2126327108165
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "ChatOutput-Q1dhr",
+          "node": {
+            "base_classes": [
+              "Message"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Display a chat message in the Playground.",
+            "display_name": "Chat Output",
+            "documentation": "https://docs.langflow.org/components-io#chat-output",
+            "edited": false,
+            "field_order": [
+              "input_value",
+              "should_store_message",
+              "sender",
+              "sender_name",
+              "session_id",
+              "data_template",
+              "clean_data"
+            ],
+            "frozen": false,
+            "icon": "MessagesSquare",
+            "legacy": false,
+            "metadata": {
+              "code_hash": "9647f4d2f4b4",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "orjson",
+                    "version": "3.10.15"
+                  },
+                  {
+                    "name": "fastapi",
+                    "version": "0.117.1"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 3
+              },
+              "module": "lfx.components.input_output.chat_output.ChatOutput"
+            },
+            "minimized": true,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Output Message",
+                "group_outputs": false,
+                "method": "message_response",
+                "name": "message",
+                "selected": "Message",
+                "tool_mode": true,
+                "types": [
+                  "Message"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "clean_data": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Basic Clean Data",
+                "dynamic": false,
+                "info": "Whether to clean data before converting to string.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "clean_data",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.schema.properties import Source\nfrom lfx.template.field.base import Output\nfrom lfx.utils.constants import (\n    MESSAGE_SENDER_AI,\n    MESSAGE_SENDER_NAME_AI,\n    MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n    display_name = \"Chat Output\"\n    description = \"Display a chat message in the Playground.\"\n    documentation: str = \"https://docs.langflow.org/components-io#chat-output\"\n    icon = \"MessagesSquare\"\n    name = \"ChatOutput\"\n    minimized = True\n\n    inputs = [\n        HandleInput(\n            name=\"input_value\",\n            display_name=\"Inputs\",\n            info=\"Message to be passed as output.\",\n            input_types=[\"Data\", \"DataFrame\", \"Message\"],\n            required=True,\n        ),\n        BoolInput(\n            name=\"should_store_message\",\n            display_name=\"Store Messages\",\n            info=\"Store the message in the history.\",\n            value=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"sender\",\n            display_name=\"Sender Type\",\n            options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n            value=MESSAGE_SENDER_AI,\n            advanced=True,\n            info=\"Type of sender.\",\n        ),\n        MessageTextInput(\n            name=\"sender_name\",\n            display_name=\"Sender Name\",\n            info=\"Name of the sender.\",\n            value=MESSAGE_SENDER_NAME_AI,\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"session_id\",\n            display_name=\"Session ID\",\n            info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"data_template\",\n            display_name=\"Data Template\",\n            value=\"{text}\",\n            advanced=True,\n            info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n        ),\n        BoolInput(\n            name=\"clean_data\",\n            display_name=\"Basic Clean Data\",\n            value=True,\n            advanced=True,\n            info=\"Whether to clean data before converting to string.\",\n        ),\n    ]\n    outputs = [\n        Output(\n            display_name=\"Output Message\",\n            name=\"message\",\n            method=\"message_response\",\n        ),\n    ]\n\n    def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n        source_dict = {}\n        if id_:\n            source_dict[\"id\"] = id_\n        if display_name:\n            source_dict[\"display_name\"] = display_name\n        if source:\n            # Handle case where source is a ChatOpenAI object\n            if hasattr(source, \"model_name\"):\n                source_dict[\"source\"] = source.model_name\n            elif hasattr(source, \"model\"):\n                source_dict[\"source\"] = str(source.model)\n            else:\n                source_dict[\"source\"] = str(source)\n        return Source(**source_dict)\n\n    async def message_response(self) -> Message:\n        # First convert the input to string if needed\n        text = self.convert_to_string()\n\n        # Get source properties\n        source, _, display_name, source_id = self.get_properties_from_source_component()\n\n        # Create or use existing Message object\n        if isinstance(self.input_value, Message):\n            message = self.input_value\n            # Update message properties\n            message.text = text\n        else:\n            message = Message(text=text)\n\n        # Set message properties\n        message.sender = self.sender\n        message.sender_name = self.sender_name\n        message.session_id = self.session_id\n        message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n        message.properties.source = self._build_source(source_id, display_name, source)\n\n        # Store message if needed\n        if self.session_id and self.should_store_message:\n            stored_message = await self.send_message(message)\n            self.message.value = stored_message\n            message = stored_message\n\n        self.status = message\n        return message\n\n    def _serialize_data(self, data: Data) -> str:\n        \"\"\"Serialize Data object to JSON string.\"\"\"\n        # Convert data.data to JSON-serializable format\n        serializable_data = jsonable_encoder(data.data)\n        # Serialize with orjson, enabling pretty printing with indentation\n        json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n        # Convert bytes to string and wrap in Markdown code blocks\n        return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n    def _validate_input(self) -> None:\n        \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n        if self.input_value is None:\n            msg = \"Input data cannot be None\"\n            raise ValueError(msg)\n        if isinstance(self.input_value, list) and not all(\n            isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n        ):\n            invalid_types = [\n                type(item).__name__\n                for item in self.input_value\n                if not isinstance(item, Message | Data | DataFrame | str)\n            ]\n            msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n            raise TypeError(msg)\n        if not isinstance(\n            self.input_value,\n            Message | Data | DataFrame | str | list | Generator | type(None),\n        ):\n            type_name = type(self.input_value).__name__\n            msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n            raise TypeError(msg)\n\n    def convert_to_string(self) -> str | Generator[Any, None, None]:\n        \"\"\"Convert input data to string with proper error handling.\"\"\"\n        self._validate_input()\n        if isinstance(self.input_value, list):\n            clean_data: bool = getattr(self, \"clean_data\", False)\n            return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n        if isinstance(self.input_value, Generator):\n            return self.input_value\n        return safe_convert(self.input_value)\n"
+              },
+              "data_template": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "Data Template",
+                "dynamic": false,
+                "info": "Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "data_template",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "{text}"
+              },
+              "input_value": {
+                "_input_type": "HandleInput",
+                "advanced": false,
+                "display_name": "Inputs",
+                "dynamic": false,
+                "info": "Message to be passed as output.",
+                "input_types": [
+                  "Data",
+                  "DataFrame",
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "input_value",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "sender": {
+                "_input_type": "DropdownInput",
+                "advanced": true,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Sender Type",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Type of sender.",
+                "name": "sender",
+                "options": [
+                  "Machine",
+                  "User"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "Machine"
+              },
+              "sender_name": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "Sender Name",
+                "dynamic": false,
+                "info": "Name of the sender.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "sender_name",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "AI"
+              },
+              "session_id": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "Session ID",
+                "dynamic": false,
+                "info": "The session ID of the chat. If empty, the current session ID parameter will be used.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "session_id",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "should_store_message": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Store Messages",
+                "dynamic": false,
+                "info": "Store the message in the history.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "should_store_message",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": false,
+          "type": "ChatOutput"
+        },
+        "dragging": false,
+        "id": "ChatOutput-Q1dhr",
+        "measured": {
+          "height": 48,
+          "width": 192
+        },
+        "position": {
+          "x": 3135.060664388748,
+          "y": 2541.1604512818694
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "DataFrameOperations-RhKoe",
+          "node": {
+            "base_classes": [
+              "DataFrame"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Perform various operations on a DataFrame.",
+            "display_name": "DataFrame Operations",
+            "documentation": "https://docs.langflow.org/components-processing#dataframe-operations",
+            "edited": false,
+            "field_order": [
+              "df",
+              "operation",
+              "column_name",
+              "filter_value",
+              "filter_operator",
+              "ascending",
+              "new_column_name",
+              "new_column_value",
+              "columns_to_select",
+              "num_rows",
+              "replace_value",
+              "replacement_value"
+            ],
+            "frozen": false,
+            "icon": "table",
+            "last_updated": "2025-10-03T20:31:36.026Z",
+            "legacy": false,
+            "metadata": {
+              "code_hash": "b4d6b19b6eef",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "pandas",
+                    "version": "2.2.3"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "lfx.components.processing.dataframe_operations.DataFrameOperationsComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "DataFrame",
+                "group_outputs": false,
+                "method": "perform_operation",
+                "name": "output",
+                "options": null,
+                "required_inputs": null,
+                "selected": "DataFrame",
+                "tool_mode": true,
+                "types": [
+                  "DataFrame"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "ascending": {
+                "_input_type": "BoolInput",
+                "advanced": false,
+                "display_name": "Sort Ascending",
+                "dynamic": true,
+                "info": "Whether to sort in ascending order.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "ascending",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": true
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "import pandas as pd\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs import SortableListInput\nfrom lfx.io import BoolInput, DataFrameInput, DropdownInput, IntInput, MessageTextInput, Output, StrInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DataFrameOperationsComponent(Component):\n    display_name = \"DataFrame Operations\"\n    description = \"Perform various operations on a DataFrame.\"\n    documentation: str = \"https://docs.langflow.org/components-processing#dataframe-operations\"\n    icon = \"table\"\n    name = \"DataFrameOperations\"\n\n    OPERATION_CHOICES = [\n        \"Add Column\",\n        \"Drop Column\",\n        \"Filter\",\n        \"Head\",\n        \"Rename Column\",\n        \"Replace Value\",\n        \"Select Columns\",\n        \"Sort\",\n        \"Tail\",\n        \"Drop Duplicates\",\n    ]\n\n    inputs = [\n        DataFrameInput(\n            name=\"df\",\n            display_name=\"DataFrame\",\n            info=\"The input DataFrame to operate on.\",\n            required=True,\n        ),\n        SortableListInput(\n            name=\"operation\",\n            display_name=\"Operation\",\n            placeholder=\"Select Operation\",\n            info=\"Select the DataFrame operation to perform.\",\n            options=[\n                {\"name\": \"Add Column\", \"icon\": \"plus\"},\n                {\"name\": \"Drop Column\", \"icon\": \"minus\"},\n                {\"name\": \"Filter\", \"icon\": \"filter\"},\n                {\"name\": \"Head\", \"icon\": \"arrow-up\"},\n                {\"name\": \"Rename Column\", \"icon\": \"pencil\"},\n                {\"name\": \"Replace Value\", \"icon\": \"replace\"},\n                {\"name\": \"Select Columns\", \"icon\": \"columns\"},\n                {\"name\": \"Sort\", \"icon\": \"arrow-up-down\"},\n                {\"name\": \"Tail\", \"icon\": \"arrow-down\"},\n                {\"name\": \"Drop Duplicates\", \"icon\": \"copy-x\"},\n            ],\n            real_time_refresh=True,\n            limit=1,\n        ),\n        StrInput(\n            name=\"column_name\",\n            display_name=\"Column Name\",\n            info=\"The column name to use for the operation.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"filter_value\",\n            display_name=\"Filter Value\",\n            info=\"The value to filter rows by.\",\n            dynamic=True,\n            show=False,\n        ),\n        DropdownInput(\n            name=\"filter_operator\",\n            display_name=\"Filter Operator\",\n            options=[\n                \"equals\",\n                \"not equals\",\n                \"contains\",\n                \"not contains\",\n                \"starts with\",\n                \"ends with\",\n                \"greater than\",\n                \"less than\",\n            ],\n            value=\"equals\",\n            info=\"The operator to apply for filtering rows.\",\n            advanced=False,\n            dynamic=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"ascending\",\n            display_name=\"Sort Ascending\",\n            info=\"Whether to sort in ascending order.\",\n            dynamic=True,\n            show=False,\n            value=True,\n        ),\n        StrInput(\n            name=\"new_column_name\",\n            display_name=\"New Column Name\",\n            info=\"The new column name when renaming or adding a column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"new_column_value\",\n            display_name=\"New Column Value\",\n            info=\"The value to populate the new column with.\",\n            dynamic=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"columns_to_select\",\n            display_name=\"Columns to Select\",\n            dynamic=True,\n            is_list=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"num_rows\",\n            display_name=\"Number of Rows\",\n            info=\"Number of rows to return (for head/tail).\",\n            dynamic=True,\n            show=False,\n            value=5,\n        ),\n        MessageTextInput(\n            name=\"replace_value\",\n            display_name=\"Value to Replace\",\n            info=\"The value to replace in the column.\",\n            dynamic=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"replacement_value\",\n            display_name=\"Replacement Value\",\n            info=\"The value to replace with.\",\n            dynamic=True,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(\n            display_name=\"DataFrame\",\n            name=\"output\",\n            method=\"perform_operation\",\n            info=\"The resulting DataFrame after the operation.\",\n        )\n    ]\n\n    def update_build_config(self, build_config, field_value, field_name=None):\n        dynamic_fields = [\n            \"column_name\",\n            \"filter_value\",\n            \"filter_operator\",\n            \"ascending\",\n            \"new_column_name\",\n            \"new_column_value\",\n            \"columns_to_select\",\n            \"num_rows\",\n            \"replace_value\",\n            \"replacement_value\",\n        ]\n        for field in dynamic_fields:\n            build_config[field][\"show\"] = False\n\n        if field_name == \"operation\":\n            # Handle SortableListInput format\n            if isinstance(field_value, list):\n                operation_name = field_value[0].get(\"name\", \"\") if field_value else \"\"\n            else:\n                operation_name = field_value or \"\"\n\n            # If no operation selected, all dynamic fields stay hidden (already set to False above)\n            if not operation_name:\n                return build_config\n\n            if operation_name == \"Filter\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"filter_value\"][\"show\"] = True\n                build_config[\"filter_operator\"][\"show\"] = True\n            elif operation_name == \"Sort\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"ascending\"][\"show\"] = True\n            elif operation_name == \"Drop Column\":\n                build_config[\"column_name\"][\"show\"] = True\n            elif operation_name == \"Rename Column\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"new_column_name\"][\"show\"] = True\n            elif operation_name == \"Add Column\":\n                build_config[\"new_column_name\"][\"show\"] = True\n                build_config[\"new_column_value\"][\"show\"] = True\n            elif operation_name == \"Select Columns\":\n                build_config[\"columns_to_select\"][\"show\"] = True\n            elif operation_name in {\"Head\", \"Tail\"}:\n                build_config[\"num_rows\"][\"show\"] = True\n            elif operation_name == \"Replace Value\":\n                build_config[\"column_name\"][\"show\"] = True\n                build_config[\"replace_value\"][\"show\"] = True\n                build_config[\"replacement_value\"][\"show\"] = True\n            elif operation_name == \"Drop Duplicates\":\n                build_config[\"column_name\"][\"show\"] = True\n\n        return build_config\n\n    def perform_operation(self) -> DataFrame:\n        df_copy = self.df.copy()\n\n        # Handle SortableListInput format for operation\n        operation_input = getattr(self, \"operation\", [])\n        if isinstance(operation_input, list) and len(operation_input) > 0:\n            op = operation_input[0].get(\"name\", \"\")\n        else:\n            op = \"\"\n\n        # If no operation selected, return original DataFrame\n        if not op:\n            return df_copy\n\n        if op == \"Filter\":\n            return self.filter_rows_by_value(df_copy)\n        if op == \"Sort\":\n            return self.sort_by_column(df_copy)\n        if op == \"Drop Column\":\n            return self.drop_column(df_copy)\n        if op == \"Rename Column\":\n            return self.rename_column(df_copy)\n        if op == \"Add Column\":\n            return self.add_column(df_copy)\n        if op == \"Select Columns\":\n            return self.select_columns(df_copy)\n        if op == \"Head\":\n            return self.head(df_copy)\n        if op == \"Tail\":\n            return self.tail(df_copy)\n        if op == \"Replace Value\":\n            return self.replace_values(df_copy)\n        if op == \"Drop Duplicates\":\n            return self.drop_duplicates(df_copy)\n        msg = f\"Unsupported operation: {op}\"\n        logger.error(msg)\n        raise ValueError(msg)\n\n    def filter_rows_by_value(self, df: DataFrame) -> DataFrame:\n        column = df[self.column_name]\n        filter_value = self.filter_value\n\n        # Handle regular DropdownInput format (just a string value)\n        operator = getattr(self, \"filter_operator\", \"equals\")  # Default to equals for backward compatibility\n\n        if operator == \"equals\":\n            mask = column == filter_value\n        elif operator == \"not equals\":\n            mask = column != filter_value\n        elif operator == \"contains\":\n            mask = column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"not contains\":\n            mask = ~column.astype(str).str.contains(str(filter_value), na=False)\n        elif operator == \"starts with\":\n            mask = column.astype(str).str.startswith(str(filter_value), na=False)\n        elif operator == \"ends with\":\n            mask = column.astype(str).str.endswith(str(filter_value), na=False)\n        elif operator == \"greater than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column > numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) > str(filter_value)\n        elif operator == \"less than\":\n            try:\n                # Try to convert filter_value to numeric for comparison\n                numeric_value = pd.to_numeric(filter_value)\n                mask = column < numeric_value\n            except (ValueError, TypeError):\n                # If conversion fails, compare as strings\n                mask = column.astype(str) < str(filter_value)\n        else:\n            mask = column == filter_value  # Fallback to equals\n\n        return DataFrame(df[mask])\n\n    def sort_by_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.sort_values(by=self.column_name, ascending=self.ascending))\n\n    def drop_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop(columns=[self.column_name]))\n\n    def rename_column(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.rename(columns={self.column_name: self.new_column_name}))\n\n    def add_column(self, df: DataFrame) -> DataFrame:\n        df[self.new_column_name] = [self.new_column_value] * len(df)\n        return DataFrame(df)\n\n    def select_columns(self, df: DataFrame) -> DataFrame:\n        columns = [col.strip() for col in self.columns_to_select]\n        return DataFrame(df[columns])\n\n    def head(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.head(self.num_rows))\n\n    def tail(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.tail(self.num_rows))\n\n    def replace_values(self, df: DataFrame) -> DataFrame:\n        df[self.column_name] = df[self.column_name].replace(self.replace_value, self.replacement_value)\n        return DataFrame(df)\n\n    def drop_duplicates(self, df: DataFrame) -> DataFrame:\n        return DataFrame(df.drop_duplicates(subset=self.column_name))\n"
+              },
+              "column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Column Name",
+                "dynamic": true,
+                "info": "The column name to use for the operation.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "column_name",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "columns_to_select": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "Columns to Select",
+                "dynamic": true,
+                "info": "",
+                "list": true,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "columns_to_select",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "df": {
+                "_input_type": "DataFrameInput",
+                "advanced": false,
+                "display_name": "DataFrame",
+                "dynamic": false,
+                "info": "The input DataFrame to operate on.",
+                "input_types": [
+                  "DataFrame"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "df",
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "other",
+                "value": ""
+              },
+              "filter_operator": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Filter Operator",
+                "dynamic": true,
+                "external_options": {},
+                "info": "The operator to apply for filtering rows.",
+                "name": "filter_operator",
+                "options": [
+                  "equals",
+                  "not equals",
+                  "contains",
+                  "not contains",
+                  "starts with",
+                  "ends with",
+                  "greater than",
+                  "less than"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "equals"
+              },
+              "filter_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Filter Value",
+                "dynamic": true,
+                "info": "The value to filter rows by.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "filter_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "new_column_name": {
+                "_input_type": "StrInput",
+                "advanced": false,
+                "display_name": "New Column Name",
+                "dynamic": true,
+                "info": "The new column name when renaming or adding a column.",
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "new_column_name",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "new_column_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "New Column Value",
+                "dynamic": true,
+                "info": "The value to populate the new column with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "new_column_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "num_rows": {
+                "_input_type": "IntInput",
+                "advanced": false,
+                "display_name": "Number of Rows",
+                "dynamic": true,
+                "info": "Number of rows to return (for head/tail).",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "num_rows",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 5
+              },
+              "operation": {
+                "_input_type": "SortableListInput",
+                "advanced": false,
+                "display_name": "Operation",
+                "dynamic": false,
+                "info": "Select the DataFrame operation to perform.",
+                "limit": 1,
+                "name": "operation",
+                "options": [
+                  {
+                    "icon": "plus",
+                    "name": "Add Column"
+                  },
+                  {
+                    "icon": "minus",
+                    "name": "Drop Column"
+                  },
+                  {
+                    "icon": "filter",
+                    "name": "Filter"
+                  },
+                  {
+                    "icon": "arrow-up",
+                    "name": "Head"
+                  },
+                  {
+                    "icon": "pencil",
+                    "name": "Rename Column"
+                  },
+                  {
+                    "icon": "replace",
+                    "name": "Replace Value"
+                  },
+                  {
+                    "icon": "columns",
+                    "name": "Select Columns"
+                  },
+                  {
+                    "icon": "arrow-up-down",
+                    "name": "Sort"
+                  },
+                  {
+                    "icon": "arrow-down",
+                    "name": "Tail"
+                  },
+                  {
+                    "icon": "copy-x",
+                    "name": "Drop Duplicates"
+                  }
+                ],
+                "placeholder": "Select Operation",
+                "real_time_refresh": true,
+                "required": false,
+                "search_category": [],
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "sortableList",
+                "value": [
+                  {
+                    "chosen": false,
+                    "icon": "arrow-up",
+                    "name": "Head",
+                    "selected": false
+                  }
+                ]
+              },
+              "replace_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Value to Replace",
+                "dynamic": true,
+                "info": "The value to replace in the column.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replace_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "replacement_value": {
+                "_input_type": "MessageTextInput",
+                "advanced": false,
+                "display_name": "Replacement Value",
+                "dynamic": true,
+                "info": "The value to replace with.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "replacement_value",
+                "placeholder": "",
+                "required": false,
+                "show": false,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "DataFrameOperations"
+        },
+        "dragging": false,
+        "id": "DataFrameOperations-RhKoe",
+        "measured": {
+          "height": 317,
+          "width": 320
+        },
+        "position": {
+          "x": 2773.2060092972047,
+          "y": 2337.54590413581
+        },
+        "selected": false,
+        "type": "genericNode"
+      },
+      {
+        "data": {
+          "id": "EmbeddingModel-eC65s",
+          "node": {
+            "base_classes": [
+              "Embeddings"
+            ],
+            "beta": false,
+            "conditional_paths": [],
+            "custom_fields": {},
+            "description": "Generate embeddings using a specified provider.",
+            "display_name": "Embedding Model",
+            "documentation": "https://docs.langflow.org/components-embedding-models",
+            "edited": false,
+            "field_order": [
+              "provider",
+              "model",
+              "api_key",
+              "api_base",
+              "dimensions",
+              "chunk_size",
+              "request_timeout",
+              "max_retries",
+              "show_progress_bar",
+              "model_kwargs"
+            ],
+            "frozen": false,
+            "icon": "binary",
+            "last_updated": "2025-10-03T20:31:47.177Z",
+            "legacy": false,
+            "metadata": {
+              "code_hash": "8607e963fdef",
+              "dependencies": {
+                "dependencies": [
+                  {
+                    "name": "langchain_openai",
+                    "version": "0.3.23"
+                  },
+                  {
+                    "name": "lfx",
+                    "version": null
+                  }
+                ],
+                "total_dependencies": 2
+              },
+              "module": "lfx.components.models.embedding_model.EmbeddingModelComponent"
+            },
+            "minimized": false,
+            "output_types": [],
+            "outputs": [
+              {
+                "allows_loop": false,
+                "cache": true,
+                "display_name": "Embedding Model",
+                "group_outputs": false,
+                "method": "build_embeddings",
+                "name": "embeddings",
+                "options": null,
+                "required_inputs": null,
+                "selected": "Embeddings",
+                "tool_mode": true,
+                "types": [
+                  "Embeddings"
+                ],
+                "value": "__UNDEFINED__"
+              }
+            ],
+            "pinned": false,
+            "template": {
+              "_type": "Component",
+              "api_base": {
+                "_input_type": "MessageTextInput",
+                "advanced": true,
+                "display_name": "API Base URL",
+                "dynamic": false,
+                "info": "Base URL for the API. Leave empty for default.",
+                "input_types": [
+                  "Message"
+                ],
+                "list": false,
+                "list_add_label": "Add More",
+                "load_from_db": false,
+                "name": "api_base",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": ""
+              },
+              "api_key": {
+                "_input_type": "SecretStrInput",
+                "advanced": false,
+                "display_name": "OpenAI API Key",
+                "dynamic": false,
+                "info": "Model Provider API key",
+                "input_types": [],
+                "load_from_db": true,
+                "name": "api_key",
+                "password": true,
+                "placeholder": "",
+                "real_time_refresh": true,
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "str",
+                "value": "OPENAI_API_KEY"
+              },
+              "chunk_size": {
+                "_input_type": "IntInput",
+                "advanced": true,
+                "display_name": "Chunk Size",
+                "dynamic": false,
+                "info": "",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "chunk_size",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 1000
+              },
+              "code": {
+                "advanced": true,
+                "dynamic": true,
+                "fileTypes": [],
+                "file_path": "",
+                "info": "",
+                "list": false,
+                "load_from_db": false,
+                "multiline": true,
+                "name": "code",
+                "password": false,
+                "placeholder": "",
+                "required": true,
+                "show": true,
+                "title_case": false,
+                "type": "code",
+                "value": "from typing import Any\n\nfrom langchain_openai import OpenAIEmbeddings\n\nfrom lfx.base.embeddings.model import LCEmbeddingsModel\nfrom lfx.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom lfx.field_typing import Embeddings\nfrom lfx.io import (\n    BoolInput,\n    DictInput,\n    DropdownInput,\n    FloatInput,\n    IntInput,\n    MessageTextInput,\n    SecretStrInput,\n)\nfrom lfx.schema.dotdict import dotdict\n\n\nclass EmbeddingModelComponent(LCEmbeddingsModel):\n    display_name = \"Embedding Model\"\n    description = \"Generate embeddings using a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-embedding-models\"\n    icon = \"binary\"\n    name = \"EmbeddingModel\"\n    category = \"models\"\n\n    inputs = [\n        DropdownInput(\n            name=\"provider\",\n            display_name=\"Model Provider\",\n            options=[\"OpenAI\"],\n            value=\"OpenAI\",\n            info=\"Select the embedding model provider\",\n            real_time_refresh=True,\n            options_metadata=[{\"icon\": \"OpenAI\"}],\n        ),\n        DropdownInput(\n            name=\"model\",\n            display_name=\"Model Name\",\n            options=OPENAI_EMBEDDING_MODEL_NAMES,\n            value=OPENAI_EMBEDDING_MODEL_NAMES[0],\n            info=\"Select the embedding model to use\",\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"OpenAI API Key\",\n            info=\"Model Provider API key\",\n            required=True,\n            show=True,\n            real_time_refresh=True,\n        ),\n        MessageTextInput(\n            name=\"api_base\",\n            display_name=\"API Base URL\",\n            info=\"Base URL for the API. Leave empty for default.\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"dimensions\",\n            display_name=\"Dimensions\",\n            info=\"The number of dimensions the resulting output embeddings should have. \"\n            \"Only supported by certain models.\",\n            advanced=True,\n        ),\n        IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n        FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n        IntInput(name=\"max_retries\", display_name=\"Max Retries\", advanced=True, value=3),\n        BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n        DictInput(\n            name=\"model_kwargs\",\n            display_name=\"Model Kwargs\",\n            advanced=True,\n            info=\"Additional keyword arguments to pass to the model.\",\n        ),\n    ]\n\n    def build_embeddings(self) -> Embeddings:\n        provider = self.provider\n        model = self.model\n        api_key = self.api_key\n        api_base = self.api_base\n        dimensions = self.dimensions\n        chunk_size = self.chunk_size\n        request_timeout = self.request_timeout\n        max_retries = self.max_retries\n        show_progress_bar = self.show_progress_bar\n        model_kwargs = self.model_kwargs or {}\n\n        if provider == \"OpenAI\":\n            if not api_key:\n                msg = \"OpenAI API key is required when using OpenAI provider\"\n                raise ValueError(msg)\n            return OpenAIEmbeddings(\n                model=model,\n                dimensions=dimensions or None,\n                base_url=api_base or None,\n                api_key=api_key,\n                chunk_size=chunk_size,\n                max_retries=max_retries,\n                timeout=request_timeout or None,\n                show_progress_bar=show_progress_bar,\n                model_kwargs=model_kwargs,\n            )\n        msg = f\"Unknown provider: {provider}\"\n        raise ValueError(msg)\n\n    def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n        if field_name == \"provider\" and field_value == \"OpenAI\":\n            build_config[\"model\"][\"options\"] = OPENAI_EMBEDDING_MODEL_NAMES\n            build_config[\"model\"][\"value\"] = OPENAI_EMBEDDING_MODEL_NAMES[0]\n            build_config[\"api_key\"][\"display_name\"] = \"OpenAI API Key\"\n            build_config[\"api_base\"][\"display_name\"] = \"OpenAI API Base URL\"\n        return build_config\n"
+              },
+              "dimensions": {
+                "_input_type": "IntInput",
+                "advanced": true,
+                "display_name": "Dimensions",
+                "dynamic": false,
+                "info": "The number of dimensions the resulting output embeddings should have. Only supported by certain models.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "dimensions",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": ""
+              },
+              "max_retries": {
+                "_input_type": "IntInput",
+                "advanced": true,
+                "display_name": "Max Retries",
+                "dynamic": false,
+                "info": "",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "max_retries",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "int",
+                "value": 3
+              },
+              "model": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Model Name",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Select the embedding model to use",
+                "name": "model",
+                "options": [
+                  "text-embedding-3-small",
+                  "text-embedding-3-large",
+                  "text-embedding-ada-002"
+                ],
+                "options_metadata": [],
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "text-embedding-3-small"
+              },
+              "model_kwargs": {
+                "_input_type": "DictInput",
+                "advanced": true,
+                "display_name": "Model Kwargs",
+                "dynamic": false,
+                "info": "Additional keyword arguments to pass to the model.",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "model_kwargs",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_input": true,
+                "type": "dict",
+                "value": {}
+              },
+              "provider": {
+                "_input_type": "DropdownInput",
+                "advanced": false,
+                "combobox": false,
+                "dialog_inputs": {},
+                "display_name": "Model Provider",
+                "dynamic": false,
+                "external_options": {},
+                "info": "Select the embedding model provider",
+                "name": "provider",
+                "options": [
+                  "OpenAI"
+                ],
+                "options_metadata": [
+                  {
+                    "icon": "OpenAI"
+                  }
+                ],
+                "placeholder": "",
+                "real_time_refresh": true,
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "toggle": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "str",
+                "value": "OpenAI"
+              },
+              "request_timeout": {
+                "_input_type": "FloatInput",
+                "advanced": true,
+                "display_name": "Request Timeout",
+                "dynamic": false,
+                "info": "",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "request_timeout",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "float",
+                "value": ""
+              },
+              "show_progress_bar": {
+                "_input_type": "BoolInput",
+                "advanced": true,
+                "display_name": "Show Progress Bar",
+                "dynamic": false,
+                "info": "",
+                "list": false,
+                "list_add_label": "Add More",
+                "name": "show_progress_bar",
+                "placeholder": "",
+                "required": false,
+                "show": true,
+                "title_case": false,
+                "tool_mode": false,
+                "trace_as_metadata": true,
+                "type": "bool",
+                "value": false
+              }
+            },
+            "tool_mode": false
+          },
+          "showNode": true,
+          "type": "EmbeddingModel"
+        },
+        "dragging": false,
+        "id": "EmbeddingModel-eC65s",
+        "measured": {
+          "height": 369,
+          "width": 320
+        },
+        "position": {
+          "x": 2160.1718548185536,
+          "y": 2003.7747198162415
+        },
+        "selected": false,
+        "type": "genericNode"
+      }
+    ],
+    "viewport": {
+      "x": -407.1633937626607,
+      "y": -577.5291936220412,
+      "zoom": 0.5347553210574026
+    }
+  },
+  "description": "This flow is to ingest the URL to open search.",
+  "endpoint_name": null,
+  "mcp_enabled": true,
+  "id": "72c3d17c-2dac-4a73-b48a-6518473d7830",
+  "is_component": false,
+  "last_tested_version": "1.6.0",
+  "name": "OpenSearch URL Ingestion Flow",
+  "tags": [
+    "openai",
+    "astradb",
+    "rag",
+    "q-a"
+  ]
+}
\ No newline at end of file
diff --git a/frontend/components/docling-health-banner.tsx b/frontend/components/docling-health-banner.tsx
new file mode 100644
index 00000000..c65a93cc
--- /dev/null
+++ b/frontend/components/docling-health-banner.tsx
@@ -0,0 +1,134 @@
+"use client";
+
+import { AlertTriangle, ExternalLink, Copy } from "lucide-react";
+import { useDoclingHealthQuery } from "@/src/app/api/queries/useDoclingHealthQuery";
+import { Banner, BannerIcon, BannerTitle, BannerAction } from "@/components/ui/banner";
+import { Button } from "@/components/ui/button";
+import {
+  Dialog,
+  DialogContent,
+  DialogHeader,
+  DialogTitle,
+  DialogDescription,
+  DialogFooter
+} from "@/components/ui/dialog";
+import { cn } from "@/lib/utils";
+import { useState } from "react";
+
+interface DoclingHealthBannerProps {
+  className?: string;
+}
+
+// DoclingSetupDialog component
+interface DoclingSetupDialogProps {
+  open: boolean;
+  onOpenChange: (open: boolean) => void;
+  className?: string;
+}
+
+function DoclingSetupDialog({
+  open,
+  onOpenChange,
+  className
+}: DoclingSetupDialogProps) {
+  const [copied, setCopied] = useState(false);
+
+  const handleCopy = async () => {
+    await navigator.clipboard.writeText("uv run openrag");
+    setCopied(true);
+    setTimeout(() => setCopied(false), 2000);
+  };
+
+  return (
+    <Dialog open={open} onOpenChange={onOpenChange}>
+      <DialogContent className={cn("max-w-lg", className)}>
+        <DialogHeader>
+          <DialogTitle className="flex items-center gap-2 text-base">
+            <AlertTriangle className="h-4 w-4 text-amber-600 dark:text-amber-400" />
+            docling-serve is stopped. Knowledge ingest is unavailable.
+          </DialogTitle>
+          <DialogDescription>
+            Start docling-serve by running:
+          </DialogDescription>
+        </DialogHeader>
+
+        <div className="space-y-4">
+          <div className="flex items-center gap-2">
+            <code className="flex-1 bg-muted px-3 py-2.5 rounded-md text-sm font-mono">
+              uv run openrag
+            </code>
+            <Button
+              variant="ghost"
+              size="icon"
+              onClick={handleCopy}
+              className="shrink-0"
+              title={copied ? "Copied!" : "Copy to clipboard"}
+            >
+              <Copy className="h-4 w-4" />
+            </Button>
+          </div>
+
+          <DialogDescription>
+            Then, select <span className="font-semibold text-foreground">Start Native Services</span> in the TUI. Once docling-serve is running, refresh OpenRAG.
+          </DialogDescription>
+        </div>
+
+        <DialogFooter>
+          <Button
+            variant="default"
+            onClick={() => onOpenChange(false)}
+          >
+            Close
+          </Button>
+        </DialogFooter>
+      </DialogContent>
+    </Dialog>
+  );
+}
+
+export function DoclingHealthBanner({ className }: DoclingHealthBannerProps) {
+  const { data: health, isLoading, isError } = useDoclingHealthQuery();
+  const [showDialog, setShowDialog] = useState(false);
+
+  const isHealthy = health?.status === "healthy" && !isError;
+  const isUnhealthy = health?.status === "unhealthy" || isError;
+
+  // Only show banner when service is unhealthy
+  if (isLoading || isHealthy) {
+    return null;
+  }
+
+  if (isUnhealthy) {
+    return (
+      <>
+        <Banner
+          className={cn(
+            "bg-amber-50 text-amber-900 dark:bg-amber-950 dark:text-amber-200 border-amber-200 dark:border-amber-800",
+            className
+          )}
+        >
+          <BannerIcon
+            icon={AlertTriangle}
+          />
+          <BannerTitle className="font-medium">
+            docling-serve native service is stopped. Knowledge ingest is unavailable.
+          </BannerTitle>
+          <BannerAction
+            onClick={() => setShowDialog(true)}
+            className="bg-foreground text-background hover:bg-primary/90"
+          >
+            Setup Docling Serve
+            <ExternalLink className="h-3 w-3 ml-1" />
+          </BannerAction>
+        </Banner>
+
+        <DoclingSetupDialog
+          open={showDialog}
+          onOpenChange={setShowDialog}
+        />
+      </>
+    );
+  }
+
+  return null;
+}
\ No newline at end of file
diff --git a/frontend/components/duplicate-handling-dialog.tsx b/frontend/components/duplicate-handling-dialog.tsx
new file mode 100644
index 00000000..d5cb2edf
--- /dev/null
+++ b/frontend/components/duplicate-handling-dialog.tsx
@@ -0,0 +1,66 @@
+"use client";
+
+import { RotateCcw } from "lucide-react";
+import type React from "react";
+import { Button } from "./ui/button";
+import {
+	Dialog,
+	DialogContent,
+	DialogDescription,
+	DialogFooter,
+	DialogHeader,
+	DialogTitle,
+} from "./ui/dialog";
+
+interface DuplicateHandlingDialogProps {
+	open: boolean;
+	onOpenChange: (open: boolean) => void;
+	onOverwrite: () => void | Promise<void>;
+	isLoading?: boolean;
+}
+
+export const DuplicateHandlingDialog: React.FC<
+	DuplicateHandlingDialogProps
+> = ({ open, onOpenChange, onOverwrite, isLoading = false }) => {
+	const handleOverwrite = async () => {
+		await onOverwrite();
+		onOpenChange(false);
+	};
+
+	return (
+		<Dialog open={open} onOpenChange={onOpenChange}>
+			<DialogContent className="sm:max-w-[450px]">
+				<DialogHeader>
+					<DialogTitle>Overwrite document</DialogTitle>
+					<DialogDescription className="pt-2 text-muted-foreground">
+						Overwriting will replace the existing document with another version.
+						This can't be undone.
+					</DialogDescription>
+				</DialogHeader>
+
+				<DialogFooter className="flex-row gap-2 justify-end">
+					<Button
+						type="button"
+						variant="ghost"
+						onClick={() => onOpenChange(false)}
+						disabled={isLoading}
+						size="sm"
+					>
+						Cancel
+					</Button>
+					<Button
+						type="button"
+						variant="default"
+						size="sm"
+						onClick={handleOverwrite}
+						disabled={isLoading}
+						className="flex items-center gap-2 !bg-accent-amber-foreground hover:!bg-foreground text-primary-foreground"
+					>
+						<RotateCcw className="h-3.5 w-3.5" />
+						Overwrite
+					</Button>
+				</DialogFooter>
+			</DialogContent>
+		</Dialog>
+	);
+};
diff --git a/frontend/components/knowledge-dropdown.tsx b/frontend/components/knowledge-dropdown.tsx
index ee49fc3a..7fe84259 100644
--- a/frontend/components/knowledge-dropdown.tsx
+++ b/frontend/components/knowledge-dropdown.tsx
@@ -1,625 +1,696 @@
 "use client";
 
+import { useQueryClient } from "@tanstack/react-query";
 import {
-  ChevronDown,
-  Cloud,
-  FolderOpen,
-  Loader2,
-  PlugZap,
-  Plus,
-  Upload,
+	ChevronDown,
+	Cloud,
+	FolderOpen,
+	Loader2,
+	PlugZap,
+	Plus,
+	Upload,
 } from "lucide-react";
 import { useRouter } from "next/navigation";
 import { useEffect, useRef, useState } from "react";
 import { toast } from "sonner";
+import { useGetTasksQuery } from "@/app/api/queries/useGetTasksQuery";
+import { DuplicateHandlingDialog } from "@/components/duplicate-handling-dialog";
 import { Button } from "@/components/ui/button";
 import {
-  Dialog,
-  DialogContent,
-  DialogDescription,
-  DialogHeader,
-  DialogTitle,
+	Dialog,
+	DialogContent,
+	DialogDescription,
+	DialogHeader,
+	DialogTitle,
 } from "@/components/ui/dialog";
 import { Input } from "@/components/ui/input";
 import { Label } from "@/components/ui/label";
 import { useTask } from "@/contexts/task-context";
 import { cn } from "@/lib/utils";
+import type { File as SearchFile } from "@/src/app/api/queries/useGetSearchQuery";
 
 interface KnowledgeDropdownProps {
-  active?: boolean;
-  variant?: "navigation" | "button";
+	active?: boolean;
+	variant?: "navigation" | "button";
 }
 
 export function KnowledgeDropdown({
-  active,
-  variant = "navigation",
+	active,
+	variant = "navigation",
 }: KnowledgeDropdownProps) {
-  const { addTask } = useTask();
-  const router = useRouter();
-  const [isOpen, setIsOpen] = useState(false);
-  const [showFolderDialog, setShowFolderDialog] = useState(false);
-  const [showS3Dialog, setShowS3Dialog] = useState(false);
-  const [awsEnabled, setAwsEnabled] = useState(false);
-  const [folderPath, setFolderPath] = useState("/app/documents/");
-  const [bucketUrl, setBucketUrl] = useState("s3://");
-  const [folderLoading, setFolderLoading] = useState(false);
-  const [s3Loading, setS3Loading] = useState(false);
-  const [fileUploading, setFileUploading] = useState(false);
-  const [isNavigatingToCloud, setIsNavigatingToCloud] = useState(false);
-  const [cloudConnectors, setCloudConnectors] = useState<{
-    [key: string]: {
-      name: string;
-      available: boolean;
-      connected: boolean;
-      hasToken: boolean;
-    };
-  }>({});
-  const fileInputRef = useRef<HTMLInputElement>(null);
-  const dropdownRef = useRef<HTMLDivElement>(null);
+	const { addTask } = useTask();
+	const { refetch: refetchTasks } = useGetTasksQuery();
+	const queryClient = useQueryClient();
+	const router = useRouter();
+	const [isOpen, setIsOpen] = useState(false);
+	const [showFolderDialog, setShowFolderDialog] = useState(false);
+	const [showS3Dialog, setShowS3Dialog] = useState(false);
+	const [showDuplicateDialog, setShowDuplicateDialog] = useState(false);
+	const [awsEnabled, setAwsEnabled] = useState(false);
+	const [folderPath, setFolderPath] = useState("/app/documents/");
+	const [bucketUrl, setBucketUrl] = useState("s3://");
+	const [folderLoading, setFolderLoading] = useState(false);
+	const [s3Loading, setS3Loading] = useState(false);
+	const [fileUploading, setFileUploading] = useState(false);
+	const [isNavigatingToCloud, setIsNavigatingToCloud] = useState(false);
+	const [pendingFile, setPendingFile] = useState<File | null>(null);
+	const [duplicateFilename, setDuplicateFilename] = useState<string>("");
+	const [cloudConnectors, setCloudConnectors] = useState<{
+		[key: string]: {
+			name: string;
+			available: boolean;
+			connected: boolean;
+			hasToken: boolean;
+		};
+	}>({});
+	const fileInputRef = useRef<HTMLInputElement>(null);
+	const dropdownRef = useRef<HTMLDivElement>(null);
 
-  // Check AWS availability and cloud connectors on mount
-  useEffect(() => {
-    const checkAvailability = async () => {
-      try {
-        // Check AWS
-        const awsRes = await fetch("/api/upload_options");
-        if (awsRes.ok) {
-          const awsData = await awsRes.json();
-          setAwsEnabled(Boolean(awsData.aws));
-        }
+	// Check AWS availability and cloud connectors on mount
+	useEffect(() => {
+		const checkAvailability = async () => {
+			try {
+				// Check AWS
+				const awsRes = await fetch("/api/upload_options");
+				if (awsRes.ok) {
+					const awsData = await awsRes.json();
+					setAwsEnabled(Boolean(awsData.aws));
+				}
 
-        // Check cloud connectors
-        const connectorsRes = await fetch("/api/connectors");
-        if (connectorsRes.ok) {
-          const connectorsResult = await connectorsRes.json();
-          const cloudConnectorTypes = [
-            "google_drive",
-            "onedrive",
-            "sharepoint",
-          ];
-          const connectorInfo: {
-            [key: string]: {
-              name: string;
-              available: boolean;
-              connected: boolean;
-              hasToken: boolean;
-            };
-          } = {};
+				// Check cloud connectors
+				const connectorsRes = await fetch("/api/connectors");
+				if (connectorsRes.ok) {
+					const connectorsResult = await connectorsRes.json();
+					const cloudConnectorTypes = [
+						"google_drive",
+						"onedrive",
+						"sharepoint",
+					];
+					const connectorInfo: {
+						[key: string]: {
+							name: string;
+							available: boolean;
+							connected: boolean;
+							hasToken: boolean;
+						};
+					} = {};
 
-          for (const type of cloudConnectorTypes) {
-            if (connectorsResult.connectors[type]) {
-              connectorInfo[type] = {
-                name: connectorsResult.connectors[type].name,
-                available: connectorsResult.connectors[type].available,
-                connected: false,
-                hasToken: false,
-              };
+					for (const type of cloudConnectorTypes) {
+						if (connectorsResult.connectors[type]) {
+							connectorInfo[type] = {
+								name: connectorsResult.connectors[type].name,
+								available: connectorsResult.connectors[type].available,
+								connected: false,
+								hasToken: false,
+							};
 
-              // Check connection status
-              try {
-                const statusRes = await fetch(`/api/connectors/${type}/status`);
-                if (statusRes.ok) {
-                  const statusData = await statusRes.json();
-                  const connections = statusData.connections || [];
-                  const activeConnection = connections.find(
-                    (conn: { is_active: boolean; connection_id: string }) =>
-                      conn.is_active
-                  );
-                  const isConnected = activeConnection !== undefined;
+							// Check connection status
+							try {
+								const statusRes = await fetch(`/api/connectors/${type}/status`);
+								if (statusRes.ok) {
+									const statusData = await statusRes.json();
+									const connections = statusData.connections || [];
+									const activeConnection = connections.find(
+										(conn: { is_active: boolean; connection_id: string }) =>
+											conn.is_active,
+									);
+									const isConnected = activeConnection !== undefined;
 
-                  if (isConnected && activeConnection) {
-                    connectorInfo[type].connected = true;
+									if (isConnected && activeConnection) {
+										connectorInfo[type].connected = true;
 
-                    // Check token availability
-                    try {
-                      const tokenRes = await fetch(
-                        `/api/connectors/${type}/token?connection_id=${activeConnection.connection_id}`
-                      );
-                      if (tokenRes.ok) {
-                        const tokenData = await tokenRes.json();
-                        if (tokenData.access_token) {
-                          connectorInfo[type].hasToken = true;
-                        }
-                      }
-                    } catch {
-                      // Token check failed
-                    }
-                  }
-                }
-              } catch {
-                // Status check failed
-              }
-            }
-          }
+										// Check token availability
+										try {
+											const tokenRes = await fetch(
+												`/api/connectors/${type}/token?connection_id=${activeConnection.connection_id}`,
+											);
+											if (tokenRes.ok) {
+												const tokenData = await tokenRes.json();
+												if (tokenData.access_token) {
+													connectorInfo[type].hasToken = true;
+												}
+											}
+										} catch {
+											// Token check failed
+										}
+									}
+								}
+							} catch {
+								// Status check failed
+							}
+						}
+					}
 
-          setCloudConnectors(connectorInfo);
-        }
-      } catch (err) {
-        console.error("Failed to check availability", err);
-      }
-    };
-    checkAvailability();
-  }, []);
+					setCloudConnectors(connectorInfo);
+				}
+			} catch (err) {
+				console.error("Failed to check availability", err);
+			}
+		};
+		checkAvailability();
+	}, []);
 
-  // Handle click outside to close dropdown
-  useEffect(() => {
-    const handleClickOutside = (event: MouseEvent) => {
-      if (
-        dropdownRef.current &&
-        !dropdownRef.current.contains(event.target as Node)
-      ) {
-        setIsOpen(false);
-      }
-    };
+	// Handle click outside to close dropdown
+	useEffect(() => {
+		const handleClickOutside = (event: MouseEvent) => {
+			if (
+				dropdownRef.current &&
+				!dropdownRef.current.contains(event.target as Node)
+			) {
+				setIsOpen(false);
+			}
+		};
 
-    if (isOpen) {
-      document.addEventListener("mousedown", handleClickOutside);
-      return () =>
-        document.removeEventListener("mousedown", handleClickOutside);
-    }
-  }, [isOpen]);
+		if (isOpen) {
+			document.addEventListener("mousedown", handleClickOutside);
+			return () =>
+				document.removeEventListener("mousedown", handleClickOutside);
+		}
+	}, [isOpen]);
 
-  const handleFileUpload = () => {
-    fileInputRef.current?.click();
-  };
+	const handleFileUpload = () => {
+		fileInputRef.current?.click();
+	};
 
-  const handleFileChange = async (e: React.ChangeEvent<HTMLInputElement>) => {
-    const files = e.target.files;
-    if (files && files.length > 0) {
-      // Close dropdown and disable button immediately after file selection
-      setIsOpen(false);
-      setFileUploading(true);
+	const handleFileChange = async (e: React.ChangeEvent<HTMLInputElement>) => {
+		const files = e.target.files;
+		if (files && files.length > 0) {
+			const file = files[0];
 
-      // Trigger the same file upload event as the chat page
-      window.dispatchEvent(
-        new CustomEvent("fileUploadStart", {
-          detail: { filename: files[0].name },
-        })
-      );
+			// Close dropdown immediately after file selection
+			setIsOpen(false);
 
-      try {
-        const formData = new FormData();
-        formData.append("file", files[0]);
+			try {
+				// Check if filename already exists (using ORIGINAL filename)
+				console.log("[Duplicate Check] Checking file:", file.name);
+				const checkResponse = await fetch(
+					`/api/documents/check-filename?filename=${encodeURIComponent(file.name)}`,
+				);
 
-        // Use router upload and ingest endpoint (automatically routes based on configuration)
-        const uploadIngestRes = await fetch("/api/router/upload_ingest", {
-          method: "POST",
-          body: formData,
-        });
+				console.log("[Duplicate Check] Response status:", checkResponse.status);
 
-        const uploadIngestJson = await uploadIngestRes.json();
+				if (!checkResponse.ok) {
+					const errorText = await checkResponse.text();
+					console.error("[Duplicate Check] Error response:", errorText);
+					throw new Error(
+						`Failed to check duplicates: ${checkResponse.statusText}`,
+					);
+				}
 
-        if (!uploadIngestRes.ok) {
-          throw new Error(
-            uploadIngestJson?.error || "Upload and ingest failed"
-          );
-        }
+				const checkData = await checkResponse.json();
+				console.log("[Duplicate Check] Result:", checkData);
 
-        // Extract results from the response - handle both unified and simple formats
-        const fileId = uploadIngestJson?.upload?.id || uploadIngestJson?.id;
-        const filePath =
-          uploadIngestJson?.upload?.path ||
-          uploadIngestJson?.path ||
-          "uploaded";
-        const runJson = uploadIngestJson?.ingestion;
-        const deleteResult = uploadIngestJson?.deletion;
+				if (checkData.exists) {
+					// Show duplicate handling dialog
+					console.log("[Duplicate Check] Duplicate detected, showing dialog");
+					setPendingFile(file);
+					setDuplicateFilename(file.name);
+					setShowDuplicateDialog(true);
+					// Reset file input
+					if (fileInputRef.current) {
+						fileInputRef.current.value = "";
+					}
+					return;
+				}
 
-        if (!fileId) {
-          throw new Error("Upload successful but no file id returned");
-        }
+				// No duplicate, proceed with upload
+				console.log("[Duplicate Check] No duplicate, proceeding with upload");
+				await uploadFile(file, false);
+			} catch (error) {
+				console.error("[Duplicate Check] Exception:", error);
+				toast.error("Failed to check for duplicates", {
+					description: error instanceof Error ? error.message : "Unknown error",
+				});
+			}
+		}
 
-        // Check if ingestion actually succeeded
-        if (
-          runJson &&
-          runJson.status !== "COMPLETED" &&
-          runJson.status !== "SUCCESS"
-        ) {
-          const errorMsg = runJson.error || "Ingestion pipeline failed";
-          throw new Error(
-            `Ingestion failed: ${errorMsg}. Try setting DISABLE_INGEST_WITH_LANGFLOW=true if you're experiencing Langflow component issues.`
-          );
-        }
+		// Reset file input
+		if (fileInputRef.current) {
+			fileInputRef.current.value = "";
+		}
+	};
 
-        // Log deletion status if provided
-        if (deleteResult) {
-          if (deleteResult.status === "deleted") {
-            console.log(
-              "File successfully cleaned up from Langflow:",
-              deleteResult.file_id
-            );
-          } else if (deleteResult.status === "delete_failed") {
-            console.warn(
-              "Failed to cleanup file from Langflow:",
-              deleteResult.error
-            );
-          }
-        }
+	const uploadFile = async (file: File, replace: boolean) => {
+		setFileUploading(true);
 
-        // Notify UI
-        window.dispatchEvent(
-          new CustomEvent("fileUploaded", {
-            detail: {
-              file: files[0],
-              result: {
-                file_id: fileId,
-                file_path: filePath,
-                run: runJson,
-                deletion: deleteResult,
-                unified: true,
-              },
-            },
-          })
-        );
+		// Trigger the same file upload event as the chat page
+		window.dispatchEvent(
+			new CustomEvent("fileUploadStart", {
+				detail: { filename: file.name },
+			}),
+		);
 
-        // Trigger search refresh after successful ingestion
-        window.dispatchEvent(new CustomEvent("knowledgeUpdated"));
-      } catch (error) {
-        window.dispatchEvent(
-          new CustomEvent("fileUploadError", {
-            detail: {
-              filename: files[0].name,
-              error: error instanceof Error ? error.message : "Upload failed",
-            },
-          })
-        );
-      } finally {
-        window.dispatchEvent(new CustomEvent("fileUploadComplete"));
-        setFileUploading(false);
-        // Don't call refetchSearch() here - the knowledgeUpdated event will handle it
-      }
-    }
+		try {
+			const formData = new FormData();
+			formData.append("file", file);
+			formData.append("replace_duplicates", replace.toString());
 
-    // Reset file input
-    if (fileInputRef.current) {
-      fileInputRef.current.value = "";
-    }
-  };
+			// Use router upload and ingest endpoint (automatically routes based on configuration)
+			const uploadIngestRes = await fetch("/api/router/upload_ingest", {
+				method: "POST",
+				body: formData,
+			});
 
-  const handleFolderUpload = async () => {
-    if (!folderPath.trim()) return;
+			const uploadIngestJson = await uploadIngestRes.json();
 
-    setFolderLoading(true);
-    setShowFolderDialog(false);
+			if (!uploadIngestRes.ok) {
+				throw new Error(uploadIngestJson?.error || "Upload and ingest failed");
+			}
 
-    try {
-      const response = await fetch("/api/upload_path", {
-        method: "POST",
-        headers: {
-          "Content-Type": "application/json",
-        },
-        body: JSON.stringify({ path: folderPath }),
-      });
+			// Extract results from the response - handle both unified and simple formats
+			const fileId =
+				uploadIngestJson?.upload?.id ||
+				uploadIngestJson?.id ||
+				uploadIngestJson?.task_id;
+			const filePath =
+				uploadIngestJson?.upload?.path || uploadIngestJson?.path || "uploaded";
+			const runJson = uploadIngestJson?.ingestion;
+			const deleteResult = uploadIngestJson?.deletion;
+			console.log("c", uploadIngestJson);
+			if (!fileId) {
+				throw new Error("Upload successful but no file id returned");
+			}
+			// Check if ingestion actually succeeded
+			if (
+				runJson &&
+				runJson.status !== "COMPLETED" &&
+				runJson.status !== "SUCCESS"
+			) {
+				const errorMsg = runJson.error || "Ingestion pipeline failed";
+				throw new Error(
+					`Ingestion failed: ${errorMsg}. Try setting DISABLE_INGEST_WITH_LANGFLOW=true if you're experiencing Langflow component issues.`,
+				);
+			}
+			// Log deletion status if provided
+			if (deleteResult) {
+				if (deleteResult.status === "deleted") {
+					console.log(
+						"File successfully cleaned up from Langflow:",
+						deleteResult.file_id,
+					);
+				} else if (deleteResult.status === "delete_failed") {
+					console.warn(
+						"Failed to cleanup file from Langflow:",
+						deleteResult.error,
+					);
+				}
+			}
+			// Notify UI
+			window.dispatchEvent(
+				new CustomEvent("fileUploaded", {
+					detail: {
+						file: file,
+						result: {
+							file_id: fileId,
+							file_path: filePath,
+							run: runJson,
+							deletion: deleteResult,
+							unified: true,
+						},
+					},
+				}),
+			);
 
-      const result = await response.json();
+			refetchTasks();
+		} catch (error) {
+			window.dispatchEvent(
+				new CustomEvent("fileUploadError", {
+					detail: {
+						filename: file.name,
+						error: error instanceof Error ? error.message : "Upload failed",
+					},
+				}),
+			);
+		} finally {
+			window.dispatchEvent(new CustomEvent("fileUploadComplete"));
+			setFileUploading(false);
+		}
+	};
 
-      if (response.status === 201) {
-        const taskId = result.task_id || result.id;
+	const handleOverwriteFile = async () => {
+		if (pendingFile) {
+			// Remove the old file from all search query caches before overwriting
+			queryClient.setQueriesData({ queryKey: ["search"] }, (oldData: []) => {
+				if (!oldData) return oldData;
+				// Filter out the file that's being overwritten
+				return oldData.filter(
+					(file: SearchFile) => file.filename !== pendingFile.name,
+				);
+			});
 
-        if (!taskId) {
-          throw new Error("No task ID received from server");
-        }
+			await uploadFile(pendingFile, true);
+			setPendingFile(null);
+			setDuplicateFilename("");
+		}
+	};
 
-        addTask(taskId);
-        setFolderPath("");
-        // Trigger search refresh after successful folder processing starts
-        console.log(
-          "Folder upload successful, dispatching knowledgeUpdated event"
-        );
-        window.dispatchEvent(new CustomEvent("knowledgeUpdated"));
-      } else if (response.ok) {
-        setFolderPath("");
-        console.log(
-          "Folder upload successful (direct), dispatching knowledgeUpdated event"
-        );
-        window.dispatchEvent(new CustomEvent("knowledgeUpdated"));
-      } else {
-        console.error("Folder upload failed:", result.error);
-        if (response.status === 400) {
-          toast.error("Upload failed", {
-            description: result.error || "Bad request",
-          });
-        }
-      }
-    } catch (error) {
-      console.error("Folder upload error:", error);
-    } finally {
-      setFolderLoading(false);
-      // Don't call refetchSearch() here - the knowledgeUpdated event will handle it
-    }
-  };
+	const handleFolderUpload = async () => {
+		if (!folderPath.trim()) return;
 
-  const handleS3Upload = async () => {
-    if (!bucketUrl.trim()) return;
+		setFolderLoading(true);
+		setShowFolderDialog(false);
 
-    setS3Loading(true);
-    setShowS3Dialog(false);
+		try {
+			const response = await fetch("/api/upload_path", {
+				method: "POST",
+				headers: {
+					"Content-Type": "application/json",
+				},
+				body: JSON.stringify({ path: folderPath }),
+			});
 
-    try {
-      const response = await fetch("/api/upload_bucket", {
-        method: "POST",
-        headers: {
-          "Content-Type": "application/json",
-        },
-        body: JSON.stringify({ s3_url: bucketUrl }),
-      });
+			const result = await response.json();
 
-      const result = await response.json();
+			if (response.status === 201) {
+				const taskId = result.task_id || result.id;
 
-      if (response.status === 201) {
-        const taskId = result.task_id || result.id;
+				if (!taskId) {
+					throw new Error("No task ID received from server");
+				}
 
-        if (!taskId) {
-          throw new Error("No task ID received from server");
-        }
+				addTask(taskId);
+				setFolderPath("");
+				// Refetch tasks to show the new task
+				refetchTasks();
+			} else if (response.ok) {
+				setFolderPath("");
+				// Refetch tasks even for direct uploads in case tasks were created
+				refetchTasks();
+			} else {
+				console.error("Folder upload failed:", result.error);
+				if (response.status === 400) {
+					toast.error("Upload failed", {
+						description: result.error || "Bad request",
+					});
+				}
+			}
+		} catch (error) {
+			console.error("Folder upload error:", error);
+		} finally {
+			setFolderLoading(false);
+		}
+	};
 
-        addTask(taskId);
-        setBucketUrl("s3://");
-        // Trigger search refresh after successful S3 processing starts
-        console.log("S3 upload successful, dispatching knowledgeUpdated event");
-        window.dispatchEvent(new CustomEvent("knowledgeUpdated"));
-      } else {
-        console.error("S3 upload failed:", result.error);
-        if (response.status === 400) {
-          toast.error("Upload failed", {
-            description: result.error || "Bad request",
-          });
-        }
-      }
-    } catch (error) {
-      console.error("S3 upload error:", error);
-    } finally {
-      setS3Loading(false);
-      // Don't call refetchSearch() here - the knowledgeUpdated event will handle it
-    }
-  };
+	const handleS3Upload = async () => {
+		if (!bucketUrl.trim()) return;
 
-  const cloudConnectorItems = Object.entries(cloudConnectors)
-    .filter(([, info]) => info.available)
-    .map(([type, info]) => ({
-      label: info.name,
-      icon: PlugZap,
-      onClick: async () => {
-        setIsOpen(false);
-        if (info.connected && info.hasToken) {
-          setIsNavigatingToCloud(true);
-          try {
-            router.push(`/upload/${type}`);
-            // Keep loading state for a short time to show feedback
-            setTimeout(() => setIsNavigatingToCloud(false), 1000);
-          } catch {
-            setIsNavigatingToCloud(false);
-          }
-        } else {
-          router.push("/settings");
-        }
-      },
-      disabled: !info.connected || !info.hasToken,
-      tooltip: !info.connected
-        ? `Connect ${info.name} in Settings first`
-        : !info.hasToken
-        ? `Reconnect ${info.name} - access token required`
-        : undefined,
-    }));
+		setS3Loading(true);
+		setShowS3Dialog(false);
 
-  const menuItems = [
-    {
-      label: "Add File",
-      icon: Upload,
-      onClick: handleFileUpload,
-    },
-    {
-      label: "Process Folder",
-      icon: FolderOpen,
-      onClick: () => {
-        setIsOpen(false);
-        setShowFolderDialog(true);
-      },
-    },
-    ...(awsEnabled
-      ? [
-          {
-            label: "Process S3 Bucket",
-            icon: Cloud,
-            onClick: () => {
-              setIsOpen(false);
-              setShowS3Dialog(true);
-            },
-          },
-        ]
-      : []),
-    ...cloudConnectorItems,
-  ];
+		try {
+			const response = await fetch("/api/upload_bucket", {
+				method: "POST",
+				headers: {
+					"Content-Type": "application/json",
+				},
+				body: JSON.stringify({ s3_url: bucketUrl }),
+			});
 
-  // Comprehensive loading state
-  const isLoading =
-    fileUploading || folderLoading || s3Loading || isNavigatingToCloud;
+			const result = await response.json();
 
-  return (
-    <>
-      <div ref={dropdownRef} className="relative">
-        <button
-          onClick={() => !isLoading && setIsOpen(!isOpen)}
-          disabled={isLoading}
-          className={cn(
-            variant === "button"
-              ? "rounded-lg h-12 px-4 flex items-center gap-2 bg-primary text-primary-foreground hover:bg-primary/90 transition-colors disabled:opacity-50 disabled:cursor-not-allowed"
-              : "text-sm group flex p-3 w-full justify-start font-medium cursor-pointer hover:bg-accent hover:text-accent-foreground rounded-lg transition-all disabled:opacity-50 disabled:cursor-not-allowed",
-            variant === "navigation" && active
-              ? "bg-accent text-accent-foreground shadow-sm"
-              : variant === "navigation"
-              ? "text-foreground hover:text-accent-foreground"
-              : ""
-          )}
-        >
-          {variant === "button" ? (
-            <>
-              {isLoading ? (
-                <Loader2 className="h-4 w-4 animate-spin" />
-              ) : (
-                <Plus className="h-4 w-4" />
-              )}
-              <span>
-                {isLoading
-                  ? fileUploading
-                    ? "Uploading..."
-                    : folderLoading
-                    ? "Processing Folder..."
-                    : s3Loading
-                    ? "Processing S3..."
-                    : isNavigatingToCloud
-                    ? "Loading..."
-                    : "Processing..."
-                  : "Add Knowledge"}
-              </span>
-              {!isLoading && (
-                <ChevronDown
-                  className={cn(
-                    "h-4 w-4 transition-transform",
-                    isOpen && "rotate-180"
-                  )}
-                />
-              )}
-            </>
-          ) : (
-            <>
-              <div className="flex items-center flex-1">
-                {isLoading ? (
-                  <Loader2 className="h-4 w-4 mr-3 shrink-0 animate-spin" />
-                ) : (
-                  <Upload
-                    className={cn(
-                      "h-4 w-4 mr-3 shrink-0",
-                      active
-                        ? "text-accent-foreground"
-                        : "text-muted-foreground group-hover:text-foreground"
-                    )}
-                  />
-                )}
-                Knowledge
-              </div>
-              {!isLoading && (
-                <ChevronDown
-                  className={cn(
-                    "h-4 w-4 transition-transform",
-                    isOpen && "rotate-180"
-                  )}
-                />
-              )}
-            </>
-          )}
-        </button>
+			if (response.status === 201) {
+				const taskId = result.task_id || result.id;
 
-        {isOpen && !isLoading && (
-          <div className="absolute top-full left-0 right-0 mt-1 bg-popover border border-border rounded-md shadow-md z-50">
-            <div className="py-1">
-              {menuItems.map((item, index) => (
-                <button
-                  key={index}
-                  onClick={item.onClick}
-                  disabled={"disabled" in item ? item.disabled : false}
-                  title={"tooltip" in item ? item.tooltip : undefined}
-                  className={cn(
-                    "w-full px-3 py-2 text-left text-sm hover:bg-accent hover:text-accent-foreground",
-                    "disabled" in item &&
-                      item.disabled &&
-                      "opacity-50 cursor-not-allowed hover:bg-transparent hover:text-current"
-                  )}
-                >
-                  {item.label}
-                </button>
-              ))}
-            </div>
-          </div>
-        )}
+				if (!taskId) {
+					throw new Error("No task ID received from server");
+				}
 
-        <input
-          ref={fileInputRef}
-          type="file"
-          onChange={handleFileChange}
-          className="hidden"
-          accept=".pdf,.doc,.docx,.txt,.md,.rtf,.odt"
-        />
-      </div>
+				addTask(taskId);
+				setBucketUrl("s3://");
+				// Refetch tasks to show the new task
+				refetchTasks();
+			} else {
+				console.error("S3 upload failed:", result.error);
+				if (response.status === 400) {
+					toast.error("Upload failed", {
+						description: result.error || "Bad request",
+					});
+				}
+			}
+		} catch (error) {
+			console.error("S3 upload error:", error);
+		} finally {
+			setS3Loading(false);
+		}
+	};
 
-      {/* Process Folder Dialog */}
-      <Dialog open={showFolderDialog} onOpenChange={setShowFolderDialog}>
-        <DialogContent>
-          <DialogHeader>
-            <DialogTitle className="flex items-center gap-2">
-              <FolderOpen className="h-5 w-5" />
-              Process Folder
-            </DialogTitle>
-            <DialogDescription>
-              Process all documents in a folder path
-            </DialogDescription>
-          </DialogHeader>
-          <div className="space-y-4">
-            <div className="space-y-2">
-              <Label htmlFor="folder-path">Folder Path</Label>
-              <Input
-                id="folder-path"
-                type="text"
-                placeholder="/path/to/documents"
-                value={folderPath}
-                onChange={e => setFolderPath(e.target.value)}
-              />
-            </div>
-            <div className="flex justify-end gap-2">
-              <Button
-                variant="outline"
-                onClick={() => setShowFolderDialog(false)}
-              >
-                Cancel
-              </Button>
-              <Button
-                onClick={handleFolderUpload}
-                disabled={!folderPath.trim() || folderLoading}
-              >
-                {folderLoading ? "Processing..." : "Process Folder"}
-              </Button>
-            </div>
-          </div>
-        </DialogContent>
-      </Dialog>
+	const cloudConnectorItems = Object.entries(cloudConnectors)
+		.filter(([, info]) => info.available)
+		.map(([type, info]) => ({
+			label: info.name,
+			icon: PlugZap,
+			onClick: async () => {
+				setIsOpen(false);
+				if (info.connected && info.hasToken) {
+					setIsNavigatingToCloud(true);
+					try {
+						router.push(`/upload/${type}`);
+						// Keep loading state for a short time to show feedback
+						setTimeout(() => setIsNavigatingToCloud(false), 1000);
+					} catch {
+						setIsNavigatingToCloud(false);
+					}
+				} else {
+					router.push("/settings");
+				}
+			},
+			disabled: !info.connected || !info.hasToken,
+			tooltip: !info.connected
+				? `Connect ${info.name} in Settings first`
+				: !info.hasToken
+					? `Reconnect ${info.name} - access token required`
+					: undefined,
+		}));
 
-      {/* Process S3 Bucket Dialog */}
-      <Dialog open={showS3Dialog} onOpenChange={setShowS3Dialog}>
-        <DialogContent>
-          <DialogHeader>
-            <DialogTitle className="flex items-center gap-2">
-              <Cloud className="h-5 w-5" />
-              Process S3 Bucket
-            </DialogTitle>
-            <DialogDescription>
-              Process all documents from an S3 bucket. AWS credentials must be
-              configured.
-            </DialogDescription>
-          </DialogHeader>
-          <div className="space-y-4">
-            <div className="space-y-2">
-              <Label htmlFor="bucket-url">S3 URL</Label>
-              <Input
-                id="bucket-url"
-                type="text"
-                placeholder="s3://bucket/path"
-                value={bucketUrl}
-                onChange={e => setBucketUrl(e.target.value)}
-              />
-            </div>
-            <div className="flex justify-end gap-2">
-              <Button variant="outline" onClick={() => setShowS3Dialog(false)}>
-                Cancel
-              </Button>
-              <Button
-                onClick={handleS3Upload}
-                disabled={!bucketUrl.trim() || s3Loading}
-              >
-                {s3Loading ? "Processing..." : "Process Bucket"}
-              </Button>
-            </div>
-          </div>
-        </DialogContent>
-      </Dialog>
-    </>
-  );
+	const menuItems = [
+		{
+			label: "Add File",
+			icon: Upload,
+			onClick: handleFileUpload,
+		},
+		{
+			label: "Process Folder",
+			icon: FolderOpen,
+			onClick: () => {
+				setIsOpen(false);
+				setShowFolderDialog(true);
+			},
+		},
+		...(awsEnabled
+			? [
+					{
+						label: "Process S3 Bucket",
+						icon: Cloud,
+						onClick: () => {
+							setIsOpen(false);
+							setShowS3Dialog(true);
+						},
+					},
+				]
+			: []),
+		...cloudConnectorItems,
+	];
+
+	// Comprehensive loading state
+	const isLoading =
+		fileUploading || folderLoading || s3Loading || isNavigatingToCloud;
+
+	return (
+		<>
+			<div ref={dropdownRef} className="relative">
+				<button
+					type="button"
+					onClick={() => !isLoading && setIsOpen(!isOpen)}
+					disabled={isLoading}
+					className={cn(
+						variant === "button"
+							? "rounded-lg h-12 px-4 flex items-center gap-2 bg-primary text-primary-foreground hover:bg-primary/90 transition-colors disabled:opacity-50 disabled:cursor-not-allowed"
+							: "text-sm group flex p-3 w-full justify-start font-medium cursor-pointer hover:bg-accent hover:text-accent-foreground rounded-lg transition-all disabled:opacity-50 disabled:cursor-not-allowed",
+						variant === "navigation" && active
+							? "bg-accent text-accent-foreground shadow-sm"
+							: variant === "navigation"
+								? "text-foreground hover:text-accent-foreground"
+								: "",
+					)}
+				>
+					{variant === "button" ? (
+						<>
+							{isLoading ? (
+								<Loader2 className="h-4 w-4 animate-spin" />
+							) : (
+								<Plus className="h-4 w-4" />
+							)}
+							<span>
+								{isLoading
+									? fileUploading
+										? "Uploading..."
+										: folderLoading
+											? "Processing Folder..."
+											: s3Loading
+												? "Processing S3..."
+												: isNavigatingToCloud
+													? "Loading..."
+													: "Processing..."
+									: "Add Knowledge"}
+							</span>
+							{!isLoading && (
+								<ChevronDown
+									className={cn(
+										"h-4 w-4 transition-transform",
+										isOpen && "rotate-180",
+									)}
+								/>
+							)}
+						</>
+					) : (
+						<>
+							<div className="flex items-center flex-1">
+								{isLoading ? (
+									<Loader2 className="h-4 w-4 mr-3 shrink-0 animate-spin" />
+								) : (
+									<Upload
+										className={cn(
+											"h-4 w-4 mr-3 shrink-0",
+											active
+												? "text-accent-foreground"
+												: "text-muted-foreground group-hover:text-foreground",
+										)}
+									/>
+								)}
+								Knowledge
+							</div>
+							{!isLoading && (
+								<ChevronDown
+									className={cn(
+										"h-4 w-4 transition-transform",
+										isOpen && "rotate-180",
+									)}
+								/>
+							)}
+						</>
+					)}
+				</button>
+
+				{isOpen && !isLoading && (
+					<div className="absolute top-full left-0 right-0 mt-1 bg-popover border border-border rounded-md shadow-md z-50">
+						<div className="py-1">
+							{menuItems.map((item, index) => (
+								<button
+									key={`${item.label}-${index}`}
+									type="button"
+									onClick={item.onClick}
+									disabled={"disabled" in item ? item.disabled : false}
+									title={"tooltip" in item ? item.tooltip : undefined}
+									className={cn(
+										"w-full px-3 py-2 text-left text-sm hover:bg-accent hover:text-accent-foreground",
+										"disabled" in item &&
+											item.disabled &&
+											"opacity-50 cursor-not-allowed hover:bg-transparent hover:text-current",
+									)}
+								>
+									{item.label}
+								</button>
+							))}
+						</div>
+					</div>
+				)}
+
+				<input
+					ref={fileInputRef}
+					type="file"
+					onChange={handleFileChange}
+					className="hidden"
+					accept=".pdf,.doc,.docx,.txt,.md,.rtf,.odt"
+				/>
+			</div>
+
+			{/* Process Folder Dialog */}
+			<Dialog open={showFolderDialog} onOpenChange={setShowFolderDialog}>
+				<DialogContent>
+					<DialogHeader>
+						<DialogTitle className="flex items-center gap-2">
+							<FolderOpen className="h-5 w-5" />
+							Process Folder
+						</DialogTitle>
+						<DialogDescription>
+							Process all documents in a folder path
+						</DialogDescription>
+					</DialogHeader>
+					<div className="space-y-4">
+						<div className="space-y-2">
+							<Label htmlFor="folder-path">Folder Path</Label>
+							<Input
+								id="folder-path"
+								type="text"
+								placeholder="/path/to/documents"
+								value={folderPath}
+								onChange={(e) => setFolderPath(e.target.value)}
+							/>
+						</div>
+						<div className="flex justify-end gap-2">
+							<Button
+								variant="outline"
+								onClick={() => setShowFolderDialog(false)}
+							>
+								Cancel
+							</Button>
+							<Button
+								onClick={handleFolderUpload}
+								disabled={!folderPath.trim() || folderLoading}
+							>
+								{folderLoading ? "Processing..." : "Process Folder"}
+							</Button>
+						</div>
+					</div>
+				</DialogContent>
+			</Dialog>
+
+			{/* Process S3 Bucket Dialog */}
+			<Dialog open={showS3Dialog} onOpenChange={setShowS3Dialog}>
+				<DialogContent>
+					<DialogHeader>
+						<DialogTitle className="flex items-center gap-2">
+							<Cloud className="h-5 w-5" />
+							Process S3 Bucket
+						</DialogTitle>
+						<DialogDescription>
+							Process all documents from an S3 bucket. AWS credentials must be
+							configured.
+						</DialogDescription>
+					</DialogHeader>
+					<div className="space-y-4">
+						<div className="space-y-2">
+							<Label htmlFor="bucket-url">S3 URL</Label>
+							<Input
+								id="bucket-url"
+								type="text"
+								placeholder="s3://bucket/path"
+								value={bucketUrl}
+								onChange={(e) => setBucketUrl(e.target.value)}
+							/>
+						</div>
+						<div className="flex justify-end gap-2">
+							<Button variant="outline" onClick={() => setShowS3Dialog(false)}>
+								Cancel
+							</Button>
+							<Button
+								onClick={handleS3Upload}
+								disabled={!bucketUrl.trim() || s3Loading}
+							>
+								{s3Loading ? "Processing..." : "Process Bucket"}
+							</Button>
+						</div>
+					</div>
+				</DialogContent>
+			</Dialog>
+
+			{/* Duplicate Handling Dialog */}
+			<DuplicateHandlingDialog
+				open={showDuplicateDialog}
+				onOpenChange={setShowDuplicateDialog}
+				onOverwrite={handleOverwriteFile}
+				isLoading={fileUploading}
+			/>
+		</>
+	);
 }
diff --git a/frontend/components/logo/ibm-logo.tsx b/frontend/components/logo/ibm-logo.tsx
index 158ffa3b..e37adec1 100644
--- a/frontend/components/logo/ibm-logo.tsx
+++ b/frontend/components/logo/ibm-logo.tsx
@@ -9,7 +9,7 @@ export default function IBMLogo(props: React.SVGProps<SVGSVGElement>) {
       {...props}
     >
       <title>IBM watsonx.ai Logo</title>
-      <g clip-path="url(#clip0_2620_2081)">
+      <g clipPath="url(#clip0_2620_2081)">
         <path
           d="M13 12.0007C12.4477 12.0007 12 12.4484 12 13.0007C12 13.0389 12.0071 13.0751 12.0112 13.1122C10.8708 14.0103 9.47165 14.5007 8 14.5007C5.86915 14.5007 4 12.5146 4 10.2507C4 7.90722 5.9065 6.00072 8.25 6.00072H8.5V5.00072H8.25C5.3552 5.00072 3 7.35592 3 10.2507C3 11.1927 3.2652 12.0955 3.71855 12.879C2.3619 11.6868 1.5 9.94447 1.5 8.00072C1.5 6.94312 1.74585 5.93432 2.23095 5.00292L1.34375 4.54102C0.79175 5.60157 0.5 6.79787 0.5 8.00072C0.5 12.1362 3.8645 15.5007 8 15.5007C9.6872 15.5007 11.2909 14.9411 12.6024 13.9176C12.7244 13.9706 12.8586 14.0007 13 14.0007C13.5523 14.0007 14 13.553 14 13.0007C14 12.4484 13.5523 12.0007 13 12.0007Z"
           fill="currentColor"
diff --git a/frontend/components/ui/banner.tsx b/frontend/components/ui/banner.tsx
new file mode 100644
index 00000000..3a1ea9f5
--- /dev/null
+++ b/frontend/components/ui/banner.tsx
@@ -0,0 +1,141 @@
+'use client';
+import { useControllableState } from '@radix-ui/react-use-controllable-state';
+import { type LucideIcon, XIcon } from 'lucide-react';
+import {
+  type ComponentProps,
+  createContext,
+  type HTMLAttributes,
+  type MouseEventHandler,
+  useContext,
+} from 'react';
+import { Button } from '@/components/ui/button';
+import { cn } from '@/lib/utils';
+
+type BannerContextProps = {
+  show: boolean;
+  setShow: (show: boolean) => void;
+};
+
+export const BannerContext = createContext<BannerContextProps>({
+  show: true,
+  setShow: () => {},
+});
+
+export type BannerProps = HTMLAttributes<HTMLDivElement> & {
+  visible?: boolean;
+  defaultVisible?: boolean;
+  onClose?: () => void;
+  inset?: boolean;
+};
+
+export const Banner = ({
+  children,
+  visible,
+  defaultVisible = true,
+  onClose,
+  className,
+  inset = false,
+  ...props
+}: BannerProps) => {
+  const [show, setShow] = useControllableState({
+    defaultProp: defaultVisible,
+    prop: visible,
+    onChange: onClose,
+  });
+
+  if (!show) {
+    return null;
+  }
+
+  return (
+    <BannerContext.Provider value={{ show, setShow }}>
+      <div
+        className={cn(
+          'flex w-full items-center justify-between gap-2 bg-primary px-4 py-2 text-primary-foreground',
+          inset && 'rounded-lg',
+          className
+        )}
+        {...props}
+      >
+        {children}
+      </div>
+    </BannerContext.Provider>
+  );
+};
+
+export type BannerIconProps = HTMLAttributes<HTMLDivElement> & {
+  icon: LucideIcon;
+};
+
+export const BannerIcon = ({
+  icon: Icon,
+  className,
+  ...props
+}: BannerIconProps) => (
+  <div
+    className={cn(
+      'p-1',
+      className
+    )}
+    {...props}
+  >
+    <Icon size={16} />
+  </div>
+);
+
+export type BannerTitleProps = HTMLAttributes<HTMLParagraphElement>;
+
+export const BannerTitle = ({ className, ...props }: BannerTitleProps) => (
+  <p className={cn('flex-1 text-sm', className)} {...props} />
+);
+
+export type BannerActionProps = ComponentProps<typeof Button>;
+
+export const BannerAction = ({
+  variant = 'outline',
+  size = 'sm',
+  className,
+  ...props
+}: BannerActionProps) => (
+  <Button
+    className={cn(
+      'shrink-0 bg-transparent hover:bg-background/10 hover:text-background',
+      className
+    )}
+    size={size}
+    variant={variant}
+    {...props}
+  />
+);
+
+export type BannerCloseProps = ComponentProps<typeof Button>;
+
+export const BannerClose = ({
+  variant = 'ghost',
+  size = 'icon',
+  onClick,
+  className,
+  ...props
+}: BannerCloseProps) => {
+  const { setShow } = useContext(BannerContext);
+
+  const handleClick: MouseEventHandler<HTMLButtonElement> = (e) => {
+    setShow(false);
+    onClick?.(e);
+  };
+
+  return (
+    <Button
+      className={cn(
+        'shrink-0 bg-transparent hover:bg-background/10 hover:text-background',
+        className
+      )}
+      onClick={handleClick}
+      size={size}
+      variant={variant}
+      {...props}
+    >
+      <XIcon size={18} />
+    </Button>
+  );
+};
\ No newline at end of file
diff --git a/frontend/components/ui/input.tsx b/frontend/components/ui/input.tsx
index ffcda454..86e638a1 100644
--- a/frontend/components/ui/input.tsx
+++ b/frontend/components/ui/input.tsx
@@ -44,7 +44,7 @@ const Input = React.forwardRef<HTMLInputElement, InputProps>(
           placeholder={placeholder}
           className={cn(
             "primary-input",
-            icon && "pl-9",
+            icon && "!pl-9",
             type === "password" && "!pr-8",
             icon ? inputClassName : className
           )}
diff --git a/frontend/src/app/api/mutations/useCancelTaskMutation.ts b/frontend/src/app/api/mutations/useCancelTaskMutation.ts
new file mode 100644
index 00000000..1bf2faed
--- /dev/null
+++ b/frontend/src/app/api/mutations/useCancelTaskMutation.ts
@@ -0,0 +1,47 @@
+import {
+  type UseMutationOptions,
+  useMutation,
+  useQueryClient,
+} from "@tanstack/react-query";
+
+export interface CancelTaskRequest {
+  taskId: string;
+}
+
+export interface CancelTaskResponse {
+  status: string;
+  task_id: string;
+}
+
+export const useCancelTaskMutation = (
+  options?: Omit<
+    UseMutationOptions<CancelTaskResponse, Error, CancelTaskRequest>,
+    "mutationFn"
+  >
+) => {
+  const queryClient = useQueryClient();
+
+  async function cancelTask(
+    variables: CancelTaskRequest,
+  ): Promise<CancelTaskResponse> {
+    const response = await fetch(`/api/tasks/${variables.taskId}/cancel`, {
+      method: "POST",
+    });
+
+    if (!response.ok) {
+      const errorData = await response.json().catch(() => ({}));
+      throw new Error(errorData.error || "Failed to cancel task");
+    }
+
+    return response.json();
+  }
+
+  return useMutation({
+    mutationFn: cancelTask,
+    onSuccess: () => {
+      // Invalidate tasks query to refresh the list
+      queryClient.invalidateQueries({ queryKey: ["tasks"] });
+    },
+    ...options,
+  });
+};
diff --git a/frontend/src/app/api/queries/useDoclingHealthQuery.ts b/frontend/src/app/api/queries/useDoclingHealthQuery.ts
new file mode 100644
index 00000000..16ffc6c5
--- /dev/null
+++ b/frontend/src/app/api/queries/useDoclingHealthQuery.ts
@@ -0,0 +1,55 @@
+import {
+  type UseQueryOptions,
+  useQuery,
+  useQueryClient,
+} from "@tanstack/react-query";
+
+export interface DoclingHealthResponse {
+  status: "healthy" | "unhealthy";
+  message?: string;
+}
+
+export const useDoclingHealthQuery = (
+  options?: Omit<UseQueryOptions<DoclingHealthResponse>, "queryKey" | "queryFn">,
+) => {
+  const queryClient = useQueryClient();
+
+  async function checkDoclingHealth(): Promise<DoclingHealthResponse> {
+    try {
+      const response = await fetch("http://127.0.0.1:5001/health", {
+        method: "GET",
+        headers: {
+          "Content-Type": "application/json",
+        },
+      });
+
+      if (response.ok) {
+        return { status: "healthy" };
+      } else {
+        return {
+          status: "unhealthy",
+          message: `Health check failed with status: ${response.status}`,
+        };
+      }
+    } catch (error) {
+      return {
+        status: "unhealthy",
+        message: error instanceof Error ? error.message : "Connection failed",
+      };
+    }
+  }
+
+  const queryResult = useQuery(
+    {
+      queryKey: ["docling-health"],
+      queryFn: checkDoclingHealth,
+      retry: 1,
+      refetchInterval: 30000, // Check every 30 seconds
+      staleTime: 25000, // Consider data stale after 25 seconds
+      ...options,
+    },
+    queryClient,
+  );
+
+  return queryResult;
+};
\ No newline at end of file
diff --git a/frontend/src/app/api/queries/useGetSearchQuery.ts b/frontend/src/app/api/queries/useGetSearchQuery.ts
index 5383178d..d0c1a3a9 100644
--- a/frontend/src/app/api/queries/useGetSearchQuery.ts
+++ b/frontend/src/app/api/queries/useGetSearchQuery.ts
@@ -29,6 +29,7 @@ export interface ChunkResult {
   owner_email?: string;
   file_size?: number;
   connector_type?: string;
+  index?: number;
 }
 
 export interface File {
@@ -55,7 +56,7 @@ export interface File {
 export const useGetSearchQuery = (
   query: string,
   queryData?: ParsedQueryData | null,
-  options?: Omit<UseQueryOptions, "queryKey" | "queryFn">,
+  options?: Omit<UseQueryOptions, "queryKey" | "queryFn">
 ) => {
   const queryClient = useQueryClient();
 
@@ -184,7 +185,7 @@ export const useGetSearchQuery = (
       queryFn: getFiles,
       ...options,
     },
-    queryClient,
+    queryClient
   );
 
   return queryResult;
diff --git a/frontend/src/app/api/queries/useGetTasksQuery.ts b/frontend/src/app/api/queries/useGetTasksQuery.ts
new file mode 100644
index 00000000..1ea59d26
--- /dev/null
+++ b/frontend/src/app/api/queries/useGetTasksQuery.ts
@@ -0,0 +1,79 @@
+import {
+  type UseQueryOptions,
+  useQuery,
+  useQueryClient,
+} from "@tanstack/react-query";
+
+export interface Task {
+  task_id: string;
+  status:
+    | "pending"
+    | "running"
+    | "processing"
+    | "completed"
+    | "failed"
+    | "error";
+  total_files?: number;
+  processed_files?: number;
+  successful_files?: number;
+  failed_files?: number;
+  running_files?: number;
+  pending_files?: number;
+  created_at: string;
+  updated_at: string;
+  duration_seconds?: number;
+  result?: Record<string, unknown>;
+  error?: string;
+  files?: Record<string, Record<string, unknown>>;
+}
+
+export interface TasksResponse {
+  tasks: Task[];
+}
+
+export const useGetTasksQuery = (
+  options?: Omit<UseQueryOptions<Task[]>, "queryKey" | "queryFn">
+) => {
+  const queryClient = useQueryClient();
+
+  async function getTasks(): Promise<Task[]> {
+    const response = await fetch("/api/tasks");
+    
+    if (!response.ok) {
+      throw new Error("Failed to fetch tasks");
+    }
+
+    const data: TasksResponse = await response.json();
+    return data.tasks || [];
+  }
+
+  const queryResult = useQuery(
+    {
+      queryKey: ["tasks"],
+      queryFn: getTasks,
+      refetchInterval: (query) => {
+        // Only poll if there are tasks with pending or running status
+        const data = query.state.data;
+        if (!data || data.length === 0) {
+          return false; // Stop polling if no tasks
+        }
+
+        const hasActiveTasks = data.some(
+          (task: Task) => 
+            task.status === "pending" || 
+            task.status === "running" || 
+            task.status === "processing"
+        );
+
+        return hasActiveTasks ? 3000 : false; // Poll every 3 seconds if active tasks exist
+      },
+      refetchIntervalInBackground: true,
+      staleTime: 0, // Always consider data stale to ensure fresh updates
+      gcTime: 5 * 60 * 1000, // Keep in cache for 5 minutes
+      ...options,
+    },
+    queryClient,
+  );
+
+  return queryResult;
+};
diff --git a/frontend/src/app/chat/page.tsx b/frontend/src/app/chat/page.tsx
index 01ee43c7..2c3bf278 100644
--- a/frontend/src/app/chat/page.tsx
+++ b/frontend/src/app/chat/page.tsx
@@ -31,6 +31,7 @@ import {
 import { useAuth } from "@/contexts/auth-context";
 import { type EndpointType, useChat } from "@/contexts/chat-context";
 import { useKnowledgeFilter } from "@/contexts/knowledge-filter-context";
+import { useLayout } from "@/contexts/layout-context";
 import { useTask } from "@/contexts/task-context";
 import { useLoadingStore } from "@/stores/loadingStore";
 import { useGetNudgesQuery } from "../api/queries/useGetNudgesQuery";
@@ -151,6 +152,7 @@ function ChatPage() {
   const streamIdRef = useRef(0);
   const lastLoadedConversationRef = useRef<string | null>(null);
   const { addTask, isMenuOpen } = useTask();
+  const { totalTopOffset } = useLayout();
   const { selectedFilter, parsedFilterData, isPanelOpen, setSelectedFilter } =
     useKnowledgeFilter();
 
@@ -2046,7 +2048,7 @@ function ChatPage() {
 
   return (
     <div
-      className={`fixed inset-0 md:left-72 top-[53px] flex flex-col transition-all duration-300 ${
+      className={`fixed inset-0 md:left-72 flex flex-col transition-all duration-300 ${
         isMenuOpen && isPanelOpen
           ? "md:right-[704px]" // Both open: 384px (menu) + 320px (KF panel)
           : isMenuOpen
@@ -2055,6 +2057,7 @@ function ChatPage() {
           ? "md:right-80" // Only KF panel open: 320px
           : "md:right-6" // Neither open: 24px
       }`}
+      style={{ top: `${totalTopOffset}px` }}
     >
       {/* Debug header - only show in debug mode */}
       {isDebugMode && (
diff --git a/frontend/src/app/knowledge/chunks/page.tsx b/frontend/src/app/knowledge/chunks/page.tsx
index cb96eddc..327bd884 100644
--- a/frontend/src/app/knowledge/chunks/page.tsx
+++ b/frontend/src/app/knowledge/chunks/page.tsx
@@ -1,176 +1,204 @@
 "use client";
 
-import { ArrowLeft, Check, Copy, Loader2, Search } from "lucide-react";
-import { Suspense, useCallback, useEffect, useMemo, useState } from "react";
+import { ArrowLeft, Check, Copy, Loader2, Search, X } from "lucide-react";
 import { useRouter, useSearchParams } from "next/navigation";
+import { Suspense, useCallback, useEffect, useMemo, useState } from "react";
+// import { Label } from "@/components/ui/label";
+// import { Checkbox } from "@/components/ui/checkbox";
+import { filterAccentClasses } from "@/components/knowledge-filter-panel";
 import { ProtectedRoute } from "@/components/protected-route";
 import { Button } from "@/components/ui/button";
-import { useKnowledgeFilter } from "@/contexts/knowledge-filter-context";
-import { useTask } from "@/contexts/task-context";
-import {
-  type ChunkResult,
-  type File,
-  useGetSearchQuery,
-} from "../../api/queries/useGetSearchQuery";
-import { Label } from "@/components/ui/label";
 import { Checkbox } from "@/components/ui/checkbox";
 import { Input } from "@/components/ui/input";
+import { Label } from "@/components/ui/label";
+import { useKnowledgeFilter } from "@/contexts/knowledge-filter-context";
+import { useLayout } from "@/contexts/layout-context";
+import { useTask } from "@/contexts/task-context";
+import {
+	type ChunkResult,
+	type File,
+	useGetSearchQuery,
+} from "../../api/queries/useGetSearchQuery";
 
 const getFileTypeLabel = (mimetype: string) => {
-  if (mimetype === "application/pdf") return "PDF";
-  if (mimetype === "text/plain") return "Text";
-  if (mimetype === "application/msword") return "Word Document";
-  return "Unknown";
+	if (mimetype === "application/pdf") return "PDF";
+	if (mimetype === "text/plain") return "Text";
+	if (mimetype === "application/msword") return "Word Document";
+	return "Unknown";
 };
 
 function ChunksPageContent() {
-  const router = useRouter();
-  const searchParams = useSearchParams();
-  const { isMenuOpen } = useTask();
-  const { parsedFilterData, isPanelOpen } = useKnowledgeFilter();
+	const router = useRouter();
+	const searchParams = useSearchParams();
+	const { selectedFilter, setSelectedFilter, parsedFilterData, isPanelOpen } =
+		useKnowledgeFilter();
+	const { isMenuOpen } = useTask();
+	const { totalTopOffset } = useLayout();
 
-  const filename = searchParams.get("filename");
-  const [chunks, setChunks] = useState<ChunkResult[]>([]);
-  const [chunksFilteredByQuery, setChunksFilteredByQuery] = useState<
-    ChunkResult[]
-  >([]);
-  const [selectedChunks, setSelectedChunks] = useState<Set<number>>(new Set());
-  const [activeCopiedChunkIndex, setActiveCopiedChunkIndex] = useState<
-    number | null
-  >(null);
+	const filename = searchParams.get("filename");
+	const [chunks, setChunks] = useState<ChunkResult[]>([]);
+	const [chunksFilteredByQuery, setChunksFilteredByQuery] = useState<
+		ChunkResult[]
+	>([]);
+	const [selectedChunks, setSelectedChunks] = useState<Set<number>>(new Set());
+	const [activeCopiedChunkIndex, setActiveCopiedChunkIndex] = useState<
+		number | null
+	>(null);
 
-  // Calculate average chunk length
-  const averageChunkLength = useMemo(
-    () =>
-      chunks.reduce((acc, chunk) => acc + chunk.text.length, 0) /
-        chunks.length || 0,
-    [chunks]
-  );
+	// Calculate average chunk length
+	const averageChunkLength = useMemo(
+		() =>
+			chunks.reduce((acc, chunk) => acc + chunk.text.length, 0) /
+				chunks.length || 0,
+		[chunks],
+	);
 
-  const [selectAll, setSelectAll] = useState(false);
-  const [queryInputText, setQueryInputText] = useState(
-    parsedFilterData?.query ?? ""
-  );
+	const [selectAll, setSelectAll] = useState(false);
+	const [queryInputText, setQueryInputText] = useState(
+		parsedFilterData?.query ?? "",
+	);
 
-  // Use the same search query as the knowledge page, but we'll filter for the specific file
-  const { data = [], isFetching } = useGetSearchQuery("*", parsedFilterData);
+	// Use the same search query as the knowledge page, but we'll filter for the specific file
+	const { data = [], isFetching } = useGetSearchQuery("*", parsedFilterData);
 
-  useEffect(() => {
-    if (queryInputText === "") {
-      setChunksFilteredByQuery(chunks);
-    } else {
-      setChunksFilteredByQuery(
-        chunks.filter((chunk) =>
-          chunk.text.toLowerCase().includes(queryInputText.toLowerCase())
-        )
-      );
-    }
-  }, [queryInputText, chunks]);
+	useEffect(() => {
+		if (queryInputText === "") {
+			setChunksFilteredByQuery(chunks);
+		} else {
+			setChunksFilteredByQuery(
+				chunks.filter((chunk) =>
+					chunk.text.toLowerCase().includes(queryInputText.toLowerCase()),
+				),
+			);
+		}
+	}, [queryInputText, chunks]);
 
-  const handleCopy = useCallback((text: string, index: number) => {
-    // Trim whitespace and remove new lines/tabs for cleaner copy
-    navigator.clipboard.writeText(text.trim().replace(/[\n\r\t]/gm, ""));
-    setActiveCopiedChunkIndex(index);
-    setTimeout(() => setActiveCopiedChunkIndex(null), 10 * 1000); // 10 seconds
-  }, []);
+	const handleCopy = useCallback((text: string, index: number) => {
+		// Trim whitespace and remove new lines/tabs for cleaner copy
+		navigator.clipboard.writeText(text.trim().replace(/[\n\r\t]/gm, ""));
+		setActiveCopiedChunkIndex(index);
+		setTimeout(() => setActiveCopiedChunkIndex(null), 10 * 1000); // 10 seconds
+	}, []);
 
-  const fileData = (data as File[]).find(
-    (file: File) => file.filename === filename
-  );
+	const fileData = (data as File[]).find(
+		(file: File) => file.filename === filename,
+	);
 
-  // Extract chunks for the specific file
-  useEffect(() => {
-    if (!filename || !(data as File[]).length) {
-      setChunks([]);
-      return;
-    }
+	// Extract chunks for the specific file
+	useEffect(() => {
+		if (!filename || !(data as File[]).length) {
+			setChunks([]);
+			return;
+		}
 
-    setChunks(fileData?.chunks || []);
-  }, [data, filename]);
+		setChunks(
+			fileData?.chunks?.map((chunk, i) => ({ ...chunk, index: i + 1 })) || [],
+		);
+	}, [data, filename]);
 
-  // Set selected state for all checkboxes when selectAll changes
-  useEffect(() => {
-    if (selectAll) {
-      setSelectedChunks(new Set(chunks.map((_, index) => index)));
-    } else {
-      setSelectedChunks(new Set());
-    }
-  }, [selectAll, setSelectedChunks, chunks]);
+	// Set selected state for all checkboxes when selectAll changes
+	useEffect(() => {
+		if (selectAll) {
+			setSelectedChunks(new Set(chunks.map((_, index) => index)));
+		} else {
+			setSelectedChunks(new Set());
+		}
+	}, [selectAll, setSelectedChunks, chunks]);
 
-  const handleBack = useCallback(() => {
-    router.push("/knowledge");
-  }, [router]);
+	const handleBack = useCallback(() => {
+		router.push("/knowledge");
+	}, [router]);
 
-  const handleChunkCardCheckboxChange = useCallback(
-    (index: number) => {
-      setSelectedChunks((prevSelected) => {
-        const newSelected = new Set(prevSelected);
-        if (newSelected.has(index)) {
-          newSelected.delete(index);
-        } else {
-          newSelected.add(index);
-        }
-        return newSelected;
-      });
-    },
-    [setSelectedChunks]
-  );
+	// const handleChunkCardCheckboxChange = useCallback(
+	//   (index: number) => {
+	//     setSelectedChunks((prevSelected) => {
+	//       const newSelected = new Set(prevSelected);
+	//       if (newSelected.has(index)) {
+	//         newSelected.delete(index);
+	//       } else {
+	//         newSelected.add(index);
+	//       }
+	//       return newSelected;
+	//     });
+	//   },
+	//   [setSelectedChunks]
+	// );
 
-  if (!filename) {
-    return (
-      <div className="flex items-center justify-center h-64">
-        <div className="text-center">
-          <Search className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50" />
-          <p className="text-lg text-muted-foreground">No file specified</p>
-          <p className="text-sm text-muted-foreground/70 mt-2">
-            Please select a file from the knowledge page
-          </p>
-        </div>
-      </div>
-    );
-  }
+	if (!filename) {
+		return (
+			<div className="flex items-center justify-center h-64">
+				<div className="text-center">
+					<Search className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50" />
+					<p className="text-lg text-muted-foreground">No file specified</p>
+					<p className="text-sm text-muted-foreground/70 mt-2">
+						Please select a file from the knowledge page
+					</p>
+				</div>
+			</div>
+		);
+	}
 
-  return (
-    <div
-      className={`fixed inset-0 md:left-72 top-[53px] flex flex-row transition-all duration-300 ${
-        isMenuOpen && isPanelOpen
-          ? "md:right-[704px]"
-          : // Both open: 384px (menu) + 320px (KF panel)
-          isMenuOpen
-          ? "md:right-96"
-          : // Only menu open: 384px
-          isPanelOpen
-          ? "md:right-80"
-          : // Only KF panel open: 320px
-            "md:right-6" // Neither open: 24px
-      }`}
-    >
-      <div className="flex-1 flex flex-col min-h-0 px-6 py-6">
-        {/* Header */}
-        <div className="flex flex-col mb-6">
-          <div className="flex flex-row items-center gap-3 mb-6">
-            <Button variant="ghost" onClick={handleBack} size="sm">
-              <ArrowLeft size={24} />
-            </Button>
-            <h1 className="text-lg font-semibold">
-              {/* Removes file extension from filename */}
-              {filename.replace(/\.[^/.]+$/, "")}
-            </h1>
-          </div>
-          <div className="flex flex-col items-start mt-2">
-            <div className="flex-1 flex items-center gap-2 w-full max-w-[616px] mb-8">
-              <Input
-                name="search-query"
-                icon={!queryInputText.length ? <Search size={18} /> : null}
-                id="search-query"
-                type="text"
-                defaultValue={parsedFilterData?.query}
-                value={queryInputText}
-                onChange={(e) => setQueryInputText(e.target.value)}
-                placeholder="Search chunks..."
-              />
-            </div>
-            <div className="flex items-center pl-4 gap-2">
+	return (
+		<div
+			className={`fixed inset-0 md:left-72 flex flex-row transition-all duration-300 ${
+				isMenuOpen && isPanelOpen
+					? "md:right-[704px]"
+					: // Both open: 384px (menu) + 320px (KF panel)
+						isMenuOpen
+						? "md:right-96"
+						: // Only menu open: 384px
+							isPanelOpen
+							? "md:right-80"
+							: // Only KF panel open: 320px
+								"md:right-6" // Neither open: 24px
+			}`}
+			style={{ top: `${totalTopOffset}px` }}
+		>
+			<div className="flex-1 flex flex-col min-h-0 px-6 py-6">
+				{/* Header */}
+				<div className="flex flex-col mb-6">
+					<div className="flex flex-row items-center gap-3 mb-6">
+						<Button variant="ghost" onClick={handleBack} size="sm">
+							<ArrowLeft size={24} />
+						</Button>
+						<h1 className="text-lg font-semibold">
+							{/* Removes file extension from filename */}
+							{filename.replace(/\.[^/.]+$/, "")}
+						</h1>
+					</div>
+					<div className="flex flex-col items-start mt-2">
+						<div className="flex-1 flex items-center gap-2 w-full max-w-[640px]">
+							<div className="primary-input min-h-10 !flex items-center flex-nowrap focus-within:border-foreground transition-colors !p-[0.3rem]">
+								{selectedFilter?.name && (
+									<div
+										className={`flex items-center gap-1 h-full px-1.5 py-0.5 mr-1 rounded max-w-[25%] ${
+											filterAccentClasses[parsedFilterData?.color || "zinc"]
+										}`}
+									>
+										<span className="truncate">{selectedFilter?.name}</span>
+										<X
+											aria-label="Remove filter"
+											className="h-4 w-4 flex-shrink-0 cursor-pointer"
+											onClick={() => setSelectedFilter(null)}
+										/>
+									</div>
+								)}
+								<Search
+									className="h-4 w-4 ml-1 flex-shrink-0 text-placeholder-foreground"
+									strokeWidth={1.5}
+								/>
+								<input
+									className="bg-transparent w-full h-full ml-2 focus:outline-none focus-visible:outline-none font-mono placeholder:font-mono"
+									name="search-query"
+									id="search-query"
+									type="text"
+									placeholder="Enter your search query..."
+									onChange={(e) => setQueryInputText(e.target.value)}
+									value={queryInputText}
+								/>
+							</div>
+						</div>
+						{/* <div className="flex items-center pl-4 gap-2">
               <Checkbox
                 id="selectAllChunks"
                 checked={selectAll}
@@ -184,106 +212,114 @@ function ChunksPageContent() {
               >
                 Select all
               </Label>
-            </div>
-          </div>
-        </div>
+            </div> */}
+					</div>
+				</div>
 
-        {/* Content Area - matches knowledge page structure */}
-        <div className="flex-1 overflow-scroll pr-6">
-          {isFetching ? (
-            <div className="flex items-center justify-center h-64">
-              <div className="text-center">
-                <Loader2 className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50 animate-spin" />
-                <p className="text-lg text-muted-foreground">
-                  Loading chunks...
-                </p>
-              </div>
-            </div>
-          ) : chunks.length === 0 ? (
-            <div className="flex items-center justify-center h-64">
-              <div className="text-center">
-                <Search className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50" />
-                <p className="text-lg text-muted-foreground">No chunks found</p>
-                <p className="text-sm text-muted-foreground/70 mt-2">
-                  This file may not have been indexed yet
-                </p>
-              </div>
-            </div>
-          ) : (
-            <div className="space-y-4 pb-6">
-              {chunksFilteredByQuery.map((chunk, index) => (
-                <div
-                  key={chunk.filename + index}
-                  className="bg-muted rounded-lg p-4 border border-border/50"
-                >
-                  <div className="flex items-center justify-between mb-2">
-                    <div className="flex items-center gap-3">
-                      <div>
+				{/* Content Area - matches knowledge page structure */}
+				<div className="flex-1 overflow-scroll pr-6">
+					{isFetching ? (
+						<div className="flex items-center justify-center h-64">
+							<div className="text-center">
+								<Loader2 className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50 animate-spin" />
+								<p className="text-lg text-muted-foreground">
+									Loading chunks...
+								</p>
+							</div>
+						</div>
+					) : chunks.length === 0 ? (
+						<div className="flex items-center justify-center h-64">
+							<div className="text-center">
+								<p className="text-xl font-semibold mb-2">No knowledge</p>
+								<p className="text-sm text-secondary-foreground">
+									Clear the knowledge filter or return to the knowledge page
+								</p>
+							</div>
+						</div>
+					) : (
+						<div className="space-y-4 pb-6">
+							{chunksFilteredByQuery.map((chunk, index) => (
+								<div
+									key={chunk.filename + index}
+									className="bg-muted rounded-lg p-4 border border-border/50"
+								>
+									<div className="flex items-center justify-between mb-2">
+										<div className="flex items-center gap-3">
+											{/* <div>
                         <Checkbox
                           checked={selectedChunks.has(index)}
                           onCheckedChange={() =>
                             handleChunkCardCheckboxChange(index)
                           }
                         />
-                      </div>
-                      <span className="text-sm font-bold">
-                        Chunk {chunk.page}
-                      </span>
-                      <span className="bg-background p-1 rounded text-xs text-muted-foreground/70">
-                        {chunk.text.length} chars
-                      </span>
-                      <div className="py-1">
-                        <Button
-                          onClick={() => handleCopy(chunk.text, index)}
-                          variant="ghost"
-                          size="sm"
-                        >
-                          {activeCopiedChunkIndex === index ? (
-                            <Check className="text-muted-foreground" />
-                          ) : (
-                            <Copy className="text-muted-foreground" />
-                          )}
-                        </Button>
-                      </div>
-                    </div>
+                      </div> */}
+											<span className="text-sm font-bold">
+												Chunk {chunk.index}
+											</span>
+											<span className="bg-background p-1 rounded text-xs text-muted-foreground/70">
+												{chunk.text.length} chars
+											</span>
+											<div className="py-1">
+												<Button
+													onClick={() => handleCopy(chunk.text, index)}
+													variant="ghost"
+													size="sm"
+												>
+													{activeCopiedChunkIndex === index ? (
+														<Check className="text-muted-foreground" />
+													) : (
+														<Copy className="text-muted-foreground" />
+													)}
+												</Button>
+											</div>
+										</div>
 
-                    {/* TODO: Update to use active toggle */}
-                    {/* <span className="px-2 py-1 text-green-500">
+										<span className="bg-background p-1 rounded text-xs text-muted-foreground/70">
+											{chunk.score.toFixed(2)} score
+										</span>
+
+										{/* TODO: Update to use active toggle */}
+										{/* <span className="px-2 py-1 text-green-500">
                       <Switch
                         className="ml-2 bg-green-500"
                         checked={true}
                       />
                       Active
                     </span> */}
-                  </div>
-                  <blockquote className="text-sm text-muted-foreground leading-relaxed border-l-2 border-input ml-1.5 pl-4">
-                    {chunk.text}
-                  </blockquote>
-                </div>
-              ))}
-            </div>
-          )}
-        </div>
-      </div>
-      {/* Right panel - Summary (TODO), Technical details,  */}
-      <div className="w-[320px] py-20 px-2">
-        <div className="mb-8">
-          <h2 className="text-xl font-semibold mt-3 mb-4">Technical details</h2>
-          <dl>
-            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
-              <dt className="text-sm/6 text-muted-foreground">Total chunks</dt>
-              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
-                {chunks.length}
-              </dd>
-            </div>
-            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
-              <dt className="text-sm/6 text-muted-foreground">Avg length</dt>
-              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
-                {averageChunkLength.toFixed(0)} chars
-              </dd>
-            </div>
-            {/* TODO: Uncomment after data is available */}
-            {/* <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+									</div>
+									<blockquote className="text-sm text-muted-foreground leading-relaxed ml-1.5">
+										{chunk.text}
+									</blockquote>
+								</div>
+							))}
+						</div>
+					)}
+				</div>
+			</div>
+			{/* Right panel - Summary (TODO), Technical details,  */}
+			{chunks.length > 0 && (
+				<div className="w-[320px] py-20 px-2">
+					<div className="mb-8">
+						<h2 className="text-xl font-semibold mt-3 mb-4">
+							Technical details
+						</h2>
+						<dl>
+							<div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+								<dt className="text-sm/6 text-muted-foreground">
+									Total chunks
+								</dt>
+								<dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+									{chunks.length}
+								</dd>
+							</div>
+							<div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+								<dt className="text-sm/6 text-muted-foreground">Avg length</dt>
+								<dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+									{averageChunkLength.toFixed(0)} chars
+								</dd>
+							</div>
+							{/* TODO: Uncomment after data is available */}
+							{/* <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
               <dt className="text-sm/6 text-muted-foreground">Process time</dt>
               <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
               </dd>
@@ -293,76 +329,79 @@ function ChunksPageContent() {
               <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
               </dd>
             </div> */}
-          </dl>
-        </div>
-        <div className="mb-8">
-          <h2 className="text-xl font-semibold mt-2 mb-3">Original document</h2>
-          <dl>
-            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+						</dl>
+					</div>
+					<div className="mb-8">
+						<h2 className="text-xl font-semibold mt-2 mb-3">
+							Original document
+						</h2>
+						<dl>
+							{/* <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
               <dt className="text-sm/6 text-muted-foreground">Name</dt>
               <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
                 {fileData?.filename}
               </dd>
-            </div>
-            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
-              <dt className="text-sm/6 text-muted-foreground">Type</dt>
-              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
-                {fileData ? getFileTypeLabel(fileData.mimetype) : "Unknown"}
-              </dd>
-            </div>
-            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
-              <dt className="text-sm/6 text-muted-foreground">Size</dt>
-              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
-                {fileData?.size
-                  ? `${Math.round(fileData.size / 1024)} KB`
-                  : "Unknown"}
-              </dd>
-            </div>
-            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+            </div> */}
+							<div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+								<dt className="text-sm/6 text-muted-foreground">Type</dt>
+								<dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+									{fileData ? getFileTypeLabel(fileData.mimetype) : "Unknown"}
+								</dd>
+							</div>
+							<div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+								<dt className="text-sm/6 text-muted-foreground">Size</dt>
+								<dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+									{fileData?.size
+										? `${Math.round(fileData.size / 1024)} KB`
+										: "Unknown"}
+								</dd>
+							</div>
+							{/* <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
               <dt className="text-sm/6 text-muted-foreground">Uploaded</dt>
               <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
                 N/A
               </dd>
-            </div>
-            {/* TODO: Uncomment after data is available */}
-            {/* <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+            </div> */}
+							{/* TODO: Uncomment after data is available */}
+							{/* <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
               <dt className="text-sm/6 text-muted-foreground">Source</dt>
               <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0"></dd>
             </div> */}
-            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+							{/* <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
               <dt className="text-sm/6 text-muted-foreground">Updated</dt>
               <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
                 N/A
               </dd>
-            </div>
-          </dl>
-        </div>
-      </div>
-    </div>
-  );
+            </div> */}
+						</dl>
+					</div>
+				</div>
+			)}
+		</div>
+	);
 }
 
 function ChunksPage() {
-  return (
-    <Suspense
-      fallback={
-        <div className="flex items-center justify-center h-64">
-          <div className="text-center">
-            <Loader2 className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50 animate-spin" />
-            <p className="text-lg text-muted-foreground">Loading...</p>
-          </div>
-        </div>
-      }
-    >
-      <ChunksPageContent />
-    </Suspense>
-  );
+	return (
+		<Suspense
+			fallback={
+				<div className="flex items-center justify-center h-64">
+					<div className="text-center">
+						<Loader2 className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50 animate-spin" />
+						<p className="text-lg text-muted-foreground">Loading...</p>
+					</div>
+				</div>
+			}
+		>
+			<ChunksPageContent />
+		</Suspense>
+	);
 }
 
 export default function ProtectedChunksPage() {
-  return (
-    <ProtectedRoute>
-      <ChunksPage />
-    </ProtectedRoute>
-  );
+	return (
+		<ProtectedRoute>
+			<ChunksPage />
+		</ProtectedRoute>
+	);
 }
diff --git a/frontend/src/app/knowledge/page.tsx b/frontend/src/app/knowledge/page.tsx
index 1b8b60ef..64eeb49c 100644
--- a/frontend/src/app/knowledge/page.tsx
+++ b/frontend/src/app/knowledge/page.tsx
@@ -1,236 +1,284 @@
 "use client";
 
-import type { ColDef } from "ag-grid-community";
+import type { ColDef, GetRowIdParams } from "ag-grid-community";
 import { AgGridReact, type CustomCellRendererProps } from "ag-grid-react";
 import { Building2, Cloud, HardDrive, Search, Trash2, X } from "lucide-react";
 import { useRouter } from "next/navigation";
-import { type ChangeEvent, useCallback, useRef, useState } from "react";
+import {
+	type ChangeEvent,
+	useCallback,
+	useEffect,
+	useRef,
+	useState,
+} from "react";
 import { SiGoogledrive } from "react-icons/si";
 import { TbBrandOnedrive } from "react-icons/tb";
 import { KnowledgeDropdown } from "@/components/knowledge-dropdown";
 import { ProtectedRoute } from "@/components/protected-route";
 import { Button } from "@/components/ui/button";
 import { useKnowledgeFilter } from "@/contexts/knowledge-filter-context";
+import { useLayout } from "@/contexts/layout-context";
 import { useTask } from "@/contexts/task-context";
 import { type File, useGetSearchQuery } from "../api/queries/useGetSearchQuery";
 import "@/components/AgGrid/registerAgGridModules";
 import "@/components/AgGrid/agGridStyles.css";
 import { toast } from "sonner";
 import { KnowledgeActionsDropdown } from "@/components/knowledge-actions-dropdown";
+import { filterAccentClasses } from "@/components/knowledge-filter-panel";
 import { StatusBadge } from "@/components/ui/status-badge";
 import { DeleteConfirmationDialog } from "../../../components/confirmation-dialog";
 import { useDeleteDocument } from "../api/mutations/useDeleteDocument";
-import { filterAccentClasses } from "@/components/knowledge-filter-panel";
 
 // Function to get the appropriate icon for a connector type
 function getSourceIcon(connectorType?: string) {
-  switch (connectorType) {
-    case "google_drive":
-      return (
-        <SiGoogledrive className="h-4 w-4 text-foreground flex-shrink-0" />
-      );
-    case "onedrive":
-      return (
-        <TbBrandOnedrive className="h-4 w-4 text-foreground flex-shrink-0" />
-      );
-    case "sharepoint":
-      return <Building2 className="h-4 w-4 text-foreground flex-shrink-0" />;
-    case "s3":
-      return <Cloud className="h-4 w-4 text-foreground flex-shrink-0" />;
-    default:
-      return (
-        <HardDrive className="h-4 w-4 text-muted-foreground flex-shrink-0" />
-      );
-  }
+	switch (connectorType) {
+		case "google_drive":
+			return (
+				<SiGoogledrive className="h-4 w-4 text-foreground flex-shrink-0" />
+			);
+		case "onedrive":
+			return (
+				<TbBrandOnedrive className="h-4 w-4 text-foreground flex-shrink-0" />
+			);
+		case "sharepoint":
+			return <Building2 className="h-4 w-4 text-foreground flex-shrink-0" />;
+		case "s3":
+			return <Cloud className="h-4 w-4 text-foreground flex-shrink-0" />;
+		default:
+			return (
+				<HardDrive className="h-4 w-4 text-muted-foreground flex-shrink-0" />
+			);
+	}
 }
 
 function SearchPage() {
-  const router = useRouter();
-  const { isMenuOpen, files: taskFiles } = useTask();
-  const { selectedFilter, setSelectedFilter, parsedFilterData, isPanelOpen } =
-    useKnowledgeFilter();
-  const [selectedRows, setSelectedRows] = useState<File[]>([]);
-  const [showBulkDeleteDialog, setShowBulkDeleteDialog] = useState(false);
+	const router = useRouter();
+	const { isMenuOpen, files: taskFiles, refreshTasks } = useTask();
+  const { totalTopOffset } = useLayout();
+	const { selectedFilter, setSelectedFilter, parsedFilterData, isPanelOpen } =
+		useKnowledgeFilter();
+	const [selectedRows, setSelectedRows] = useState<File[]>([]);
+	const [showBulkDeleteDialog, setShowBulkDeleteDialog] = useState(false);
 
-  const deleteDocumentMutation = useDeleteDocument();
+	const deleteDocumentMutation = useDeleteDocument();
 
-  const { data = [], isFetching } = useGetSearchQuery(
-    parsedFilterData?.query || "*",
-    parsedFilterData
-  );
+	useEffect(() => {
+		refreshTasks();
+	}, [refreshTasks]);
 
-  const handleTableSearch = (e: ChangeEvent<HTMLInputElement>) => {
-    gridRef.current?.api.setGridOption("quickFilterText", e.target.value);
-  };
+	const { data: searchData = [], isFetching } = useGetSearchQuery(
+		parsedFilterData?.query || "*",
+		parsedFilterData,
+	);
+	// Convert TaskFiles to File format and merge with backend results
+	const taskFilesAsFiles: File[] = taskFiles.map((taskFile) => {
+		return {
+			filename: taskFile.filename,
+			mimetype: taskFile.mimetype,
+			source_url: taskFile.source_url,
+			size: taskFile.size,
+			connector_type: taskFile.connector_type,
+			status: taskFile.status,
+		};
+	});
 
-  // Convert TaskFiles to File format and merge with backend results
-  const taskFilesAsFiles: File[] = taskFiles.map((taskFile) => {
-    return {
-      filename: taskFile.filename,
-      mimetype: taskFile.mimetype,
-      source_url: taskFile.source_url,
-      size: taskFile.size,
-      connector_type: taskFile.connector_type,
-      status: taskFile.status,
-    };
-  });
+	// Create a map of task files by filename for quick lookup
+	const taskFileMap = new Map(
+		taskFilesAsFiles.map((file) => [file.filename, file]),
+	);
 
-  const backendFiles = data as File[];
+	// Override backend files with task file status if they exist
+	const backendFiles = (searchData as File[])
+		.map((file) => {
+			const taskFile = taskFileMap.get(file.filename);
+			if (taskFile) {
+				// Override backend file with task file data (includes status)
+				return { ...file, ...taskFile };
+			}
+			return file;
+		})
+		.filter((file) => {
+			// Only filter out files that are currently processing AND in taskFiles
+			const taskFile = taskFileMap.get(file.filename);
+			return !taskFile || taskFile.status !== "processing";
+		});
 
-  const filteredTaskFiles = taskFilesAsFiles.filter((taskFile) => {
-    return (
-      taskFile.status !== "active" &&
-      !backendFiles.some(
-        (backendFile) => backendFile.filename === taskFile.filename
-      )
-    );
-  });
+	const filteredTaskFiles = taskFilesAsFiles.filter((taskFile) => {
+		return (
+			taskFile.status !== "active" &&
+			!backendFiles.some(
+				(backendFile) => backendFile.filename === taskFile.filename,
+			)
+		);
+	});
 
-  // Combine task files first, then backend files
-  const fileResults = [...backendFiles, ...filteredTaskFiles];
+	// Combine task files first, then backend files
+	const fileResults = [...backendFiles, ...filteredTaskFiles];
 
-  const gridRef = useRef<AgGridReact>(null);
+	const handleTableSearch = (e: ChangeEvent<HTMLInputElement>) => {
+		gridRef.current?.api.setGridOption("quickFilterText", e.target.value);
+	};
 
-  const [columnDefs] = useState<ColDef<File>[]>([
-    {
-      field: "filename",
-      headerName: "Source",
-      checkboxSelection: true,
-      headerCheckboxSelection: true,
-      initialFlex: 2,
-      minWidth: 220,
-      cellRenderer: ({ data, value }: CustomCellRendererProps<File>) => {
-        return (
-          <button
-            type="button"
-            className="flex items-center gap-2 cursor-pointer hover:text-blue-600 transition-colors text-left w-full"
-            onClick={() => {
-              router.push(
-                `/knowledge/chunks?filename=${encodeURIComponent(
-                  data?.filename ?? ""
-                )}`
-              );
-            }}
-          >
-            {getSourceIcon(data?.connector_type)}
-            <span className="font-medium text-foreground truncate">
-              {value}
-            </span>
-          </button>
-        );
-      },
-    },
-    {
-      field: "size",
-      headerName: "Size",
-      valueFormatter: (params) =>
-        params.value ? `${Math.round(params.value / 1024)} KB` : "-",
-    },
-    {
-      field: "mimetype",
-      headerName: "Type",
-    },
-    {
-      field: "owner",
-      headerName: "Owner",
-      valueFormatter: (params) =>
-        params.data?.owner_name || params.data?.owner_email || "—",
-    },
-    {
-      field: "chunkCount",
-      headerName: "Chunks",
-      valueFormatter: (params) => params.data?.chunkCount?.toString() || "-",
-    },
-    {
-      field: "avgScore",
-      headerName: "Avg score",
-      initialFlex: 0.5,
-      cellRenderer: ({ value }: CustomCellRendererProps<File>) => {
-        return (
-          <span className="text-xs text-accent-emerald-foreground bg-accent-emerald px-2 py-1 rounded">
-            {value?.toFixed(2) ?? "-"}
-          </span>
-        );
-      },
-    },
-    {
-      field: "status",
-      headerName: "Status",
-      cellRenderer: ({ data }: CustomCellRendererProps<File>) => {
-        // Default to 'active' status if no status is provided
-        const status = data?.status || "active";
-        return <StatusBadge status={status} />;
-      },
-    },
-    {
-      cellRenderer: ({ data }: CustomCellRendererProps<File>) => {
-        return <KnowledgeActionsDropdown filename={data?.filename || ""} />;
-      },
-      cellStyle: {
-        alignItems: "center",
-        display: "flex",
-        justifyContent: "center",
-        padding: 0,
-      },
-      colId: "actions",
-      filter: false,
-      minWidth: 0,
-      width: 40,
-      resizable: false,
-      sortable: false,
-      initialFlex: 0,
-    },
-  ]);
+	const gridRef = useRef<AgGridReact>(null);
 
-  const defaultColDef: ColDef<File> = {
-    resizable: false,
-    suppressMovable: true,
-    initialFlex: 1,
-    minWidth: 100,
-  };
+	const columnDefs = [
+		{
+			field: "filename",
+			headerName: "Source",
+			checkboxSelection: (params: CustomCellRendererProps<File>) =>
+				(params?.data?.status || "active") === "active",
+			headerCheckboxSelection: true,
+			initialFlex: 2,
+			minWidth: 220,
+			cellRenderer: ({ data, value }: CustomCellRendererProps<File>) => {
+				// Read status directly from data on each render
+				const status = data?.status || "active";
+				const isActive = status === "active";
+				console.log(data?.filename, status, "a");
+				return (
+					<div className="flex items-center overflow-hidden w-full">
+						<div
+							className={`transition-opacity duration-200 ${isActive ? "w-0" : "w-7"}`}
+						></div>
+						<button
+							type="button"
+							className="flex items-center gap-2 cursor-pointer hover:text-blue-600 transition-colors text-left flex-1 overflow-hidden"
+							onClick={() => {
+								if (!isActive) {
+									return;
+								}
+								router.push(
+									`/knowledge/chunks?filename=${encodeURIComponent(
+										data?.filename ?? "",
+									)}`,
+								);
+							}}
+						>
+							{getSourceIcon(data?.connector_type)}
+							<span className="font-medium text-foreground truncate">
+								{value}
+							</span>
+						</button>
+					</div>
+				);
+			},
+		},
+		{
+			field: "size",
+			headerName: "Size",
+			valueFormatter: (params: CustomCellRendererProps<File>) =>
+				params.value ? `${Math.round(params.value / 1024)} KB` : "-",
+		},
+		{
+			field: "mimetype",
+			headerName: "Type",
+		},
+		{
+			field: "owner",
+			headerName: "Owner",
+			valueFormatter: (params: CustomCellRendererProps<File>) =>
+				params.data?.owner_name || params.data?.owner_email || "—",
+		},
+		{
+			field: "chunkCount",
+			headerName: "Chunks",
+			valueFormatter: (params: CustomCellRendererProps<File>) => params.data?.chunkCount?.toString() || "-",
+		},
+		{
+			field: "avgScore",
+			headerName: "Avg score",
+			initialFlex: 0.5,
+			cellRenderer: ({ value }: CustomCellRendererProps<File>) => {
+				return (
+					<span className="text-xs text-accent-emerald-foreground bg-accent-emerald px-2 py-1 rounded">
+						{value?.toFixed(2) ?? "-"}
+					</span>
+				);
+			},
+		},
+		{
+			field: "status",
+			headerName: "Status",
+			cellRenderer: ({ data }: CustomCellRendererProps<File>) => {
+				console.log(data?.filename, data?.status, "b");
+				// Default to 'active' status if no status is provided
+				const status = data?.status || "active";
+				return <StatusBadge status={status} />;
+			},
+		},
+		{
+			cellRenderer: ({ data }: CustomCellRendererProps<File>) => {
+				const status = data?.status || "active";
+				if (status !== "active") {
+					return null;
+				}
+				return <KnowledgeActionsDropdown filename={data?.filename || ""} />;
+			},
+			cellStyle: {
+				alignItems: "center",
+				display: "flex",
+				justifyContent: "center",
+				padding: 0,
+			},
+			colId: "actions",
+			filter: false,
+			minWidth: 0,
+			width: 40,
+			resizable: false,
+			sortable: false,
+			initialFlex: 0,
+		},
+	];
 
-  const onSelectionChanged = useCallback(() => {
-    if (gridRef.current) {
-      const selectedNodes = gridRef.current.api.getSelectedRows();
-      setSelectedRows(selectedNodes);
-    }
-  }, []);
+	const defaultColDef: ColDef<File> = {
+		resizable: false,
+		suppressMovable: true,
+		initialFlex: 1,
+		minWidth: 100,
+	};
 
-  const handleBulkDelete = async () => {
-    if (selectedRows.length === 0) return;
+	const onSelectionChanged = useCallback(() => {
+		if (gridRef.current) {
+			const selectedNodes = gridRef.current.api.getSelectedRows();
+			setSelectedRows(selectedNodes);
+		}
+	}, []);
 
-    try {
-      // Delete each file individually since the API expects one filename at a time
-      const deletePromises = selectedRows.map((row) =>
-        deleteDocumentMutation.mutateAsync({ filename: row.filename })
-      );
+	const handleBulkDelete = async () => {
+		if (selectedRows.length === 0) return;
 
-      await Promise.all(deletePromises);
+		try {
+			// Delete each file individually since the API expects one filename at a time
+			const deletePromises = selectedRows.map((row) =>
+				deleteDocumentMutation.mutateAsync({ filename: row.filename }),
+			);
 
-      toast.success(
-        `Successfully deleted ${selectedRows.length} document${
-          selectedRows.length > 1 ? "s" : ""
-        }`
-      );
-      setSelectedRows([]);
-      setShowBulkDeleteDialog(false);
+			await Promise.all(deletePromises);
 
-      // Clear selection in the grid
-      if (gridRef.current) {
-        gridRef.current.api.deselectAll();
-      }
-    } catch (error) {
-      toast.error(
-        error instanceof Error
-          ? error.message
-          : "Failed to delete some documents"
-      );
-    }
-  };
+			toast.success(
+				`Successfully deleted ${selectedRows.length} document${
+					selectedRows.length > 1 ? "s" : ""
+				}`,
+			);
+			setSelectedRows([]);
+			setShowBulkDeleteDialog(false);
+
+			// Clear selection in the grid
+			if (gridRef.current) {
+				gridRef.current.api.deselectAll();
+			}
+		} catch (error) {
+			toast.error(
+				error instanceof Error
+					? error.message
+					: "Failed to delete some documents",
+			);
+		}
+	};
 
   return (
     <div
-      className={`fixed inset-0 md:left-72 top-[53px] flex flex-col transition-all duration-300 ${
+      className={`fixed inset-0 md:left-72 flex flex-col transition-all duration-300 ${
         isMenuOpen && isPanelOpen
           ? "md:right-[704px]"
           : // Both open: 384px (menu) + 320px (KF panel)
@@ -242,6 +290,7 @@ function SearchPage() {
           : // Only KF panel open: 320px
             "md:right-6" // Neither open: 24px
       }`}
+      style={{ top: `${totalTopOffset}px` }}
     >
       <div className="flex-1 flex flex-col min-h-0 px-6 py-6">
         <div className="flex items-center justify-between mb-6">
@@ -249,38 +298,37 @@ function SearchPage() {
           <KnowledgeDropdown variant="button" />
         </div>
 
-        {/* Search Input Area */}
-        <div className="flex-shrink-0 mb-6 xl:max-w-[75%]">
-          <form className="flex gap-3">
-            <div className="primary-input min-h-10 !flex items-center flex-nowrap focus-within:border-foreground transition-colors !p-[0.3rem]">
-              {selectedFilter?.name && (
-                <div
-                  className={`flex items-center gap-1 h-full px-1.5 py-0.5 mr-1 rounded max-w-[25%] ${
-                    filterAccentClasses[parsedFilterData?.color || "zinc"]
-                  }`}
-                >
-                  <span className="truncate">{selectedFilter?.name}</span>
-                  <X
-                    aria-label="Remove filter"
-                    className="h-4 w-4 flex-shrink-0 cursor-pointer"
-                    onClick={() => setSelectedFilter(null)}
-                  />
-                </div>
-              )}
-              <Search
-                className="h-4 w-4 ml-1 flex-shrink-0 text-placeholder-foreground"
-                strokeWidth={1.5}
-              />
-              <input
-                className="bg-transparent w-full h-full ml-2 focus:outline-none focus-visible:outline-none font-mono placeholder:font-mono"
-                name="search-query"
-                id="search-query"
-                type="text"
-                placeholder="Search your documents..."
-                onChange={handleTableSearch}
-              />
-            </div>
-            {/* <Button
+				{/* Search Input Area */}
+				<div className="flex-shrink-0 mb-6 xl:max-w-[75%]">
+					<form className="flex gap-3">
+						<div className="primary-input min-h-10 !flex items-center flex-nowrap focus-within:border-foreground transition-colors !p-[0.3rem]">
+							{selectedFilter?.name && (
+								<div
+									className={`flex items-center gap-1 h-full px-1.5 py-0.5 mr-1 rounded max-w-[25%] ${
+										filterAccentClasses[parsedFilterData?.color || "zinc"]
+									}`}
+								>
+									<span className="truncate">{selectedFilter?.name}</span>
+									<X
+										aria-label="Remove filter"
+										className="h-4 w-4 flex-shrink-0 cursor-pointer"
+										onClick={() => setSelectedFilter(null)}
+									/>
+								</div>
+							)}
+							<Search
+								className="h-4 w-4 ml-1 flex-shrink-0 text-placeholder-foreground"
+							/>
+							<input
+								className="bg-transparent w-full h-full ml-2 focus:outline-none focus-visible:outline-none font-mono placeholder:font-mono"
+								name="search-query"
+								id="search-query"
+								type="text"
+								placeholder="Enter your search query..."
+								onChange={handleTableSearch}
+							/>
+						</div>
+						{/* <Button
               type="submit"
               variant="outline"
               className="rounded-lg p-0 flex-shrink-0"
@@ -291,8 +339,8 @@ function SearchPage() {
                 <Search className="h-4 w-4" />
               )}
             </Button> */}
-            {/* //TODO: Implement sync button */}
-            {/* <Button
+						{/* //TODO: Implement sync button */}
+						{/* <Button
               type="button"
               variant="outline"
               className="rounded-lg flex-shrink-0"
@@ -300,69 +348,69 @@ function SearchPage() {
             >
               Sync
             </Button> */}
-            {selectedRows.length > 0 && (
-              <Button
-                type="button"
-                variant="destructive"
-                className="rounded-lg flex-shrink-0"
-                onClick={() => setShowBulkDeleteDialog(true)}
-              >
-                <Trash2 className="h-4 w-4" /> Delete
-              </Button>
-            )}
-          </form>
-        </div>
-        <AgGridReact
-          className="w-full overflow-auto"
-          columnDefs={columnDefs}
-          defaultColDef={defaultColDef}
-          loading={isFetching}
-          ref={gridRef}
-          rowData={fileResults}
-          rowSelection="multiple"
-          rowMultiSelectWithClick={false}
-          suppressRowClickSelection={true}
-          getRowId={(params) => params.data.filename}
-          domLayout="normal"
-          onSelectionChanged={onSelectionChanged}
-          noRowsOverlayComponent={() => (
-            <div className="text-center pb-[45px]">
-              <div className="text-lg text-primary font-semibold">
-                No knowledge
-              </div>
-              <div className="text-sm mt-1 text-muted-foreground">
-                Add files from local or your preferred cloud.
-              </div>
-            </div>
-          )}
-        />
-      </div>
+						{selectedRows.length > 0 && (
+							<Button
+								type="button"
+								variant="destructive"
+								className="rounded-lg flex-shrink-0"
+								onClick={() => setShowBulkDeleteDialog(true)}
+							>
+								<Trash2 className="h-4 w-4" /> Delete
+							</Button>
+						)}
+					</form>
+				</div>
+				<AgGridReact
+					className="w-full overflow-auto"
+					columnDefs={columnDefs as ColDef<File>[]}
+					defaultColDef={defaultColDef}
+					loading={isFetching}
+					ref={gridRef}
+					rowData={fileResults}
+					rowSelection="multiple"
+					rowMultiSelectWithClick={false}
+					suppressRowClickSelection={true}
+					getRowId={(params: GetRowIdParams<File>) => params.data?.filename}
+					domLayout="normal"
+					onSelectionChanged={onSelectionChanged}
+					noRowsOverlayComponent={() => (
+						<div className="text-center pb-[45px]">
+							<div className="text-lg text-primary font-semibold">
+								No knowledge
+							</div>
+							<div className="text-sm mt-1 text-muted-foreground">
+								Add files from local or your preferred cloud.
+							</div>
+						</div>
+					)}
+				/>
+			</div>
 
-      {/* Bulk Delete Confirmation Dialog */}
-      <DeleteConfirmationDialog
-        open={showBulkDeleteDialog}
-        onOpenChange={setShowBulkDeleteDialog}
-        title="Delete Documents"
-        description={`Are you sure you want to delete ${
-          selectedRows.length
-        } document${
-          selectedRows.length > 1 ? "s" : ""
-        }? This will remove all chunks and data associated with these documents. This action cannot be undone.
+			{/* Bulk Delete Confirmation Dialog */}
+			<DeleteConfirmationDialog
+				open={showBulkDeleteDialog}
+				onOpenChange={setShowBulkDeleteDialog}
+				title="Delete Documents"
+				description={`Are you sure you want to delete ${
+					selectedRows.length
+				} document${
+					selectedRows.length > 1 ? "s" : ""
+				}? This will remove all chunks and data associated with these documents. This action cannot be undone.
 
 Documents to be deleted:
 ${selectedRows.map((row) => `• ${row.filename}`).join("\n")}`}
-        confirmText="Delete All"
-        onConfirm={handleBulkDelete}
-        isLoading={deleteDocumentMutation.isPending}
-      />
-    </div>
-  );
+				confirmText="Delete All"
+				onConfirm={handleBulkDelete}
+				isLoading={deleteDocumentMutation.isPending}
+			/>
+		</div>
+	);
 }
 
 export default function ProtectedSearchPage() {
-  return (
-    <ProtectedRoute>
-      <SearchPage />
-    </ProtectedRoute>
-  );
+	return (
+		<ProtectedRoute>
+			<SearchPage />
+		</ProtectedRoute>
+	);
 }
diff --git a/frontend/src/app/settings/page.tsx b/frontend/src/app/settings/page.tsx
index 514b12d5..a4101535 100644
--- a/frontend/src/app/settings/page.tsx
+++ b/frontend/src/app/settings/page.tsx
@@ -149,7 +149,7 @@ function KnowledgeSourcesPage() {
 	const [systemPrompt, setSystemPrompt] = useState<string>("");
 	const [chunkSize, setChunkSize] = useState<number>(1024);
 	const [chunkOverlap, setChunkOverlap] = useState<number>(50);
-	const [tableStructure, setTableStructure] = useState<boolean>(false);
+	const [tableStructure, setTableStructure] = useState<boolean>(true);
 	const [ocr, setOcr] = useState<boolean>(false);
 	const [pictureDescriptions, setPictureDescriptions] =
 		useState<boolean>(false);
diff --git a/frontend/src/components/layout-wrapper.tsx b/frontend/src/components/layout-wrapper.tsx
index cb0794e0..79417654 100644
--- a/frontend/src/components/layout-wrapper.tsx
+++ b/frontend/src/components/layout-wrapper.tsx
@@ -7,6 +7,7 @@ import {
   type ChatConversation,
 } from "@/app/api/queries/useGetConversationsQuery";
 import { useGetSettingsQuery } from "@/app/api/queries/useGetSettingsQuery";
+import { DoclingHealthBanner } from "@/components/docling-health-banner";
 import { KnowledgeFilterPanel } from "@/components/knowledge-filter-panel";
 import Logo from "@/components/logo/logo";
 import { Navigation } from "@/components/navigation";
@@ -16,9 +17,11 @@ import { UserNav } from "@/components/user-nav";
 import { useAuth } from "@/contexts/auth-context";
 import { useChat } from "@/contexts/chat-context";
 import { useKnowledgeFilter } from "@/contexts/knowledge-filter-context";
+import { LayoutProvider } from "@/contexts/layout-context";
 // import { GitHubStarButton } from "@/components/github-star-button"
 // import { DiscordLink } from "@/components/discord-link"
 import { useTask } from "@/contexts/task-context";
+import { useDoclingHealthQuery } from "@/src/app/api/queries/useDoclingHealthQuery";
 import { cn } from "@/lib/utils";
 
 export function LayoutWrapper({ children }: { children: React.ReactNode }) {
@@ -35,6 +38,11 @@ export function LayoutWrapper({ children }: { children: React.ReactNode }) {
   const { isLoading: isSettingsLoading, data: settings } = useGetSettingsQuery({
     enabled: isAuthenticated || isNoAuthMode,
   });
+  const {
+    data: health,
+    isLoading: isHealthLoading,
+    isError,
+  } = useDoclingHealthQuery();
 
   // Only fetch conversations on chat page
   const isOnChatPage = pathname === "/" || pathname === "/chat";
@@ -64,6 +72,17 @@ export function LayoutWrapper({ children }: { children: React.ReactNode }) {
       task.status === "processing"
   );
 
+  const isUnhealthy = health?.status === "unhealthy" || isError;
+  const isBannerVisible = !isHealthLoading && isUnhealthy;
+
+  // Dynamic height calculations based on banner visibility
+  const headerHeight = 53;
+  const bannerHeight = 52; // Approximate banner height
+  const totalTopOffset = isBannerVisible
+    ? headerHeight + bannerHeight
+    : headerHeight;
+  const mainContentHeight = `calc(100vh - ${totalTopOffset}px)`;
+
   // Show loading state when backend isn't ready
   if (isLoading || isSettingsLoading) {
     return (
@@ -76,7 +95,7 @@ export function LayoutWrapper({ children }: { children: React.ReactNode }) {
     );
   }
 
-  if (isAuthPage || (settings && !settings.edited)) {
+  if (isAuthPage) {
     // For auth pages, render without navigation
     return <div className="h-full">{children}</div>;
   }
@@ -84,6 +103,7 @@ export function LayoutWrapper({ children }: { children: React.ReactNode }) {
   // For all other pages, render with Langflow-styled navigation and task menu
   return (
     <div className="h-full relative">
+      <DoclingHealthBanner className="w-full pt-2" />
       <header className="header-arrangement bg-background sticky top-0 z-50 h-10">
         <div className="header-start-display px-[16px]">
           {/* Logo/Title */}
@@ -124,7 +144,10 @@ export function LayoutWrapper({ children }: { children: React.ReactNode }) {
           </div>
         </div>
       </header>
-      <div className="side-bar-arrangement bg-background fixed left-0 top-[40px] bottom-0 md:flex hidden pt-1">
+      <div
+        className="side-bar-arrangement bg-background fixed left-0 top-[40px] bottom-0 md:flex hidden pt-1"
+        style={{ top: `${totalTopOffset}px` }}
+      >
         <Navigation
           conversations={conversations}
           isConversationsLoading={isConversationsLoading}
@@ -132,7 +155,7 @@ export function LayoutWrapper({ children }: { children: React.ReactNode }) {
         />
       </div>
       <main
-        className={`md:pl-72 transition-all duration-300 overflow-y-auto h-[calc(100vh-53px)] ${
+        className={`md:pl-72 transition-all duration-300 overflow-y-auto ${
           isMenuOpen && isPanelOpen
             ? "md:pr-[728px]"
             : // Both open: 384px (menu) + 320px (KF panel) + 24px (original padding)
@@ -144,15 +167,21 @@ export function LayoutWrapper({ children }: { children: React.ReactNode }) {
             : // Only KF panel open: 320px
               "md:pr-0" // Neither open: 24px
         }`}
+        style={{ height: mainContentHeight }}
       >
-        <div
-          className={cn(
-            "py-6 lg:py-8 px-4 lg:px-6",
-            isSmallWidthPath ? "max-w-[850px]" : "container"
-          )}
+        <LayoutProvider
+          headerHeight={headerHeight}
+          totalTopOffset={totalTopOffset}
         >
-          {children}
-        </div>
+          <div
+            className={cn(
+              "py-6 lg:py-8 px-4 lg:px-6",
+              isSmallWidthPath ? "max-w-[850px]" : "container"
+            )}
+          >
+            {children}
+          </div>
+        </LayoutProvider>
       </main>
       <TaskNotificationMenu />
       <KnowledgeFilterPanel />
diff --git a/frontend/src/components/task-notification-menu.tsx b/frontend/src/components/task-notification-menu.tsx
index e17f9579..fed7e6f1 100644
--- a/frontend/src/components/task-notification-menu.tsx
+++ b/frontend/src/components/task-notification-menu.tsx
@@ -1,6 +1,6 @@
 "use client"
 
-import { useState } from 'react'
+import { useEffect, useState } from 'react'
 import { Bell, CheckCircle, XCircle, Clock, Loader2, ChevronDown, ChevronUp, X } from 'lucide-react'
 import { Button } from '@/components/ui/button'
 import { Card, CardContent, CardDescription, CardHeader, CardTitle } from '@/components/ui/card'
@@ -8,9 +8,16 @@ import { Badge } from '@/components/ui/badge'
 import { useTask, Task } from '@/contexts/task-context'
 
 export function TaskNotificationMenu() {
-  const { tasks, isFetching, isMenuOpen, cancelTask } = useTask()
+  const { tasks, isFetching, isMenuOpen, isRecentTasksExpanded, cancelTask } = useTask()
   const [isExpanded, setIsExpanded] = useState(false)
 
+  // Sync local state with context state
+  useEffect(() => {
+    if (isRecentTasksExpanded) {
+      setIsExpanded(true)
+    }
+  }, [isRecentTasksExpanded])
+
   // Don't render if menu is closed
   if (!isMenuOpen) return null
 
diff --git a/frontend/src/components/ui/animated-processing-icon.tsx b/frontend/src/components/ui/animated-processing-icon.tsx
index eb36b2ab..51815414 100644
--- a/frontend/src/components/ui/animated-processing-icon.tsx
+++ b/frontend/src/components/ui/animated-processing-icon.tsx
@@ -1,26 +1,16 @@
-interface AnimatedProcessingIconProps {
-  className?: string;
-  size?: number;
-}
+import type { SVGProps } from "react";
 
-export const AnimatedProcessingIcon = ({
-  className = "",
-  size = 10,
-}: AnimatedProcessingIconProps) => {
-  const width = Math.round((size * 6) / 10);
-  const height = size;
-
-  return (
-    <svg
-      width={width}
-      height={height}
-      viewBox="0 0 6 10"
-      fill="none"
-      xmlns="http://www.w3.org/2000/svg"
-      className={className}
-    >
-      <style>
-        {`
+export const AnimatedProcessingIcon = (props: SVGProps<SVGSVGElement>) => {
+	return (
+		<svg
+			viewBox="0 0 8 12"
+			fill="none"
+			xmlns="http://www.w3.org/2000/svg"
+			{...props}
+		>
+			<title>Processing</title>
+			<style>
+				{`
           .dot-1 { animation: pulse-wave 1.5s infinite; animation-delay: 0s; }
           .dot-2 { animation: pulse-wave 1.5s infinite; animation-delay: 0.1s; }
           .dot-3 { animation: pulse-wave 1.5s infinite; animation-delay: 0.2s; }
@@ -30,20 +20,18 @@ export const AnimatedProcessingIcon = ({
           @keyframes pulse-wave {
             0%, 60%, 100% { 
               opacity: 0.25; 
-              transform: scale(1);
             }
             30% { 
               opacity: 1; 
-              transform: scale(1.2);
             }
           }
         `}
-      </style>
-      <circle className="dot-1" cx="1" cy="5" r="1" fill="currentColor" />
-      <circle className="dot-2" cx="1" cy="9" r="1" fill="currentColor" />
-      <circle className="dot-3" cx="5" cy="1" r="1" fill="currentColor" />
-      <circle className="dot-4" cx="5" cy="5" r="1" fill="currentColor" />
-      <circle className="dot-5" cx="5" cy="9" r="1" fill="currentColor" />
-    </svg>
-  );
+			</style>
+			<circle className="dot-1" cx="2" cy="6" r="1" fill="currentColor" />
+			<circle className="dot-2" cx="2" cy="10" r="1" fill="currentColor" />
+			<circle className="dot-3" cx="6" cy="2" r="1" fill="currentColor" />
+			<circle className="dot-4" cx="6" cy="6" r="1" fill="currentColor" />
+			<circle className="dot-5" cx="6" cy="10" r="1" fill="currentColor" />
+		</svg>
+	);
 };
diff --git a/frontend/src/components/ui/status-badge.tsx b/frontend/src/components/ui/status-badge.tsx
index d3b1a323..e57ad3b5 100644
--- a/frontend/src/components/ui/status-badge.tsx
+++ b/frontend/src/components/ui/status-badge.tsx
@@ -50,7 +50,7 @@ export const StatusBadge = ({ status, className }: StatusBadgeProps) => {
       }`}
     >
       {status === "processing" && (
-        <AnimatedProcessingIcon className="text-current mr-2" size={10} />
+        <AnimatedProcessingIcon className="text-current h-3 w-3 shrink-0" />
       )}
       {config.label}
     </div>
diff --git a/frontend/src/contexts/layout-context.tsx b/frontend/src/contexts/layout-context.tsx
new file mode 100644
index 00000000..f40ea28c
--- /dev/null
+++ b/frontend/src/contexts/layout-context.tsx
@@ -0,0 +1,34 @@
+"use client";
+
+import { createContext, useContext } from "react";
+
+interface LayoutContextType {
+  headerHeight: number;
+  totalTopOffset: number;
+}
+
+const LayoutContext = createContext<LayoutContextType | undefined>(undefined);
+
+export function useLayout() {
+  const context = useContext(LayoutContext);
+  if (context === undefined) {
+    throw new Error("useLayout must be used within a LayoutProvider");
+  }
+  return context;
+}
+
+export function LayoutProvider({
+  children,
+  headerHeight,
+  totalTopOffset
+}: {
+  children: React.ReactNode;
+  headerHeight: number;
+  totalTopOffset: number;
+}) {
+  return (
+    <LayoutContext.Provider value={{ headerHeight, totalTopOffset }}>
+      {children}
+    </LayoutContext.Provider>
+  );
+}
\ No newline at end of file
diff --git a/frontend/src/contexts/task-context.tsx b/frontend/src/contexts/task-context.tsx
index 5eb10ea9..12ad3c24 100644
--- a/frontend/src/contexts/task-context.tsx
+++ b/frontend/src/contexts/task-context.tsx
@@ -7,33 +7,18 @@ import {
   useCallback,
   useContext,
   useEffect,
+  useRef,
   useState,
 } from "react";
 import { toast } from "sonner";
+import { useCancelTaskMutation } from "@/app/api/mutations/useCancelTaskMutation";
+import {
+  type Task,
+  useGetTasksQuery,
+} from "@/app/api/queries/useGetTasksQuery";
 import { useAuth } from "@/contexts/auth-context";
 
-export interface Task {
-  task_id: string;
-  status:
-    | "pending"
-    | "running"
-    | "processing"
-    | "completed"
-    | "failed"
-    | "error";
-  total_files?: number;
-  processed_files?: number;
-  successful_files?: number;
-  failed_files?: number;
-  running_files?: number;
-  pending_files?: number;
-  created_at: string;
-  updated_at: string;
-  duration_seconds?: number;
-  result?: Record<string, unknown>;
-  error?: string;
-  files?: Record<string, Record<string, unknown>>;
-}
+// Task interface is now imported from useGetTasksQuery
 
 export interface TaskFile {
   filename: string;
@@ -51,27 +36,54 @@ interface TaskContextType {
   files: TaskFile[];
   addTask: (taskId: string) => void;
   addFiles: (files: Partial<TaskFile>[], taskId: string) => void;
-  removeTask: (taskId: string) => void;
   refreshTasks: () => Promise<void>;
   cancelTask: (taskId: string) => Promise<void>;
   isPolling: boolean;
   isFetching: boolean;
   isMenuOpen: boolean;
   toggleMenu: () => void;
+  isRecentTasksExpanded: boolean;
+  setRecentTasksExpanded: (expanded: boolean) => void;
+  // React Query states
+  isLoading: boolean;
+  error: Error | null;
 }
 
 const TaskContext = createContext<TaskContextType | undefined>(undefined);
 
 export function TaskProvider({ children }: { children: React.ReactNode }) {
-  const [tasks, setTasks] = useState<Task[]>([]);
   const [files, setFiles] = useState<TaskFile[]>([]);
-  const [isPolling, setIsPolling] = useState(false);
-  const [isFetching, setIsFetching] = useState(false);
   const [isMenuOpen, setIsMenuOpen] = useState(false);
+  const [isRecentTasksExpanded, setIsRecentTasksExpanded] = useState(false);
+  const previousTasksRef = useRef<Task[]>([]);
   const { isAuthenticated, isNoAuthMode } = useAuth();
 
   const queryClient = useQueryClient();
 
+  // Use React Query hooks
+  const {
+    data: tasks = [],
+    isLoading,
+    error,
+    refetch: refetchTasks,
+    isFetching,
+  } = useGetTasksQuery({
+    enabled: isAuthenticated || isNoAuthMode,
+  });
+
+  const cancelTaskMutation = useCancelTaskMutation({
+    onSuccess: () => {
+      toast.success("Task cancelled", {
+        description: "Task has been cancelled successfully",
+      });
+    },
+    onError: (error) => {
+      toast.error("Failed to cancel task", {
+        description: error.message,
+      });
+    },
+  });
+
   const refetchSearch = useCallback(() => {
     queryClient.invalidateQueries({
       queryKey: ["search"],
@@ -99,265 +111,216 @@ export function TaskProvider({ children }: { children: React.ReactNode }) {
     [],
   );
 
-  const fetchTasks = useCallback(async () => {
-    if (!isAuthenticated && !isNoAuthMode) return;
-
-    setIsFetching(true);
-    try {
-      const response = await fetch("/api/tasks");
-      if (response.ok) {
-        const data = await response.json();
-        const newTasks = data.tasks || [];
-
-        // Update tasks and check for status changes in the same state update
-        setTasks((prevTasks) => {
-          // Check for newly completed tasks to show toasts
-          if (prevTasks.length > 0) {
-            newTasks.forEach((newTask: Task) => {
-              const oldTask = prevTasks.find(
-                (t) => t.task_id === newTask.task_id,
-              );
-
-              // Update or add files from task.files if available
-              if (newTask.files && typeof newTask.files === "object") {
-                const taskFileEntries = Object.entries(newTask.files);
-                const now = new Date().toISOString();
-
-                taskFileEntries.forEach(([filePath, fileInfo]) => {
-                  if (typeof fileInfo === "object" && fileInfo) {
-                    const fileName = filePath.split("/").pop() || filePath;
-                    const fileStatus = fileInfo.status as string;
-
-                    // Map backend file status to our TaskFile status
-                    let mappedStatus: TaskFile["status"];
-                    switch (fileStatus) {
-                      case "pending":
-                      case "running":
-                        mappedStatus = "processing";
-                        break;
-                      case "completed":
-                        mappedStatus = "active";
-                        break;
-                      case "failed":
-                        mappedStatus = "failed";
-                        break;
-                      default:
-                        mappedStatus = "processing";
-                    }
-
-                    setFiles((prevFiles) => {
-                      const existingFileIndex = prevFiles.findIndex(
-                        (f) =>
-                          f.source_url === filePath &&
-                          f.task_id === newTask.task_id,
-                      );
-
-                      // Detect connector type based on file path or other indicators
-                      let connectorType = "local";
-                      if (filePath.includes("/") && !filePath.startsWith("/")) {
-                        // Likely S3 key format (bucket/path/file.ext)
-                        connectorType = "s3";
-                      }
-
-                      const fileEntry: TaskFile = {
-                        filename: fileName,
-                        mimetype: "", // We don't have this info from the task
-                        source_url: filePath,
-                        size: 0, // We don't have this info from the task
-                        connector_type: connectorType,
-                        status: mappedStatus,
-                        task_id: newTask.task_id,
-                        created_at:
-                          typeof fileInfo.created_at === "string"
-                            ? fileInfo.created_at
-                            : now,
-                        updated_at:
-                          typeof fileInfo.updated_at === "string"
-                            ? fileInfo.updated_at
-                            : now,
-                      };
-
-                      if (existingFileIndex >= 0) {
-                        // Update existing file
-                        const updatedFiles = [...prevFiles];
-                        updatedFiles[existingFileIndex] = fileEntry;
-                        return updatedFiles;
-                      } else {
-                        // Add new file
-                        return [...prevFiles, fileEntry];
-                      }
-                    });
-                  }
-                });
-              }
-
-              if (
-                oldTask &&
-                oldTask.status !== "completed" &&
-                newTask.status === "completed"
-              ) {
-                // Task just completed - show success toast
-                toast.success("Task completed successfully", {
-                  description: `Task ${newTask.task_id} has finished processing.`,
-                  action: {
-                    label: "View",
-                    onClick: () => console.log("View task", newTask.task_id),
-                  },
-                });
-                refetchSearch();
-                // Dispatch knowledge updated event for all knowledge-related pages
-                console.log(
-                  "Task completed successfully, dispatching knowledgeUpdated event",
-                );
-                window.dispatchEvent(new CustomEvent("knowledgeUpdated"));
-
-                // Remove files for this completed task from the files list
-                setFiles((prevFiles) =>
-                  prevFiles.filter((file) => file.task_id !== newTask.task_id),
-                );
-              } else if (
-                oldTask &&
-                oldTask.status !== "failed" &&
-                oldTask.status !== "error" &&
-                (newTask.status === "failed" || newTask.status === "error")
-              ) {
-                // Task just failed - show error toast
-                toast.error("Task failed", {
-                  description: `Task ${newTask.task_id} failed: ${
-                    newTask.error || "Unknown error"
-                  }`,
-                });
-
-                // Files will be updated to failed status by the file parsing logic above
-              }
-            });
-          }
-
-          return newTasks;
-        });
-      }
-    } catch (error) {
-      console.error("Failed to fetch tasks:", error);
-    } finally {
-      setIsFetching(false);
+  // Handle task status changes and file updates
+  useEffect(() => {
+    if (tasks.length === 0) {
+      // Store current tasks as previous for next comparison
+      previousTasksRef.current = tasks;
+      return;
     }
-  }, [isAuthenticated, isNoAuthMode, refetchSearch]); // Removed 'tasks' from dependencies to prevent infinite loop!
 
-  const addTask = useCallback((taskId: string) => {
-    // Immediately start aggressive polling for the new task
-    let pollAttempts = 0;
-    const maxPollAttempts = 30; // Poll for up to 30 seconds
+    // Check for task status changes by comparing with previous tasks
+    tasks.forEach((currentTask) => {
+      const previousTask = previousTasksRef.current.find(
+        (prev) => prev.task_id === currentTask.task_id,
+      );
 
-    const aggressivePoll = async () => {
-      try {
-        const response = await fetch("/api/tasks");
-        if (response.ok) {
-          const data = await response.json();
-          const newTasks = data.tasks || [];
-          const foundTask = newTasks.find(
-            (task: Task) => task.task_id === taskId,
-          );
+      // Only show toasts if we have previous data and status has changed
+      if (
+        (previousTask && previousTask.status !== currentTask.status) ||
+        (!previousTask && previousTasksRef.current.length !== 0)
+      ) {
+        // Process files from failed task and add them to files list
+        if (currentTask.files && typeof currentTask.files === "object") {
+          const taskFileEntries = Object.entries(currentTask.files);
+          const now = new Date().toISOString();
 
-          if (foundTask) {
-            // Task found! Update the tasks state
-            setTasks((prevTasks) => {
-              // Check if task is already in the list
-              const exists = prevTasks.some((t) => t.task_id === taskId);
-              if (!exists) {
-                return [...prevTasks, foundTask];
+          taskFileEntries.forEach(([filePath, fileInfo]) => {
+            if (typeof fileInfo === "object" && fileInfo) {
+              // Use the filename from backend if available, otherwise extract from path
+              const fileName =
+                (fileInfo as any).filename ||
+                filePath.split("/").pop() ||
+                filePath;
+              const fileStatus = fileInfo.status as string;
+
+              // Map backend file status to our TaskFile status
+              let mappedStatus: TaskFile["status"];
+              switch (fileStatus) {
+                case "pending":
+                case "running":
+                  mappedStatus = "processing";
+                  break;
+                case "completed":
+                  mappedStatus = "active";
+                  break;
+                case "failed":
+                  mappedStatus = "failed";
+                  break;
+                default:
+                  mappedStatus = "processing";
               }
-              // Update existing task
-              return prevTasks.map((t) =>
-                t.task_id === taskId ? foundTask : t,
-              );
-            });
-            return; // Stop polling, we found it
-          }
+
+              setFiles((prevFiles) => {
+                const existingFileIndex = prevFiles.findIndex(
+                  (f) =>
+                    f.source_url === filePath &&
+                    f.task_id === currentTask.task_id,
+                );
+
+                // Detect connector type based on file path or other indicators
+                let connectorType = "local";
+                if (filePath.includes("/") && !filePath.startsWith("/")) {
+                  // Likely S3 key format (bucket/path/file.ext)
+                  connectorType = "s3";
+                }
+
+                const fileEntry: TaskFile = {
+                  filename: fileName,
+                  mimetype: "", // We don't have this info from the task
+                  source_url: filePath,
+                  size: 0, // We don't have this info from the task
+                  connector_type: connectorType,
+                  status: mappedStatus,
+                  task_id: currentTask.task_id,
+                  created_at:
+                    typeof fileInfo.created_at === "string"
+                      ? fileInfo.created_at
+                      : now,
+                  updated_at:
+                    typeof fileInfo.updated_at === "string"
+                      ? fileInfo.updated_at
+                      : now,
+                };
+
+                if (existingFileIndex >= 0) {
+                  // Update existing file
+                  const updatedFiles = [...prevFiles];
+                  updatedFiles[existingFileIndex] = fileEntry;
+                  return updatedFiles;
+                } else {
+                  // Add new file
+                  return [...prevFiles, fileEntry];
+                }
+              });
+            }
+          });
         }
-      } catch (error) {
-        console.error("Aggressive polling failed:", error);
-      }
+        if (
+          previousTask &&
+          previousTask.status !== "completed" &&
+          currentTask.status === "completed"
+        ) {
+          // Task just completed - show success toast with file counts
+          const successfulFiles = currentTask.successful_files || 0;
+          const failedFiles = currentTask.failed_files || 0;
 
-      pollAttempts++;
-      if (pollAttempts < maxPollAttempts) {
-        // Continue polling every 1 second for new tasks
-        setTimeout(aggressivePoll, 1000);
-      }
-    };
+          let description = "";
+          if (failedFiles > 0) {
+            description = `${successfulFiles} file${
+              successfulFiles !== 1 ? "s" : ""
+            } uploaded successfully, ${failedFiles} file${
+              failedFiles !== 1 ? "s" : ""
+            } failed`;
+          } else {
+            description = `${successfulFiles} file${
+              successfulFiles !== 1 ? "s" : ""
+            } uploaded successfully`;
+          }
 
-    // Start aggressive polling after a short delay to allow backend to process
-    setTimeout(aggressivePoll, 500);
-  }, []);
+          toast.success("Task completed", {
+            description,
+            action: {
+              label: "View",
+              onClick: () => {
+                setIsMenuOpen(true);
+                setIsRecentTasksExpanded(true);
+              },
+            },
+          });
+          setTimeout(() => {
+            setFiles((prevFiles) =>
+              prevFiles.filter(
+                (file) =>
+                  file.task_id !== currentTask.task_id ||
+                  file.status === "failed",
+              ),
+            );
+            refetchSearch();
+          }, 500);
+        } else if (
+          previousTask &&
+          previousTask.status !== "failed" &&
+          previousTask.status !== "error" &&
+          (currentTask.status === "failed" || currentTask.status === "error")
+        ) {
+          // Task just failed - show error toast
+          toast.error("Task failed", {
+            description: `Task ${currentTask.task_id} failed: ${
+              currentTask.error || "Unknown error"
+            }`,
+          });
+        }
+      }
+    });
+
+    // Store current tasks as previous for next comparison
+    previousTasksRef.current = tasks;
+  }, [tasks, refetchSearch]);
+
+  const addTask = useCallback(
+    (_taskId: string) => {
+      // React Query will automatically handle polling when tasks are active
+      // Just trigger a refetch to get the latest data
+      setTimeout(() => {
+        refetchTasks();
+      }, 500);
+    },
+    [refetchTasks],
+  );
 
   const refreshTasks = useCallback(async () => {
-    await fetchTasks();
-  }, [fetchTasks]);
+    setFiles([]);
+    await refetchTasks();
+  }, [refetchTasks]);
 
-  const removeTask = useCallback((taskId: string) => {
-    setTasks((prev) => prev.filter((task) => task.task_id !== taskId));
-  }, []);
 
   const cancelTask = useCallback(
     async (taskId: string) => {
-      try {
-        const response = await fetch(`/api/tasks/${taskId}/cancel`, {
-          method: "POST",
-        });
-
-        if (response.ok) {
-          // Immediately refresh tasks to show the updated status
-          await fetchTasks();
-          toast.success("Task cancelled", {
-            description: `Task ${taskId.substring(0, 8)}... has been cancelled`,
-          });
-        } else {
-          const errorData = await response.json().catch(() => ({}));
-          throw new Error(errorData.error || "Failed to cancel task");
-        }
-      } catch (error) {
-        console.error("Failed to cancel task:", error);
-        toast.error("Failed to cancel task", {
-          description: error instanceof Error ? error.message : "Unknown error",
-        });
-      }
+      cancelTaskMutation.mutate({ taskId });
     },
-    [fetchTasks],
+    [cancelTaskMutation],
   );
 
   const toggleMenu = useCallback(() => {
     setIsMenuOpen((prev) => !prev);
   }, []);
 
-  // Periodic polling for task updates
-  useEffect(() => {
-    if (!isAuthenticated && !isNoAuthMode) return;
-
-    setIsPolling(true);
-
-    // Initial fetch
-    fetchTasks();
-
-    // Set up polling interval - every 3 seconds (more responsive for active tasks)
-    const interval = setInterval(fetchTasks, 3000);
-
-    return () => {
-      clearInterval(interval);
-      setIsPolling(false);
-    };
-  }, [isAuthenticated, isNoAuthMode, fetchTasks]);
+  // Determine if we're polling based on React Query's refetch interval
+  const isPolling =
+    isFetching &&
+    tasks.some(
+      (task) =>
+        task.status === "pending" ||
+        task.status === "running" ||
+        task.status === "processing",
+    );
 
   const value: TaskContextType = {
     tasks,
     files,
     addTask,
     addFiles,
-    removeTask,
     refreshTasks,
     cancelTask,
     isPolling,
     isFetching,
     isMenuOpen,
     toggleMenu,
+    isRecentTasksExpanded,
+    setRecentTasksExpanded: setIsRecentTasksExpanded,
+    isLoading,
+    error,
   };
 
   return <TaskContext.Provider value={value}>{children}</TaskContext.Provider>;
diff --git a/frontend/src/lib/constants.ts b/frontend/src/lib/constants.ts
index 8e7770fb..9ce34634 100644
--- a/frontend/src/lib/constants.ts
+++ b/frontend/src/lib/constants.ts
@@ -12,7 +12,7 @@ export const DEFAULT_AGENT_SETTINGS = {
 export const DEFAULT_KNOWLEDGE_SETTINGS = {
   chunk_size: 1000,
   chunk_overlap: 200,
-  table_structure: false,
+  table_structure: true,
   ocr: false,
   picture_descriptions: false
 } as const;
diff --git a/pyproject.toml b/pyproject.toml
index 759732ea..be8d359c 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "openrag"
-version = "0.1.14.dev2"
+version = "0.1.14.dev3"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.13"
diff --git a/src/api/documents.py b/src/api/documents.py
index 82afb349..048f746a 100644
--- a/src/api/documents.py
+++ b/src/api/documents.py
@@ -6,14 +6,13 @@ from config.settings import INDEX_NAME
 logger = get_logger(__name__)
 
 
-async def delete_documents_by_filename(request: Request, document_service, session_manager):
-    """Delete all documents with a specific filename"""
-    data = await request.json()
-    filename = data.get("filename")
-    
+async def check_filename_exists(request: Request, document_service, session_manager):
+    """Check if a document with a specific filename already exists"""
+    filename = request.query_params.get("filename")
+
     if not filename:
-        return JSONResponse({"error": "filename is required"}, status_code=400)
-    
+        return JSONResponse({"error": "filename parameter is required"}, status_code=400)
+
     user = request.state.user
     jwt_token = session_manager.get_effective_jwt_token(user.user_id, request.state.jwt_token)
 
@@ -22,34 +21,79 @@ async def delete_documents_by_filename(request: Request, document_service, sessi
         opensearch_client = session_manager.get_user_opensearch_client(
             user.user_id, jwt_token
         )
-        
+
+        # Search for any document with this exact filename
+        from utils.opensearch_queries import build_filename_search_body
+
+        search_body = build_filename_search_body(filename, size=1, source=["filename"])
+
+        logger.debug(f"Checking filename existence: {filename}")
+
+        response = await opensearch_client.search(
+            index=INDEX_NAME,
+            body=search_body
+        )
+
+        # Check if any hits were found
+        hits = response.get("hits", {}).get("hits", [])
+        exists = len(hits) > 0
+
+        logger.debug(f"Filename check result - exists: {exists}, hits: {len(hits)}")
+
+        return JSONResponse({
+            "exists": exists,
+            "filename": filename
+        }, status_code=200)
+
+    except Exception as e:
+        logger.error("Error checking filename existence", filename=filename, error=str(e))
+        error_str = str(e)
+        if "AuthenticationException" in error_str:
+            return JSONResponse({"error": "Access denied: insufficient permissions"}, status_code=403)
+        else:
+            return JSONResponse({"error": str(e)}, status_code=500)
+
+
+async def delete_documents_by_filename(request: Request, document_service, session_manager):
+    """Delete all documents with a specific filename"""
+    data = await request.json()
+    filename = data.get("filename")
+
+    if not filename:
+        return JSONResponse({"error": "filename is required"}, status_code=400)
+
+    user = request.state.user
+    jwt_token = session_manager.get_effective_jwt_token(user.user_id, request.state.jwt_token)
+
+    try:
+        # Get user's OpenSearch client
+        opensearch_client = session_manager.get_user_opensearch_client(
+            user.user_id, jwt_token
+        )
+
         # Delete by query to remove all chunks of this document
-        delete_query = {
-            "query": {
-                "bool": {
-                    "must": [
-                        {"term": {"filename": filename}}
-                    ]
-                }
-            }
-        }
-        
+        from utils.opensearch_queries import build_filename_delete_body
+
+        delete_query = build_filename_delete_body(filename)
+
+        logger.debug(f"Deleting documents with filename: {filename}")
+
         result = await opensearch_client.delete_by_query(
             index=INDEX_NAME,
             body=delete_query,
             conflicts="proceed"
         )
-        
+
         deleted_count = result.get("deleted", 0)
         logger.info(f"Deleted {deleted_count} chunks for filename {filename}", user_id=user.user_id)
-        
+
         return JSONResponse({
             "success": True,
             "deleted_chunks": deleted_count,
             "filename": filename,
             "message": f"All documents with filename '{filename}' deleted successfully"
         }, status_code=200)
-        
+
     except Exception as e:
         logger.error("Error deleting documents by filename", filename=filename, error=str(e))
         error_str = str(e)
diff --git a/src/api/langflow_files.py b/src/api/langflow_files.py
index 4fa17315..0226d4d5 100644
--- a/src/api/langflow_files.py
+++ b/src/api/langflow_files.py
@@ -189,19 +189,20 @@ async def upload_and_ingest_user_file(
         # Create temporary file for task processing
         import tempfile
         import os
-        
+
         # Read file content
         content = await upload_file.read()
-        
-        # Create temporary file
+
+        # Create temporary file with the actual filename (not a temp prefix)
+        # Store in temp directory but use the real filename
+        temp_dir = tempfile.gettempdir()
         safe_filename = upload_file.filename.replace(" ", "_").replace("/", "_")
-        temp_fd, temp_path = tempfile.mkstemp(
-            suffix=f"_{safe_filename}"
-        )
+        temp_path = os.path.join(temp_dir, safe_filename)
+
         
         try:
             # Write content to temp file
-            with os.fdopen(temp_fd, 'wb') as temp_file:
+            with open(temp_path, 'wb') as temp_file:
                 temp_file.write(content)
 
             logger.debug("Created temporary file for task processing", temp_path=temp_path)
diff --git a/src/api/router.py b/src/api/router.py
index 42080693..15a9b116 100644
--- a/src/api/router.py
+++ b/src/api/router.py
@@ -13,27 +13,27 @@ logger = get_logger(__name__)
 
 
 async def upload_ingest_router(
-    request: Request, 
-    document_service=None, 
-    langflow_file_service=None, 
+    request: Request,
+    document_service=None,
+    langflow_file_service=None,
     session_manager=None,
-    task_service=None
+    task_service=None,
 ):
     """
     Router endpoint that automatically routes upload requests based on configuration.
-    
+
     - If DISABLE_INGEST_WITH_LANGFLOW is True: uses traditional OpenRAG upload (/upload)
     - If DISABLE_INGEST_WITH_LANGFLOW is False (default): uses Langflow upload-ingest via task service
-    
+
     This provides a single endpoint that users can call regardless of backend configuration.
     All langflow uploads are processed as background tasks for better scalability.
     """
     try:
         logger.debug(
-            "Router upload_ingest endpoint called", 
-            disable_langflow_ingest=DISABLE_INGEST_WITH_LANGFLOW
+            "Router upload_ingest endpoint called",
+            disable_langflow_ingest=DISABLE_INGEST_WITH_LANGFLOW,
         )
-        
+
         # Route based on configuration
         if DISABLE_INGEST_WITH_LANGFLOW:
             # Route to traditional OpenRAG upload
@@ -42,8 +42,10 @@ async def upload_ingest_router(
         else:
             # Route to Langflow upload and ingest using task service
             logger.debug("Routing to Langflow upload-ingest pipeline via task service")
-            return await langflow_upload_ingest_task(request, langflow_file_service, session_manager, task_service)
-            
+            return await langflow_upload_ingest_task(
+                request, langflow_file_service, session_manager, task_service
+            )
+
     except Exception as e:
         logger.error("Error in upload_ingest_router", error=str(e))
         error_msg = str(e)
@@ -57,17 +59,14 @@ async def upload_ingest_router(
 
 
 async def langflow_upload_ingest_task(
-    request: Request, 
-    langflow_file_service, 
-    session_manager, 
-    task_service
+    request: Request, langflow_file_service, session_manager, task_service
 ):
     """Task-based langflow upload and ingest for single/multiple files"""
     try:
         logger.debug("Task-based langflow upload_ingest endpoint called")
         form = await request.form()
         upload_files = form.getlist("file")
-        
+
         if not upload_files or len(upload_files) == 0:
             logger.error("No files provided in task-based upload request")
             return JSONResponse({"error": "Missing files"}, status_code=400)
@@ -77,14 +76,16 @@ async def langflow_upload_ingest_task(
         settings_json = form.get("settings")
         tweaks_json = form.get("tweaks")
         delete_after_ingest = form.get("delete_after_ingest", "true").lower() == "true"
+        replace_duplicates = form.get("replace_duplicates", "false").lower() == "true"
 
         # Parse JSON fields if provided
         settings = None
         tweaks = None
-        
+
         if settings_json:
             try:
                 import json
+
                 settings = json.loads(settings_json)
             except json.JSONDecodeError as e:
                 logger.error("Invalid settings JSON", error=str(e))
@@ -93,6 +94,7 @@ async def langflow_upload_ingest_task(
         if tweaks_json:
             try:
                 import json
+
                 tweaks = json.loads(tweaks_json)
             except json.JSONDecodeError as e:
                 logger.error("Invalid tweaks JSON", error=str(e))
@@ -106,28 +108,37 @@ async def langflow_upload_ingest_task(
         jwt_token = getattr(request.state, "jwt_token", None)
 
         if not user_id:
-            return JSONResponse({"error": "User authentication required"}, status_code=401)
+            return JSONResponse(
+                {"error": "User authentication required"}, status_code=401
+            )
 
         # Create temporary files for task processing
         import tempfile
         import os
+
         temp_file_paths = []
-        
+        original_filenames = []
+
         try:
+            # Create temp directory reference once
+            temp_dir = tempfile.gettempdir()
+
             for upload_file in upload_files:
                 # Read file content
                 content = await upload_file.read()
-                
-                # Create temporary file
+
+                # Store ORIGINAL filename (not transformed)
+                original_filenames.append(upload_file.filename)
+
+                # Create temporary file with TRANSFORMED filename for filesystem safety
+                # Transform: spaces and / to underscore
                 safe_filename = upload_file.filename.replace(" ", "_").replace("/", "_")
-                temp_fd, temp_path = tempfile.mkstemp(
-                    suffix=f"_{safe_filename}"
-                )
-                
+                temp_path = os.path.join(temp_dir, safe_filename)
+
                 # Write content to temp file
-                with os.fdopen(temp_fd, 'wb') as temp_file:
+                with open(temp_path, "wb") as temp_file:
                     temp_file.write(content)
-                
+
                 temp_file_paths.append(temp_path)
 
             logger.debug(
@@ -136,21 +147,22 @@ async def langflow_upload_ingest_task(
                 user_id=user_id,
                 has_settings=bool(settings),
                 has_tweaks=bool(tweaks),
-                delete_after_ingest=delete_after_ingest
+                delete_after_ingest=delete_after_ingest,
             )
 
             # Create langflow upload task
-            print(f"tweaks: {tweaks}")
-            print(f"settings: {settings}")
-            print(f"jwt_token: {jwt_token}")
-            print(f"user_name: {user_name}")
-            print(f"user_email: {user_email}")
-            print(f"session_id: {session_id}")
-            print(f"delete_after_ingest: {delete_after_ingest}")
-            print(f"temp_file_paths: {temp_file_paths}")
+            logger.debug(
+                f"Preparing to create langflow upload task: tweaks={tweaks}, settings={settings}, jwt_token={jwt_token}, user_name={user_name}, user_email={user_email}, session_id={session_id}, delete_after_ingest={delete_after_ingest}, temp_file_paths={temp_file_paths}",
+            )
+            # Create a map between temp_file_paths and original_filenames
+            file_path_to_original_filename = dict(zip(temp_file_paths, original_filenames))
+            logger.debug(
+                f"File path to original filename map: {file_path_to_original_filename}",
+            )
             task_id = await task_service.create_langflow_upload_task(
                 user_id=user_id,
                 file_paths=temp_file_paths,
+                original_filenames=file_path_to_original_filename,
                 langflow_file_service=langflow_file_service,
                 session_manager=session_manager,
                 jwt_token=jwt_token,
@@ -160,23 +172,28 @@ async def langflow_upload_ingest_task(
                 tweaks=tweaks,
                 settings=settings,
                 delete_after_ingest=delete_after_ingest,
+                replace_duplicates=replace_duplicates,
             )
 
             logger.debug("Langflow upload task created successfully", task_id=task_id)
-            
-            return JSONResponse({
-                "task_id": task_id,
-                "message": f"Langflow upload task created for {len(upload_files)} file(s)",
-                "file_count": len(upload_files)
-            }, status_code=202)  # 202 Accepted for async processing
-            
+
+            return JSONResponse(
+                {
+                    "task_id": task_id,
+                    "message": f"Langflow upload task created for {len(upload_files)} file(s)",
+                    "file_count": len(upload_files),
+                },
+                status_code=202,
+            )  # 202 Accepted for async processing
+
         except Exception:
             # Clean up temp files on error
             from utils.file_utils import safe_unlink
+
             for temp_path in temp_file_paths:
                 safe_unlink(temp_path)
             raise
-            
+
     except Exception as e:
         logger.error(
             "Task-based langflow upload_ingest endpoint failed",
@@ -184,5 +201,6 @@ async def langflow_upload_ingest_task(
             error=str(e),
         )
         import traceback
+
         logger.error("Full traceback", traceback=traceback.format_exc())
         return JSONResponse({"error": str(e)}, status_code=500)
diff --git a/src/config/config_manager.py b/src/config/config_manager.py
index da059d0d..93fb86c5 100644
--- a/src/config/config_manager.py
+++ b/src/config/config_manager.py
@@ -27,7 +27,7 @@ class KnowledgeConfig:
     embedding_model: str = "text-embedding-3-small"
     chunk_size: int = 1000
     chunk_overlap: int = 200
-    table_structure: bool = False
+    table_structure: bool = True
     ocr: bool = False
     picture_descriptions: bool = False
 
diff --git a/src/config/settings.py b/src/config/settings.py
index 27ea9502..6f55520d 100644
--- a/src/config/settings.py
+++ b/src/config/settings.py
@@ -34,6 +34,7 @@ _legacy_flow_id = os.getenv("FLOW_ID")
 
 LANGFLOW_CHAT_FLOW_ID = os.getenv("LANGFLOW_CHAT_FLOW_ID") or _legacy_flow_id
 LANGFLOW_INGEST_FLOW_ID = os.getenv("LANGFLOW_INGEST_FLOW_ID")
+LANGFLOW_URL_INGEST_FLOW_ID = os.getenv("LANGFLOW_URL_INGEST_FLOW_ID")
 NUDGES_FLOW_ID = os.getenv("NUDGES_FLOW_ID")
 
 if _legacy_flow_id and not os.getenv("LANGFLOW_CHAT_FLOW_ID"):
diff --git a/src/main.py b/src/main.py
index 230ded79..bf6da342 100644
--- a/src/main.py
+++ b/src/main.py
@@ -953,6 +953,17 @@ async def create_app():
             methods=["POST", "GET"],
         ),
         # Document endpoints
+        Route(
+            "/documents/check-filename",
+            require_auth(services["session_manager"])(
+                partial(
+                    documents.check_filename_exists,
+                    document_service=services["document_service"],
+                    session_manager=services["session_manager"],
+                )
+            ),
+            methods=["GET"],
+        ),
         Route(
             "/documents/delete-by-filename",
             require_auth(services["session_manager"])(
diff --git a/src/models/processors.py b/src/models/processors.py
index bd2118a9..4a5d96b5 100644
--- a/src/models/processors.py
+++ b/src/models/processors.py
@@ -55,6 +55,96 @@ class TaskProcessor:
                     await asyncio.sleep(retry_delay)
                     retry_delay *= 2  # Exponential backoff
 
+    async def check_filename_exists(
+        self,
+        filename: str,
+        opensearch_client,
+    ) -> bool:
+        """
+        Check if a document with the given filename already exists in OpenSearch.
+        Returns True if any chunks with this filename exist.
+        """
+        from config.settings import INDEX_NAME
+        from utils.opensearch_queries import build_filename_search_body
+        import asyncio
+
+        max_retries = 3
+        retry_delay = 1.0
+
+        for attempt in range(max_retries):
+            try:
+                # Search for any document with this exact filename
+                search_body = build_filename_search_body(filename, size=1, source=False)
+
+                response = await opensearch_client.search(
+                    index=INDEX_NAME,
+                    body=search_body
+                )
+
+                # Check if any hits were found
+                hits = response.get("hits", {}).get("hits", [])
+                return len(hits) > 0
+
+            except (asyncio.TimeoutError, Exception) as e:
+                if attempt == max_retries - 1:
+                    logger.error(
+                        "OpenSearch filename check failed after retries",
+                        filename=filename,
+                        error=str(e),
+                        attempt=attempt + 1
+                    )
+                    # On final failure, assume document doesn't exist (safer to reprocess than skip)
+                    logger.warning(
+                        "Assuming filename doesn't exist due to connection issues",
+                        filename=filename
+                    )
+                    return False
+                else:
+                    logger.warning(
+                        "OpenSearch filename check failed, retrying",
+                        filename=filename,
+                        error=str(e),
+                        attempt=attempt + 1,
+                        retry_in=retry_delay
+                    )
+                    await asyncio.sleep(retry_delay)
+                    retry_delay *= 2  # Exponential backoff
+
+    async def delete_document_by_filename(
+        self,
+        filename: str,
+        opensearch_client,
+    ) -> None:
+        """
+        Delete all chunks of a document with the given filename from OpenSearch.
+        """
+        from config.settings import INDEX_NAME
+        from utils.opensearch_queries import build_filename_delete_body
+
+        try:
+            # Delete all documents with this filename
+            delete_body = build_filename_delete_body(filename)
+
+            response = await opensearch_client.delete_by_query(
+                index=INDEX_NAME,
+                body=delete_body
+            )
+
+            deleted_count = response.get("deleted", 0)
+            logger.info(
+                "Deleted existing document chunks",
+                filename=filename,
+                deleted_count=deleted_count
+            )
+
+        except Exception as e:
+            logger.error(
+                "Failed to delete existing document",
+                filename=filename,
+                error=str(e)
+            )
+            raise
+
     async def process_document_standard(
         self,
         file_path: str,
@@ -527,6 +617,7 @@ class LangflowFileProcessor(TaskProcessor):
         tweaks: dict = None,
         settings: dict = None,
         delete_after_ingest: bool = True,
+        replace_duplicates: bool = False,
     ):
         super().__init__()
         self.langflow_file_service = langflow_file_service
@@ -539,6 +630,7 @@ class LangflowFileProcessor(TaskProcessor):
         self.tweaks = tweaks or {}
         self.settings = settings
         self.delete_after_ingest = delete_after_ingest
+        self.replace_duplicates = replace_duplicates
 
     async def process_item(
         self, upload_task: UploadTask, item: str, file_task: FileTask
@@ -554,37 +646,40 @@ class LangflowFileProcessor(TaskProcessor):
         file_task.updated_at = time.time()
 
         try:
-            # Compute hash and check if already exists
-            from utils.hash_utils import hash_id
-            file_hash = hash_id(item)
+            # Use the ORIGINAL filename stored in file_task (not the transformed temp path)
+            # This ensures we check/store the original filename with spaces, etc.
+            original_filename = file_task.filename or os.path.basename(item)
 
-            # Check if document already exists
+            # Check if document with same filename already exists
             opensearch_client = self.session_manager.get_user_opensearch_client(
                 self.owner_user_id, self.jwt_token
             )
-            if await self.check_document_exists(file_hash, opensearch_client):
-                file_task.status = TaskStatus.COMPLETED
-                file_task.result = {"status": "unchanged", "id": file_hash}
+
+            filename_exists = await self.check_filename_exists(original_filename, opensearch_client)
+
+            if filename_exists and not self.replace_duplicates:
+                # Duplicate exists and user hasn't confirmed replacement
+                file_task.status = TaskStatus.FAILED
+                file_task.error = f"File with name '{original_filename}' already exists"
                 file_task.updated_at = time.time()
-                upload_task.successful_files += 1
+                upload_task.failed_files += 1
                 return
+            elif filename_exists and self.replace_duplicates:
+                # Delete existing document before uploading new one
+                logger.info(f"Replacing existing document: {original_filename}")
+                await self.delete_document_by_filename(original_filename, opensearch_client)
 
             # Read file content for processing
             with open(item, 'rb') as f:
                 content = f.read()
 
-            # Create file tuple for upload
-            temp_filename = os.path.basename(item)
-            # Extract original filename from temp file suffix (remove tmp prefix)
-            if "_" in temp_filename:
-                filename = temp_filename.split("_", 1)[1]  # Get everything after first _
-            else:
-                filename = temp_filename
-            content_type, _ = mimetypes.guess_type(filename)
+            # Create file tuple for upload using ORIGINAL filename
+            # This ensures the document is indexed with the original name
+            content_type, _ = mimetypes.guess_type(original_filename)
             if not content_type:
                 content_type = 'application/octet-stream'
-            
-            file_tuple = (filename, content, content_type)
+
+            file_tuple = (original_filename, content, content_type)
 
             # Get JWT token using same logic as DocumentFileProcessor
             # This will handle anonymous JWT creation if needed
diff --git a/src/models/tasks.py b/src/models/tasks.py
index 236927ab..253cabb5 100644
--- a/src/models/tasks.py
+++ b/src/models/tasks.py
@@ -20,7 +20,8 @@ class FileTask:
     retry_count: int = 0
     created_at: float = field(default_factory=time.time)
     updated_at: float = field(default_factory=time.time)
-    
+    filename: Optional[str] = None  # Original filename for display
+
     @property
     def duration_seconds(self) -> float:
         """Duration in seconds from creation to last update"""
diff --git a/src/services/flows_service.py b/src/services/flows_service.py
index 999d9930..429eabe7 100644
--- a/src/services/flows_service.py
+++ b/src/services/flows_service.py
@@ -1,5 +1,6 @@
 from config.settings import (
     DISABLE_INGEST_WITH_LANGFLOW,
+    LANGFLOW_URL_INGEST_FLOW_ID,
     NUDGES_FLOW_ID,
     LANGFLOW_URL,
     LANGFLOW_CHAT_FLOW_ID,
@@ -116,9 +117,11 @@ class FlowsService:
             flow_id = LANGFLOW_CHAT_FLOW_ID
         elif flow_type == "ingest":
             flow_id = LANGFLOW_INGEST_FLOW_ID
+        elif flow_type == "url_ingest":
+            flow_id = LANGFLOW_URL_INGEST_FLOW_ID
         else:
             raise ValueError(
-                "flow_type must be either 'nudges', 'retrieval', or 'ingest'"
+                "flow_type must be either 'nudges', 'retrieval', 'ingest', or 'url_ingest'"
             )
 
         if not flow_id:
@@ -291,6 +294,13 @@ class FlowsService:
                     "llm_name": None,  # Ingestion flow might not have LLM
                     "llm_text_name": None,
                 },
+                {
+                    "name": "url_ingest",
+                    "flow_id": LANGFLOW_URL_INGEST_FLOW_ID,
+                    "embedding_name": OPENAI_EMBEDDING_COMPONENT_DISPLAY_NAME,
+                    "llm_name": None,
+                    "llm_text_name": None,
+                },
             ]
 
             results = []
@@ -716,6 +726,10 @@ class FlowsService:
                         "name": "ingest",
                         "flow_id": LANGFLOW_INGEST_FLOW_ID,
                     },
+                    {
+                        "name": "url_ingest",
+                        "flow_id": LANGFLOW_URL_INGEST_FLOW_ID,
+                    },
                 ]
 
             # Determine target component IDs based on provider
diff --git a/src/services/langflow_file_service.py b/src/services/langflow_file_service.py
index 7ffdd3aa..1bce86f0 100644
--- a/src/services/langflow_file_service.py
+++ b/src/services/langflow_file_service.py
@@ -67,6 +67,7 @@ class LangflowFileService:
         owner_name: Optional[str] = None,
         owner_email: Optional[str] = None,
         connector_type: Optional[str] = None,
+        file_tuples: Optional[list[tuple[str, str, str]]] = None,
     ) -> Dict[str, Any]:
         """
         Trigger the ingestion flow with provided file paths.
@@ -86,7 +87,9 @@ class LangflowFileService:
 
         # Pass files via tweaks to File component (File-PSU37 from the flow)
         if file_paths:
-            tweaks["File-PSU37"] = {"path": file_paths}
+            tweaks["DoclingRemote-Dp3PX"] = {"path": file_paths}
+            
+
 
         # Pass JWT token via tweaks using the x-langflow-global-var- pattern
         if jwt_token:
@@ -129,7 +132,8 @@ class LangflowFileService:
             list(tweaks.keys()) if isinstance(tweaks, dict) else None,
             bool(jwt_token),
         )
-
+        # To compute the file size in bytes, use len() on the file content (which should be bytes)
+        file_size_bytes = len(file_tuples[0][1]) if file_tuples and len(file_tuples[0]) > 1 else 0
         # Avoid logging full payload to prevent leaking sensitive data (e.g., JWT)
         headers={
                 "X-Langflow-Global-Var-JWT": str(jwt_token),
@@ -137,6 +141,9 @@ class LangflowFileService:
                 "X-Langflow-Global-Var-OWNER_NAME": str(owner_name),
                 "X-Langflow-Global-Var-OWNER_EMAIL": str(owner_email),
                 "X-Langflow-Global-Var-CONNECTOR_TYPE": str(connector_type),
+                "X-Langflow-Global-Var-FILENAME": str(file_tuples[0][0]),
+                "X-Langflow-Global-Var-MIMETYPE": str(file_tuples[0][2]),
+                "X-Langflow-Global-Var-FILESIZE": str(file_size_bytes),
             }
         logger.info(f"[LF] Headers {headers}")
         logger.info(f"[LF] Payload {payload}")
@@ -271,6 +278,7 @@ class LangflowFileService:
                 owner_name=owner_name,
                 owner_email=owner_email,
                 connector_type=connector_type,
+                file_tuples=[file_tuple],
             )
             logger.debug("[LF] Ingestion completed successfully")
         except Exception as e:
diff --git a/src/services/task_service.py b/src/services/task_service.py
index be5312a0..735ad483 100644
--- a/src/services/task_service.py
+++ b/src/services/task_service.py
@@ -1,6 +1,5 @@
 import asyncio
 import random
-from typing import Dict, Optional
 import time
 import uuid
 
@@ -59,6 +58,7 @@ class TaskService:
         file_paths: list,
         langflow_file_service,
         session_manager,
+        original_filenames: dict | None = None,
         jwt_token: str = None,
         owner_name: str = None,
         owner_email: str = None,
@@ -66,6 +66,7 @@ class TaskService:
         tweaks: dict = None,
         settings: dict = None,
         delete_after_ingest: bool = True,
+        replace_duplicates: bool = False,
     ) -> str:
         """Create a new upload task for Langflow file processing with upload and ingest"""
         # Use LangflowFileProcessor with user context
@@ -82,18 +83,35 @@ class TaskService:
             tweaks=tweaks,
             settings=settings,
             delete_after_ingest=delete_after_ingest,
+            replace_duplicates=replace_duplicates,
         )
-        return await self.create_custom_task(user_id, file_paths, processor)
+        return await self.create_custom_task(user_id, file_paths, processor, original_filenames)
 
-    async def create_custom_task(self, user_id: str, items: list, processor) -> str:
+    async def create_custom_task(self, user_id: str, items: list, processor, original_filenames: dict | None = None) -> str:
         """Create a new task with custom processor for any type of items"""
+        import os
         # Store anonymous tasks under a stable key so they can be retrieved later
         store_user_id = user_id or AnonymousUser().user_id
         task_id = str(uuid.uuid4())
+
+        # Create file tasks with original filenames if provided
+        normalized_originals = (
+            {str(k): v for k, v in original_filenames.items()} if original_filenames else {}
+        )
+        file_tasks = {
+            str(item): FileTask(
+                file_path=str(item),
+                filename=normalized_originals.get(
+                    str(item), os.path.basename(str(item))
+                ),
+            )
+            for item in items
+        }
+
         upload_task = UploadTask(
             task_id=task_id,
             total_files=len(items),
-            file_tasks={str(item): FileTask(file_path=str(item)) for item in items},
+            file_tasks=file_tasks,
         )
 
         # Attach the custom processor to the task
@@ -268,6 +286,7 @@ class TaskService:
                 "created_at": file_task.created_at,
                 "updated_at": file_task.updated_at,
                 "duration_seconds": file_task.duration_seconds,
+                "filename": file_task.filename,
             }
 
             # Count running and pending files
@@ -322,6 +341,7 @@ class TaskService:
                             "created_at": file_task.created_at,
                             "updated_at": file_task.updated_at,
                             "duration_seconds": file_task.duration_seconds,
+                            "filename": file_task.filename,
                         }
 
                     if file_task.status.value == "running":
diff --git a/src/tui/_assets/docker-compose-cpu.yml b/src/tui/_assets/docker-compose-cpu.yml
index 9c121f89..1086737b 100644
--- a/src/tui/_assets/docker-compose-cpu.yml
+++ b/src/tui/_assets/docker-compose-cpu.yml
@@ -55,6 +55,7 @@ services:
       - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
       - LANGFLOW_CHAT_FLOW_ID=${LANGFLOW_CHAT_FLOW_ID}
       - LANGFLOW_INGEST_FLOW_ID=${LANGFLOW_INGEST_FLOW_ID}
+      - LANGFLOW_URL_INGEST_FLOW_ID=${LANGFLOW_URL_INGEST_FLOW_ID}
       - DISABLE_INGEST_WITH_LANGFLOW=${DISABLE_INGEST_WITH_LANGFLOW:-false}
       - NUDGES_FLOW_ID=${NUDGES_FLOW_ID}
       - OPENSEARCH_PORT=9200
@@ -99,15 +100,22 @@ services:
       - OPENAI_API_KEY=${OPENAI_API_KEY}
       - LANGFLOW_LOAD_FLOWS_PATH=/app/flows
       - LANGFLOW_SECRET_KEY=${LANGFLOW_SECRET_KEY}
-      - JWT="dummy"
+      - JWT=None  
+      - OWNER=None
+      - OWNER_NAME=None
+      - OWNER_EMAIL=None
+      - CONNECTOR_TYPE=system
       - OPENRAG-QUERY-FILTER="{}"
       - OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
-      - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD
+      - FILENAME=None
+      - MIMETYPE=None
+      - FILESIZE=0
+      - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD,OWNER,OWNER_NAME,OWNER_EMAIL,CONNECTOR_TYPE,FILENAME,MIMETYPE,FILESIZE
       - LANGFLOW_LOG_LEVEL=DEBUG
       - LANGFLOW_AUTO_LOGIN=${LANGFLOW_AUTO_LOGIN}
       - LANGFLOW_SUPERUSER=${LANGFLOW_SUPERUSER}
       - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
       - LANGFLOW_NEW_USER_IS_ACTIVE=${LANGFLOW_NEW_USER_IS_ACTIVE}
       - LANGFLOW_ENABLE_SUPERUSER_CLI=${LANGFLOW_ENABLE_SUPERUSER_CLI}
-      - DEFAULT_FOLDER_NAME="OpenRAG"
+      # - DEFAULT_FOLDER_NAME=OpenRAG
       - HIDE_GETTING_STARTED_PROGRESS=true
diff --git a/src/tui/_assets/docker-compose.yml b/src/tui/_assets/docker-compose.yml
index 3f1bf1a6..32b72c65 100644
--- a/src/tui/_assets/docker-compose.yml
+++ b/src/tui/_assets/docker-compose.yml
@@ -54,6 +54,7 @@ services:
       - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
       - LANGFLOW_CHAT_FLOW_ID=${LANGFLOW_CHAT_FLOW_ID}
       - LANGFLOW_INGEST_FLOW_ID=${LANGFLOW_INGEST_FLOW_ID}
+      - LANGFLOW_URL_INGEST_FLOW_ID=${LANGFLOW_URL_INGEST_FLOW_ID}
       - DISABLE_INGEST_WITH_LANGFLOW=${DISABLE_INGEST_WITH_LANGFLOW:-false}
       - NUDGES_FLOW_ID=${NUDGES_FLOW_ID}
       - OPENSEARCH_PORT=9200
@@ -99,15 +100,22 @@ services:
       - OPENAI_API_KEY=${OPENAI_API_KEY}
       - LANGFLOW_LOAD_FLOWS_PATH=/app/flows
       - LANGFLOW_SECRET_KEY=${LANGFLOW_SECRET_KEY}
-      - JWT="dummy"
+      - JWT=None  
+      - OWNER=None
+      - OWNER_NAME=None
+      - OWNER_EMAIL=None
+      - CONNECTOR_TYPE=system
       - OPENRAG-QUERY-FILTER="{}"
       - OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
-      - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD
+      - FILENAME=None
+      - MIMETYPE=None
+      - FILESIZE=0
+      - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD,OWNER,OWNER_NAME,OWNER_EMAIL,CONNECTOR_TYPE,FILENAME,MIMETYPE,FILESIZE
       - LANGFLOW_LOG_LEVEL=DEBUG
       - LANGFLOW_AUTO_LOGIN=${LANGFLOW_AUTO_LOGIN}
       - LANGFLOW_SUPERUSER=${LANGFLOW_SUPERUSER}
       - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
       - LANGFLOW_NEW_USER_IS_ACTIVE=${LANGFLOW_NEW_USER_IS_ACTIVE}
       - LANGFLOW_ENABLE_SUPERUSER_CLI=${LANGFLOW_ENABLE_SUPERUSER_CLI}
-      - DEFAULT_FOLDER_NAME="OpenRAG"
+      # - DEFAULT_FOLDER_NAME="OpenRAG"
       - HIDE_GETTING_STARTED_PROGRESS=true
diff --git a/src/tui/managers/env_manager.py b/src/tui/managers/env_manager.py
index 9954b463..9510fb70 100644
--- a/src/tui/managers/env_manager.py
+++ b/src/tui/managers/env_manager.py
@@ -33,6 +33,7 @@ class EnvConfig:
     langflow_superuser_password: str = ""
     langflow_chat_flow_id: str = "1098eea1-6649-4e1d-aed1-b77249fb8dd0"
     langflow_ingest_flow_id: str = "5488df7c-b93f-4f87-a446-b67028bc0813"
+    langflow_url_ingest_flow_id: str = "72c3d17c-2dac-4a73-b48a-6518473d7830"
 
     # OAuth settings
     google_oauth_client_id: str = ""
@@ -114,6 +115,7 @@ class EnvManager:
                             "LANGFLOW_SUPERUSER_PASSWORD": "langflow_superuser_password",
                             "LANGFLOW_CHAT_FLOW_ID": "langflow_chat_flow_id",
                             "LANGFLOW_INGEST_FLOW_ID": "langflow_ingest_flow_id",
+                            "LANGFLOW_URL_INGEST_FLOW_ID": "langflow_url_ingest_flow_id",
                             "NUDGES_FLOW_ID": "nudges_flow_id",
                             "GOOGLE_OAUTH_CLIENT_ID": "google_oauth_client_id",
                             "GOOGLE_OAUTH_CLIENT_SECRET": "google_oauth_client_secret",
@@ -255,6 +257,7 @@ class EnvManager:
                 f.write(
                     f"LANGFLOW_INGEST_FLOW_ID={self._quote_env_value(self.config.langflow_ingest_flow_id)}\n"
                 )
+                f.write(f"LANGFLOW_URL_INGEST_FLOW_ID={self._quote_env_value(self.config.langflow_url_ingest_flow_id)}\n")
                 f.write(f"NUDGES_FLOW_ID={self._quote_env_value(self.config.nudges_flow_id)}\n")
                 f.write(f"OPENSEARCH_PASSWORD={self._quote_env_value(self.config.opensearch_password)}\n")
                 f.write(f"OPENAI_API_KEY={self._quote_env_value(self.config.openai_api_key)}\n")
diff --git a/src/utils/opensearch_queries.py b/src/utils/opensearch_queries.py
new file mode 100644
index 00000000..f29c6283
--- /dev/null
+++ b/src/utils/opensearch_queries.py
@@ -0,0 +1,55 @@
+"""
+Utility functions for constructing OpenSearch queries consistently.
+"""
+from typing import Union, List
+
+
+def build_filename_query(filename: str) -> dict:
+    """
+    Build a standardized query for finding documents by filename.
+
+    Args:
+        filename: The exact filename to search for
+
+    Returns:
+        A dict containing the OpenSearch query body
+    """
+    return {
+        "term": {
+            "filename": filename
+        }
+    }
+
+
+def build_filename_search_body(filename: str, size: int = 1, source: Union[bool, List[str]] = False) -> dict:
+    """
+    Build a complete search body for checking if a filename exists.
+
+    Args:
+        filename: The exact filename to search for
+        size: Number of results to return (default: 1)
+        source: Whether to include source fields, or list of specific fields to include (default: False)
+
+    Returns:
+        A dict containing the complete OpenSearch search body
+    """
+    return {
+        "query": build_filename_query(filename),
+        "size": size,
+        "_source": source
+    }
+
+
+def build_filename_delete_body(filename: str) -> dict:
+    """
+    Build a delete-by-query body for removing all documents with a filename.
+
+    Args:
+        filename: The exact filename to delete
+
+    Returns:
+        A dict containing the OpenSearch delete-by-query body
+    """
+    return {
+        "query": build_filename_query(filename)
+    }
diff --git a/uv.lock b/uv.lock
index 3da8f670..c9bc6714 100644
--- a/uv.lock
+++ b/uv.lock
@@ -2282,7 +2282,7 @@ wheels = [
 
 [[package]]
 name = "openrag"
-version = "0.1.14.dev2"
+version = "0.1.14.dev3"
 source = { editable = "." }
 dependencies = [
     { name = "agentd" },