gmakstutis/openrag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
openrag/flows/ingestion_flow.json
Gabriel Luiz Freitas Almeida 1d5d26b456 Update ingestion flow JSON to enhance metadata handling and improve component configurations 
This commit modifies the ingestion flow JSON by adding support for user-defined metadata through the "docs_metadata" input field, improving the context for document ingestion. Additionally, it updates the selection state of a node and adjusts the viewport settings for better layout. These changes enhance the overall functionality and clarity of the component configurations, aligning with best practices for robust async development.
2025-09-09 00:13:26 -03:00

2032 lines
No EOL
129 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"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": "OpenAIEmbeddings",
"id": "OpenAIEmbeddings-joRJ6",
"name": "embeddings",
"output_types": [
"Embeddings"
]
},
"targetHandle": {
"fieldName": "embedding",
"id": "OpenSearchHybrid-Ve6bS",
"inputTypes": [
"Embeddings"
],
"type": "other"
}
},
"id": "xy-edge__OpenAIEmbeddings-joRJ6{œdataTypeœ:œOpenAIEmbeddingsœ,œidœ:œOpenAIEmbeddings-joRJ6œ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-OpenSearchHybrid-Ve6bS{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
"selected": false,
"source": "OpenAIEmbeddings-joRJ6",
"sourceHandle": "{œdataTypeœ:œOpenAIEmbeddingsœ,œidœ:œOpenAIEmbeddings-joRJ6œ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}",
"target": "OpenSearchHybrid-Ve6bS",
"targetHandle": "{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchHybrid-Ve6bSœ,œinputTypesœ:[œEmbeddingsœ],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}"
}
],
"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": "1.5.0.post2",
"metadata": {
"code_hash": "65a90e1f4fe6",
"dependencies": {
"dependencies": [
{
"name": "langchain_text_splitters",
"version": "0.3.9"
},
{
"name": "langflow",
"version": "1.5.0.post2"
}
],
"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 langflow.custom.custom_component.component import Component\nfrom langflow.io import DropdownInput, HandleInput, IntInput, MessageTextInput, Output\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\nfrom langflow.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 data_list = [Data(text=doc.page_content, data=doc.metadata) for doc in docs]\n return data_list\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 self.log(documents)\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,
"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": 1729.1788373023007,
"y": 1330.8003441546418
},
"positionAbsolute": {
"x": 1683.4543896546102,
"y": 1350.7871623588553
},
"selected": false,
"type": "genericNode",
"width": 320
},
{
"data": {
"id": "OpenAIEmbeddings-joRJ6",
"node": {
"base_classes": [
"Embeddings"
],
"beta": false,
"conditional_paths": [],
"custom_fields": {},
"description": "Generate embeddings using OpenAI models.",
"display_name": "OpenAI Embeddings",
"documentation": "",
"edited": false,
"field_order": [
"default_headers",
"default_query",
"chunk_size",
"client",
"deployment",
"embedding_ctx_length",
"max_retries",
"model",
"model_kwargs",
"openai_api_key",
"openai_api_base",
"openai_api_type",
"openai_api_version",
"openai_organization",
"openai_proxy",
"request_timeout",
"show_progress_bar",
"skip_empty",
"tiktoken_model_name",
"tiktoken_enable",
"dimensions"
],
"frozen": false,
"icon": "OpenAI",
"legacy": false,
"lf_version": "1.5.0.post2",
"metadata": {
"code_hash": "2691dee277c9",
"dependencies": {
"dependencies": [
{
"name": "langchain_openai",
"version": "0.3.23"
},
{
"name": "langflow",
"version": "1.5.0.post2"
}
],
"total_dependencies": 2
},
"module": "langflow.components.openai.openai.OpenAIEmbeddingsComponent"
},
"output_types": [],
"outputs": [
{
"allows_loop": false,
"cache": true,
"display_name": "Embedding Model",
"group_outputs": false,
"method": "build_embeddings",
"name": "embeddings",
"selected": "Embeddings",
"tool_mode": true,
"types": [
"Embeddings"
],
"value": "__UNDEFINED__"
}
],
"pinned": false,
"template": {
"_type": "Component",
"chunk_size": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Chunk Size",
"dynamic": false,
"info": "",
"list": false,
"name": "chunk_size",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "int",
"value": 1000
},
"client": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "Client",
"dynamic": false,
"info": "",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "client",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"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_openai import OpenAIEmbeddings\n\nfrom langflow.base.embeddings.model import LCEmbeddingsModel\nfrom langflow.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom langflow.field_typing import Embeddings\nfrom langflow.io import BoolInput, DictInput, DropdownInput, FloatInput, IntInput, MessageTextInput, SecretStrInput\n\n\nclass OpenAIEmbeddingsComponent(LCEmbeddingsModel):\n display_name = \"OpenAI Embeddings\"\n description = \"Generate embeddings using OpenAI models.\"\n icon = \"OpenAI\"\n name = \"OpenAIEmbeddings\"\n\n inputs = [\n DictInput(\n name=\"default_headers\",\n display_name=\"Default Headers\",\n advanced=True,\n info=\"Default headers to use for the API request.\",\n ),\n DictInput(\n name=\"default_query\",\n display_name=\"Default Query\",\n advanced=True,\n info=\"Default query parameters to use for the API request.\",\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n MessageTextInput(name=\"client\", display_name=\"Client\", advanced=True),\n MessageTextInput(name=\"deployment\", display_name=\"Deployment\", advanced=True),\n IntInput(name=\"embedding_ctx_length\", display_name=\"Embedding Context Length\", advanced=True, value=1536),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", value=3, advanced=True),\n DropdownInput(\n name=\"model\",\n display_name=\"Model\",\n advanced=False,\n options=OPENAI_EMBEDDING_MODEL_NAMES,\n value=\"text-embedding-3-small\",\n ),\n DictInput(name=\"model_kwargs\", display_name=\"Model Kwargs\", advanced=True),\n SecretStrInput(name=\"openai_api_key\", display_name=\"OpenAI API Key\", value=\"OPENAI_API_KEY\", required=True),\n MessageTextInput(name=\"openai_api_base\", display_name=\"OpenAI API Base\", advanced=True),\n MessageTextInput(name=\"openai_api_type\", display_name=\"OpenAI API Type\", advanced=True),\n MessageTextInput(name=\"openai_api_version\", display_name=\"OpenAI API Version\", advanced=True),\n MessageTextInput(\n name=\"openai_organization\",\n display_name=\"OpenAI Organization\",\n advanced=True,\n ),\n MessageTextInput(name=\"openai_proxy\", display_name=\"OpenAI Proxy\", advanced=True),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n BoolInput(name=\"skip_empty\", display_name=\"Skip Empty\", advanced=True),\n MessageTextInput(\n name=\"tiktoken_model_name\",\n display_name=\"TikToken Model Name\",\n advanced=True,\n ),\n BoolInput(\n name=\"tiktoken_enable\",\n display_name=\"TikToken Enable\",\n advanced=True,\n value=True,\n info=\"If False, you must have transformers installed.\",\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 ]\n\n def build_embeddings(self) -> Embeddings:\n return OpenAIEmbeddings(\n client=self.client or None,\n model=self.model,\n dimensions=self.dimensions or None,\n deployment=self.deployment or None,\n api_version=self.openai_api_version or None,\n base_url=self.openai_api_base or None,\n openai_api_type=self.openai_api_type or None,\n openai_proxy=self.openai_proxy or None,\n embedding_ctx_length=self.embedding_ctx_length,\n api_key=self.openai_api_key or None,\n organization=self.openai_organization or None,\n allowed_special=\"all\",\n disallowed_special=\"all\",\n chunk_size=self.chunk_size,\n max_retries=self.max_retries,\n timeout=self.request_timeout or None,\n tiktoken_enabled=self.tiktoken_enable,\n tiktoken_model_name=self.tiktoken_model_name or None,\n show_progress_bar=self.show_progress_bar,\n model_kwargs=self.model_kwargs,\n skip_empty=self.skip_empty,\n default_headers=self.default_headers or None,\n default_query=self.default_query or None,\n )\n"
},
"default_headers": {
"_input_type": "DictInput",
"advanced": true,
"display_name": "Default Headers",
"dynamic": false,
"info": "Default headers to use for the API request.",
"list": false,
"name": "default_headers",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_input": true,
"type": "dict",
"value": {}
},
"default_query": {
"_input_type": "DictInput",
"advanced": true,
"display_name": "Default Query",
"dynamic": false,
"info": "Default query parameters to use for the API request.",
"list": false,
"name": "default_query",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_input": true,
"type": "dict",
"value": {}
},
"deployment": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "Deployment",
"dynamic": false,
"info": "",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "deployment",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"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,
"name": "dimensions",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "int",
"value": ""
},
"embedding_ctx_length": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Embedding Context Length",
"dynamic": false,
"info": "",
"list": false,
"name": "embedding_ctx_length",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "int",
"value": 1536
},
"max_retries": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "Max Retries",
"dynamic": false,
"info": "",
"list": false,
"name": "max_retries",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "int",
"value": 3
},
"model": {
"_input_type": "DropdownInput",
"advanced": false,
"combobox": false,
"display_name": "Model",
"dynamic": false,
"info": "",
"name": "model",
"options": [
"text-embedding-3-small",
"text-embedding-3-large",
"text-embedding-ada-002"
],
"placeholder": "",
"required": false,
"show": true,
"title_case": 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": "",
"list": false,
"name": "model_kwargs",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_input": true,
"type": "dict",
"value": {}
},
"openai_api_base": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "OpenAI API Base",
"dynamic": false,
"info": "",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "openai_api_base",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"openai_api_key": {
"_input_type": "SecretStrInput",
"advanced": false,
"display_name": "OpenAI API Key",
"dynamic": false,
"info": "",
"input_types": [],
"load_from_db": true,
"name": "openai_api_key",
"password": true,
"placeholder": "",
"required": true,
"show": true,
"title_case": false,
"type": "str",
"value": "OPENAI_API_KEY"
},
"openai_api_type": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "OpenAI API Type",
"dynamic": false,
"info": "",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "openai_api_type",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"openai_api_version": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "OpenAI API Version",
"dynamic": false,
"info": "",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "openai_api_version",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"openai_organization": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "OpenAI Organization",
"dynamic": false,
"info": "",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "openai_organization",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"openai_proxy": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "OpenAI Proxy",
"dynamic": false,
"info": "",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "openai_proxy",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
},
"request_timeout": {
"_input_type": "FloatInput",
"advanced": true,
"display_name": "Request Timeout",
"dynamic": false,
"info": "",
"list": false,
"name": "request_timeout",
"placeholder": "",
"required": false,
"show": true,
"title_case": 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,
"name": "show_progress_bar",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "bool",
"value": false
},
"skip_empty": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "Skip Empty",
"dynamic": false,
"info": "",
"list": false,
"name": "skip_empty",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "bool",
"value": false
},
"tiktoken_enable": {
"_input_type": "BoolInput",
"advanced": true,
"display_name": "TikToken Enable",
"dynamic": false,
"info": "If False, you must have transformers installed.",
"list": false,
"name": "tiktoken_enable",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"trace_as_metadata": true,
"type": "bool",
"value": true
},
"tiktoken_model_name": {
"_input_type": "MessageTextInput",
"advanced": true,
"display_name": "TikToken Model Name",
"dynamic": false,
"info": "",
"input_types": [
"Message"
],
"list": false,
"load_from_db": false,
"name": "tiktoken_model_name",
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"tool_mode": false,
"trace_as_input": true,
"trace_as_metadata": true,
"type": "str",
"value": ""
}
},
"tool_mode": false
},
"selected_output": "embeddings",
"type": "OpenAIEmbeddings"
},
"dragging": false,
"height": 320,
"id": "OpenAIEmbeddings-joRJ6",
"measured": {
"height": 320,
"width": 320
},
"position": {
"x": 1704.8491676318172,
"y": 1879.144249471858
},
"positionAbsolute": {
"x": 1690.9220896443658,
"y": 1866.483269483266
},
"selected": false,
"type": "genericNode",
"width": 320
},
{
"data": {
"id": "note-Bm5Xw",
"node": {
"description": "### 💡 Add your OpenAI API key here 👇",
"display_name": "",
"documentation": "",
"template": {
"backgroundColor": "transparent"
}
},
"type": "note"
},
"dragging": false,
"height": 324,
"id": "note-Bm5Xw",
"measured": {
"height": 324,
"width": 324
},
"position": {
"x": 1692.2322233423606,
"y": 1821.9077961087607
},
"positionAbsolute": {
"x": 1692.2322233423606,
"y": 1821.9077961087607
},
"selected": false,
"type": "noteNode",
"width": 324
},
{
"data": {
"id": "File-PSU37",
"node": {
"base_classes": [
"Message"
],
"beta": false,
"conditional_paths": [],
"custom_fields": {},
"description": "Loads content from files with optional advanced document processing and export using Docling.",
"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": "2025-09-09T02:18:48.064Z",
"legacy": false,
"lf_version": "1.5.0.post2",
"metadata": {
"code_hash": "086578fbbd54",
"dependencies": {
"dependencies": [
{
"name": "langflow",
"version": "1.5.0.post2"
},
{
"name": "anyio",
"version": "4.10.0"
}
],
"total_dependencies": 2
},
"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__"
},
{
"allows_loop": false,
"cache": true,
"display_name": "File Path",
"group_outputs": false,
"hidden": null,
"method": "load_files_path",
"name": "path",
"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.",
"list": false,
"list_add_label": "Add More",
"name": "advanced_mode",
"placeholder": "",
"real_time_refresh": true,
"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": "\"\"\"Enhanced file component with clearer structure and Docling isolation.\n\nNotes:\n-----\n- Functionality is preserved with minimal behavioral changes.\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 TYPE_CHECKING, Any\n\nfrom langflow.base.data.base_file import BaseFileComponent\nfrom langflow.base.data.utils import TEXT_FILE_TYPES, parallel_load_data, parse_text_file_to_data\nfrom langflow.io import (\n BoolInput,\n DropdownInput,\n FileInput,\n IntInput,\n MessageTextInput,\n Output,\n StrInput,\n)\nfrom langflow.schema.data import Data\nfrom langflow.schema.message import Message\nimport anyio\nfrom langflow.services.storage.utils import build_content_type_from_extension\nif TYPE_CHECKING:\n from langflow.schema import DataFrame\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 files with optional advanced document processing and export using Docling.\"\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 \"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 *TEXT_FILE_TYPES,\n ]\n\n # Fixed export settings used when markdown export is requested.\n EXPORT_FORMAT = \"Markdown\"\n IMAGE_MODE = \"placeholder\"\n\n # ---- Inputs / Outputs (kept as close to original as possible) -------------------\n _base_inputs = deepcopy(BaseFileComponent._base_inputs)\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 ),\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 ),\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=[\"\", \"easyocr\"],\n value=\"\",\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 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 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\"]:\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\", method=\"load_files_advanced\"),\n )\n frontend_node[\"outputs\"].append(\n Output(display_name=\"Markdown\", name=\"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\": str(self.ocr_engine) if getattr(self, \"ocr_engine\", \"\") else None,\n }\n\n # The child is a tiny, self-contained script to keep memory/state isolated.\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 if strategy == \"latest\" and pipeline == \"standard\":\n try:\n from docling.datamodel.pipeline_options import PdfPipelineOptions # type: ignore\n from docling.document_converter import PdfFormatOption # type: ignore\n pipe = PdfPipelineOptions()\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 pipe.do_ocr = False\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 return DocumentConverter(format_options=fmt)\n except Exception:\n return DocumentConverter()\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_advanced(self) -> DataFrame:\n \"\"\"Load files using advanced Docling processing and export to an advanced format.\"\"\"\n self.markdown = False\n return self.load_files()\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()\n return Message(text=str(result.text[0]))\n \n async def load_files_message(self) -> Message:\n \"\"\"Load files and return as Message.\n \n Returns:\n Message: Message containing all file data\n \"\"\"\n data_list = self.load_files_core()\n if not data_list:\n return Message() # No data -> empty message\n \n sep: str = getattr(self, \"separator\", \"\\n\\n\") or \"\\n\\n\"\n \n parts: list[str] = []\n metadata = {} # Initialize as empty dict instead of None\n \n for d in data_list:\n # Prefer explicit text if available, fall back to full dict, lastly str()\n text = (getattr(d, \"get_text\", lambda: None)() or d.data.get(\"text\")) if isinstance(d.data, dict) else None\n parts.append(text if text is not None else str(d))\n \n # Set metadata from first file (or you could combine metadata from all files)\n if not metadata and hasattr(d, 'file_path'):\n file_path = d.file_path\n # Get filename\n file_path_obj = anyio.Path(file_path)\n file_size_stat = await file_path_obj.stat()\n filesize = file_size_stat.st_size\n filename = file_path_obj.name\n metadata[\"filename\"] = filename\n metadata[\"file_size\"] = filesize\n extension = filename.split(\".\")[-1]\n if extension:\n metadata[\"mimetype\"] = build_content_type_from_extension(filename.split(\".\")[-1])\n \n # Add other common metadata fields if available\n if hasattr(d, 'data') and isinstance(d.data, dict):\n # Copy relevant metadata fields\n for field in ['mimetype', 'file_size', 'created_time', 'modified_time']:\n if field in d.data:\n metadata[field] = d.data[field]\n self.log(metadata)\n return Message(text=sep.join(parts), **metadata)\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,
"info": "OCR engine to use. Only available when pipeline is set to 'standard'.",
"name": "ocr_engine",
"options": [
"",
"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": [
"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",
"txt",
"md",
"mdx",
"csv",
"json",
"yaml",
"yml",
"xml",
"html",
"htm",
"pdf",
"docx",
"py",
"sh",
"sql",
"js",
"ts",
"tsx",
"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, txt, md, mdx, csv, json, yaml, yml, xml, html, htm, pdf, docx, py, sh, sql, js, ts, tsx; optionally bundled in file extensions: zip, tar, tgz, bz2, gz",
"list": true,
"list_add_label": "Add More",
"load_from_db": false,
"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,
"info": "Docling pipeline to use",
"name": "pipeline",
"options": [
"standard",
"vlm"
],
"options_metadata": [],
"placeholder": "",
"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": 275,
"width": 320
},
"position": {
"x": 1330.7650978046952,
"y": 1431.5905495627503
},
"selected": false,
"type": "genericNode"
},
{
"data": {
"id": "OpenSearchHybrid-Ve6bS",
"node": {
"base_classes": [
"Data",
"DataFrame",
"VectorStore"
],
"beta": false,
"conditional_paths": [],
"custom_fields": {},
"description": "Hybrid search: KNN + keyword, with optional filters, min_score, and aggregations.",
"display_name": "OpenSearch (Hybrid)",
"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,
"metadata": {
"code_hash": "deee3f04cb47",
"dependencies": {
"dependencies": [
{
"name": "langflow",
"version": "1.5.0.post2"
},
{
"name": "opensearchpy",
"version": "2.8.0"
}
],
"total_dependencies": 2
},
"module": "custom_components.opensearch_hybrid"
},
"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,
"selected": "Data",
"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": true,
"method": "as_vector_store",
"name": "vectorstoreconnection",
"options": null,
"required_inputs": null,
"selected": "VectorStore",
"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": "Auth Mode",
"dynamic": false,
"info": "Choose Basic (username/password) or JWT (Bearer token).",
"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, Dict, List, Optional\n\nfrom langflow.base.vectorstores.model import (\n LCVectorStoreComponent,\n check_cached_vector_store,\n)\nfrom langflow.base.vectorstores.vector_store_connection_decorator import (\n vector_store_connection,\n)\nfrom langflow.io import (\n BoolInput,\n DropdownInput,\n HandleInput,\n IntInput,\n MultilineInput,\n SecretStrInput,\n StrInput,\n TableInput,\n)\nfrom langflow.logging import logger\nfrom langflow.schema.data import Data\nfrom opensearchpy import OpenSearch, helpers\n\n\n@vector_store_connection\nclass OpenSearchHybridComponent(LCVectorStoreComponent):\n \"\"\"OpenSearch hybrid search: KNN (k=10, boost=0.7) + multi_match (boost=0.3) with optional filters & min_score.\"\"\"\n\n display_name: str = \"OpenSearch (Hybrid)\"\n name: str = \"OpenSearchHybrid\"\n icon: str = \"OpenSearch\"\n description: str = \"Hybrid search: KNN + keyword, with optional filters, min_score, and aggregations.\"\n\n # Keys we consider baseline\n default_keys: list[str] = [\n \"opensearch_url\",\n \"index_name\",\n *[\n i.name for i in LCVectorStoreComponent.inputs\n ], # 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=\"Ingestion Metadata\",\n info=\"Key value pairs to be inserted into each ingested document.\",\n table_schema=[\n {\n \"name\": \"key\",\n \"display_name\": \"Key\",\n \"type\": \"str\",\n \"description\": \"Key name\",\n },\n {\n \"name\": \"value\",\n \"display_name\": \"Value\",\n \"type\": \"str\",\n \"description\": \"Value of the metadata\",\n },\n ],\n value=[],\n advanced=True,\n ),\n StrInput(\n name=\"opensearch_url\",\n display_name=\"OpenSearch URL\",\n value=\"http://localhost:9200\",\n info=\"URL for your OpenSearch cluster.\",\n ),\n StrInput(\n name=\"index_name\",\n display_name=\"Index Name\",\n value=\"langflow\",\n info=\"The index to search.\",\n ),\n DropdownInput(\n name=\"engine\",\n display_name=\"Engine\",\n options=[\"jvector\", \"nmslib\", \"faiss\", \"lucene\"],\n value=\"jvector\",\n info=\"Vector search engine to use.\",\n advanced=True,\n ),\n DropdownInput(\n name=\"space_type\",\n display_name=\"Space Type\",\n options=[\"l2\", \"l1\", \"cosinesimil\", \"linf\", \"innerproduct\"],\n value=\"l2\",\n info=\"Distance metric for vector similarity.\",\n advanced=True,\n ),\n IntInput(\n name=\"ef_construction\",\n display_name=\"EF Construction\",\n value=512,\n info=\"Size of the dynamic list used during k-NN graph creation.\",\n advanced=True,\n ),\n IntInput(\n name=\"m\",\n display_name=\"M Parameter\",\n value=16,\n info=\"Number of bidirectional links created for each new element.\",\n advanced=True,\n ),\n *LCVectorStoreComponent.inputs, # includes search_query, add_documents, etc.\n HandleInput(\n name=\"embedding\", display_name=\"Embedding\", input_types=[\"Embeddings\"]\n ),\n StrInput(\n name=\"vector_field\",\n display_name=\"Vector Field\",\n value=\"chunk_embedding\",\n advanced=True,\n info=\"Vector field used for KNN.\",\n ),\n IntInput(\n name=\"number_of_results\",\n display_name=\"Default Size (limit)\",\n value=10,\n advanced=True,\n info=\"Default number of hits when no limit provided in filter_expression.\",\n ),\n MultilineInput(\n name=\"filter_expression\",\n display_name=\"Filter Expression (JSON)\",\n value=\"\",\n info=(\n \"Optional JSON to control filters/limit/score threshold.\\n\"\n \"Accepted shapes:\\n\"\n '1) {\"filter\": [ {\"term\": {\"filename\":\"foo\"}}, {\"terms\":{\"owner\":[\"u1\",\"u2\"]}} ], \"limit\": 10, \"score_threshold\": 1.6 }\\n'\n '2) Context-style maps: {\"data_sources\":[\"fileA\"], \"document_types\":[\"application/pdf\"], \"owners\":[\"123\"]}\\n'\n \"Placeholders with __IMPOSSIBLE_VALUE__ are ignored.\"\n ),\n ),\n # ----- Auth controls (dynamic) -----\n DropdownInput(\n name=\"auth_mode\",\n display_name=\"Auth Mode\",\n value=\"basic\",\n options=[\"basic\", \"jwt\"],\n info=\"Choose Basic (username/password) or JWT (Bearer token).\",\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=\"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=True,\n show=True,\n info=\"Paste a valid JWT (sent as a header).\",\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(name=\"use_ssl\", display_name=\"Use SSL\", value=True, advanced=True),\n BoolInput(\n name=\"verify_certs\",\n display_name=\"Verify Certificates\",\n value=False,\n advanced=True,\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 \"\"\"For Approximate k-NN Search, this is the default mapping to create index.\"\"\"\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 AOSS with the engine.\"\"\"\n if is_aoss and engine != \"nmslib\" and engine != \"faiss\":\n raise ValueError(\n \"Amazon OpenSearch Service Serverless only \"\n \"supports `nmslib` or `faiss` engines\"\n )\n\n def _is_aoss_enabled(self, http_auth: Any) -> bool:\n \"\"\"Check if the service is http_auth is set as `aoss`.\"\"\"\n if (\n http_auth is not None\n and hasattr(http_auth, \"service\")\n and http_auth.service == \"aoss\"\n ):\n return True\n return False\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: Optional[List[dict]] = None,\n ids: Optional[List[str]] = None,\n vector_field: str = \"vector_field\",\n text_field: str = \"text\",\n mapping: Optional[Dict] = None,\n max_chunk_bytes: Optional[int] = 1 * 1024 * 1024,\n is_aoss: bool = False,\n ) -> List[str]:\n \"\"\"Bulk Ingest Embeddings into given index.\"\"\"\n if not mapping:\n mapping = dict()\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 self.log(metadatas[i])\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 mode = (self.auth_mode or \"basic\").strip().lower()\n if mode == \"jwt\":\n token = (self.jwt_token or \"\").strip()\n if not token:\n raise ValueError(\"Auth Mode is 'jwt' but no jwt_token was provided.\")\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 raise ValueError(\"Auth Mode is 'basic' but username/password are missing.\")\n return {\"http_auth\": (user, pwd)}\n\n def build_client(self) -> OpenSearch:\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 # 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 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\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 raise ValueError(\"Embedding handle is required to embed documents.\")\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, 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(\n f\"Indexing {len(texts)} documents into '{self.index_name}' with proper KNN mapping...\"\n )\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 \"\"\"\n Accepts either:\n A) {\"filter\":[ ...term/terms objects... ], \"limit\":..., \"score_threshold\":...}\n B) Context-style: {\"data_sources\":[...], \"document_types\":[...], \"owners\":[...]}\n Returns a list of OS filter clauses (term/terms), skipping placeholders and empty terms.\n \"\"\"\n\n if not filter_obj:\n return []\n\n # If it’s a string, try to parse it once\n if isinstance(filter_obj, str):\n try:\n filter_obj = json.loads(filter_obj)\n except Exception:\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 clauses: List[dict] = []\n for f in raw or []:\n if (\n \"term\" in f\n and isinstance(f[\"term\"], dict)\n and not self._is_placeholder_term(f[\"term\"])\n ):\n 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 clauses.append(f)\n return 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 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 clauses.append({\"term\": {field: \"__IMPOSSIBLE_VALUE__\"}})\n elif len(values) == 1:\n if values[0] != \"__IMPOSSIBLE_VALUE__\":\n clauses.append({\"term\": {field: values[0]}})\n else:\n clauses.append({\"terms\": {field: values}})\n return clauses\n\n # ---------- search (single hybrid path matching your tool) ----------\n def search(self, query: str | None = None) -> list[dict[str, Any]]:\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 raise ValueError(f\"Invalid filter_expression JSON: {e}\") from e\n\n if not self.embedding:\n raise ValueError(\n \"Embedding is required to run hybrid search (KNN + keyword).\"\n )\n\n # Embed the query\n vec = self.embedding.embed_query(q)\n\n # Build filter clauses (accept both shapes)\n 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 clauses:\n body[\"query\"][\"bool\"][\"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 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(\n self, build_config: dict, field_value: str, field_name: str | None = None\n ) -> dict:\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 return build_config\n\n except Exception as e:\n self.log(f\"update_build_config error: {e}\")\n return build_config\n"
},
"docs_metadata": {
"_input_type": "TableInput",
"advanced": true,
"display_name": "Ingestion Metadata",
"dynamic": false,
"info": "Key value pairs to be inserted into each ingested document.",
"is_list": true,
"list_add_label": "Add More",
"name": "docs_metadata",
"placeholder": "",
"required": false,
"show": true,
"table_icon": "Table",
"table_schema": {
"columns": [
{
"default": "None",
"description": "Key name",
"disable_edit": false,
"display_name": "Key",
"edit_mode": "popover",
"filterable": true,
"formatter": "text",
"hidden": false,
"name": "key",
"sortable": true,
"type": "str"
},
{
"default": "None",
"description": "Value of the metadata",
"disable_edit": false,
"display_name": "Value",
"edit_mode": "popover",
"filterable": true,
"formatter": "text",
"hidden": false,
"name": "value",
"sortable": true,
"type": "str"
}
]
},
"title_case": false,
"tool_mode": false,
"trace_as_metadata": true,
"trigger_icon": "Table",
"trigger_text": "Open table",
"type": "table",
"value": []
},
"ef_construction": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "EF Construction",
"dynamic": false,
"info": "Size of the dynamic list used during k-NN graph creation.",
"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": "Engine",
"dynamic": false,
"info": "Vector search engine to use.",
"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": "Filter Expression (JSON)",
"dynamic": false,
"info": "Optional JSON to control filters/limit/score threshold.\nAccepted shapes:\n1) {\"filter\": [ {\"term\": {\"filename\":\"foo\"}}, {\"terms\":{\"owner\":[\"u1\",\"u2\"]}} ], \"limit\": 10, \"score_threshold\": 1.6 }\n2) Context-style maps: {\"data_sources\":[\"fileA\"], \"document_types\":[\"application/pdf\"], \"owners\":[\"123\"]}\nPlaceholders with __IMPOSSIBLE_VALUE__ are ignored.",
"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 index to search.",
"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": "Paste a valid JWT (sent as a header).",
"input_types": [],
"load_from_db": false,
"name": "jwt_token",
"password": true,
"placeholder": "",
"required": false,
"show": true,
"title_case": false,
"type": "str",
"value": ""
},
"m": {
"_input_type": "IntInput",
"advanced": true,
"display_name": "M Parameter",
"dynamic": false,
"info": "Number of bidirectional links created for each new element.",
"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 Size (limit)",
"dynamic": false,
"info": "Default number of hits when no limit provided in 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": "URL for your OpenSearch cluster.",
"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": "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": "Space Type",
"dynamic": false,
"info": "Distance metric for vector similarity.",
"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",
"dynamic": false,
"info": "",
"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",
"dynamic": false,
"info": "Vector field used for KNN.",
"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 Certificates",
"dynamic": false,
"info": "",
"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": "search_results",
"showNode": true,
"type": "OpenSearchHybrid"
},
"dragging": false,
"id": "OpenSearchHybrid-Ve6bS",
"measured": {
"height": 761,
"width": 320
},
"position": {
"x": 2218.9287723423276,
"y": 1332.2598463956504
},
"selected": true,
"type": "genericNode"
}
],
"viewport": {
"x": -919.0070567185035,
"y": -955.5333976627492,
"zoom": 0.8337061732891438
}
},
"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": "1.5.0.post2",
"name": "OpenSearch Ingestion Flow",
"tags": [
"openai",
"astradb",
"rag",
"q-a"
]
}
Reference in a new issue View git blame Copy permalink