2207 lines
No EOL
129 KiB
JSON
2207 lines
No EOL
129 KiB
JSON
{
|
|
"data": {
|
|
"edges": [
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "SplitText",
|
|
"id": "SplitText-3ZI5B",
|
|
"name": "dataframe",
|
|
"output_types": [
|
|
"DataFrame"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "ingest_data",
|
|
"id": "OpenSearchHybrid-XtKoA",
|
|
"inputTypes": [
|
|
"Data",
|
|
"DataFrame"
|
|
],
|
|
"type": "other"
|
|
}
|
|
},
|
|
"id": "reactflow__edge-SplitText-3ZI5B{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-3ZI5Bœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-OpenSearchHybrid-XtKoA{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchHybrid-XtKoAœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}",
|
|
"selected": false,
|
|
"source": "SplitText-3ZI5B",
|
|
"sourceHandle": "{œdataTypeœ:œSplitTextœ,œidœ:œSplitText-3ZI5Bœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}",
|
|
"target": "OpenSearchHybrid-XtKoA",
|
|
"targetHandle": "{œfieldNameœ:œingest_dataœ,œidœ:œOpenSearchHybrid-XtKoAœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "OpenAIEmbeddings",
|
|
"id": "OpenAIEmbeddings-mP45L",
|
|
"name": "embeddings",
|
|
"output_types": [
|
|
"Embeddings"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "embedding",
|
|
"id": "OpenSearchHybrid-XtKoA",
|
|
"inputTypes": [
|
|
"Embeddings"
|
|
],
|
|
"type": "other"
|
|
}
|
|
},
|
|
"id": "reactflow__edge-OpenAIEmbeddings-mP45L{œdataTypeœ:œOpenAIEmbeddingsœ,œidœ:œOpenAIEmbeddings-mP45Lœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-OpenSearchHybrid-XtKoA{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchHybrid-XtKoAœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
|
|
"selected": false,
|
|
"source": "OpenAIEmbeddings-mP45L",
|
|
"sourceHandle": "{œdataTypeœ:œOpenAIEmbeddingsœ,œidœ:œOpenAIEmbeddings-mP45Lœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}",
|
|
"target": "OpenSearchHybrid-XtKoA",
|
|
"targetHandle": "{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchHybrid-XtKoAœ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "DoclingRemote",
|
|
"id": "DoclingRemote-78KoX",
|
|
"name": "dataframe",
|
|
"output_types": [
|
|
"DataFrame"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "data_inputs",
|
|
"id": "ExportDoclingDocument-xFoCI",
|
|
"inputTypes": [
|
|
"Data",
|
|
"DataFrame"
|
|
],
|
|
"type": "other"
|
|
}
|
|
},
|
|
"id": "xy-edge__DoclingRemote-78KoX{œdataTypeœ:œDoclingRemoteœ,œidœ:œDoclingRemote-78KoXœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-ExportDoclingDocument-xFoCI{œfieldNameœ:œdata_inputsœ,œidœ:œExportDoclingDocument-xFoCIœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}",
|
|
"selected": false,
|
|
"source": "DoclingRemote-78KoX",
|
|
"sourceHandle": "{œdataTypeœ:œDoclingRemoteœ,œidœ:œDoclingRemote-78KoXœ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}",
|
|
"target": "ExportDoclingDocument-xFoCI",
|
|
"targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œExportDoclingDocument-xFoCIœ,œinputTypesœ:[œDataœ,œDataFrameœ],œtypeœ:œotherœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "ExportDoclingDocument",
|
|
"id": "ExportDoclingDocument-xFoCI",
|
|
"name": "data",
|
|
"output_types": [
|
|
"Data"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "data_inputs",
|
|
"id": "SplitText-3ZI5B",
|
|
"inputTypes": [
|
|
"Data",
|
|
"DataFrame",
|
|
"Message"
|
|
],
|
|
"type": "other"
|
|
}
|
|
},
|
|
"id": "xy-edge__ExportDoclingDocument-xFoCI{œdataTypeœ:œExportDoclingDocumentœ,œidœ:œExportDoclingDocument-xFoCIœ,œnameœ:œdataœ,œoutput_typesœ:[œDataœ]}-SplitText-3ZI5B{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-3ZI5Bœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
|
|
"selected": false,
|
|
"source": "ExportDoclingDocument-xFoCI",
|
|
"sourceHandle": "{œdataTypeœ:œExportDoclingDocumentœ,œidœ:œExportDoclingDocument-xFoCIœ,œnameœ:œdataœ,œoutput_typesœ:[œDataœ]}",
|
|
"target": "SplitText-3ZI5B",
|
|
"targetHandle": "{œfieldNameœ:œdata_inputsœ,œidœ:œSplitText-3ZI5Bœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}"
|
|
}
|
|
],
|
|
"nodes": [
|
|
{
|
|
"data": {
|
|
"description": "Split text into chunks based on specified criteria.",
|
|
"display_name": "Split Text",
|
|
"id": "SplitText-3ZI5B",
|
|
"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,
|
|
"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-3ZI5B",
|
|
"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-mP45L",
|
|
"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,
|
|
"metadata": {
|
|
"code_hash": "8a658ed6d4c9",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "langchain_openai",
|
|
"version": "0.3.23"
|
|
},
|
|
{
|
|
"name": "lfx",
|
|
"version": null
|
|
}
|
|
],
|
|
"total_dependencies": 2
|
|
},
|
|
"module": "custom_components.openai_embeddings"
|
|
},
|
|
"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",
|
|
"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
|
|
},
|
|
"client": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Client",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"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 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 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,
|
|
"list_add_label": "Add More",
|
|
"name": "default_headers",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": 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,
|
|
"list_add_label": "Add More",
|
|
"name": "default_query",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": 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,
|
|
"list_add_label": "Add More",
|
|
"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,
|
|
"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": ""
|
|
},
|
|
"embedding_ctx_length": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Embedding Context Length",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "embedding_ctx_length",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": 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,
|
|
"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",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"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": "",
|
|
"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": {}
|
|
},
|
|
"openai_api_base": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "OpenAI API Base",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"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,
|
|
"list_add_label": "Add More",
|
|
"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,
|
|
"list_add_label": "Add More",
|
|
"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,
|
|
"list_add_label": "Add More",
|
|
"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,
|
|
"list_add_label": "Add More",
|
|
"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,
|
|
"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
|
|
},
|
|
"skip_empty": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Skip Empty",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "skip_empty",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": 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,
|
|
"list_add_label": "Add More",
|
|
"name": "tiktoken_enable",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": 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,
|
|
"list_add_label": "Add More",
|
|
"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-mP45L",
|
|
"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-59mzY",
|
|
"node": {
|
|
"description": "### 💡 Add your OpenAI API key here 👇",
|
|
"display_name": "",
|
|
"documentation": "",
|
|
"template": {
|
|
"backgroundColor": "transparent"
|
|
}
|
|
},
|
|
"type": "note"
|
|
},
|
|
"dragging": false,
|
|
"height": 324,
|
|
"id": "note-59mzY",
|
|
"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": "OpenSearchHybrid-XtKoA",
|
|
"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,
|
|
"metadata": {
|
|
"code_hash": "2720a7c68202",
|
|
"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,
|
|
"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": false,
|
|
"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": "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 \"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=(\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=True,\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 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 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": true,
|
|
"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.",
|
|
"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",
|
|
"name": "key",
|
|
"type": "str"
|
|
},
|
|
{
|
|
"description": "Value of the metadata",
|
|
"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": []
|
|
},
|
|
"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": "search_results",
|
|
"showNode": true,
|
|
"type": "OpenSearchVectorStoreComponent"
|
|
},
|
|
"dragging": false,
|
|
"id": "OpenSearchHybrid-XtKoA",
|
|
"measured": {
|
|
"height": 737,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": 2218.9287723423276,
|
|
"y": 1332.2598463956504
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"id": "DoclingRemote-78KoX",
|
|
"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": "1.6.0",
|
|
"metadata": {
|
|
"code_hash": "930312ffe40c",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "httpx",
|
|
"version": "0.28.1"
|
|
},
|
|
{
|
|
"name": "docling_core",
|
|
"version": "2.45.0"
|
|
},
|
|
{
|
|
"name": "pydantic",
|
|
"version": "2.10.6"
|
|
},
|
|
{
|
|
"name": "lfx",
|
|
"version": null
|
|
}
|
|
],
|
|
"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\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 base_url = f\"{self.api_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-78KoX",
|
|
"measured": {
|
|
"height": 475,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": 974.2998232996713,
|
|
"y": 1337.9345348080217
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"id": "ExportDoclingDocument-xFoCI",
|
|
"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",
|
|
"legacy": false,
|
|
"lf_version": "1.6.0",
|
|
"metadata": {
|
|
"code_hash": "4de16ddd37ac",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "docling_core",
|
|
"version": "2.45.0"
|
|
},
|
|
{
|
|
"name": "lfx",
|
|
"version": null
|
|
}
|
|
],
|
|
"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",
|
|
"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",
|
|
"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,
|
|
"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,
|
|
"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": "data",
|
|
"showNode": true,
|
|
"type": "ExportDoclingDocument"
|
|
},
|
|
"dragging": false,
|
|
"id": "ExportDoclingDocument-xFoCI",
|
|
"measured": {
|
|
"height": 347,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": 1354.7013688969873,
|
|
"y": 1365.2986945152204
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
}
|
|
],
|
|
"viewport": {
|
|
"x": -747.2506879716952,
|
|
"y": -1001.2271322529787,
|
|
"zoom": 0.8347026947181932
|
|
}
|
|
},
|
|
"description": "Load your data for chat context with Retrieval Augmented Generation.",
|
|
"endpoint_name": null,
|
|
"id": "1402618b-e6d1-4ff2-9a11-d6ce71186915",
|
|
"is_component": false,
|
|
"last_tested_version": "1.6.0",
|
|
"name": "OpenSearch Ingestion Flow Docling Serve",
|
|
"tags": [
|
|
"openai",
|
|
"astradb",
|
|
"rag",
|
|
"q-a"
|
|
]
|
|
} |