4122 lines
326 KiB
JSON
4122 lines
326 KiB
JSON
{
|
|
"data": {
|
|
"edges": [
|
|
{
|
|
"animated": false,
|
|
"className": "not-running",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "ParserComponent",
|
|
"id": "ParserComponent-tZs7s",
|
|
"name": "parsed_text",
|
|
"output_types": [
|
|
"Message"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "docs",
|
|
"id": "Prompt Template-Wo6kR",
|
|
"inputTypes": [
|
|
"Message"
|
|
],
|
|
"type": "str"
|
|
}
|
|
},
|
|
"id": "xy-edge__ParserComponent-tZs7s{œdataTypeœ:œParserComponentœ,œidœ:œParserComponent-tZs7sœ,œnameœ:œparsed_textœ,œoutput_typesœ:[œMessageœ]}-Prompt Template-Wo6kR{œfieldNameœ:œdocsœ,œidœ:œPrompt Template-Wo6kRœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
|
|
"selected": false,
|
|
"source": "ParserComponent-tZs7s",
|
|
"sourceHandle": "{œdataTypeœ:œParserComponentœ,œidœ:œParserComponent-tZs7sœ,œnameœ:œparsed_textœ,œoutput_typesœ:[œMessageœ]}",
|
|
"target": "Prompt Template-Wo6kR",
|
|
"targetHandle": "{œfieldNameœ:œdocsœ,œidœ:œPrompt Template-Wo6kRœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "ChatInput",
|
|
"id": "ChatInput-7W1BE",
|
|
"name": "message",
|
|
"output_types": [
|
|
"Message"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "prompt",
|
|
"id": "Prompt Template-Wo6kR",
|
|
"inputTypes": [
|
|
"Message"
|
|
],
|
|
"type": "str"
|
|
}
|
|
},
|
|
"id": "xy-edge__ChatInput-7W1BE{œdataTypeœ:œChatInputœ,œidœ:œChatInput-7W1BEœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}-Prompt Template-Wo6kR{œfieldNameœ:œpromptœ,œidœ:œPrompt Template-Wo6kRœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
|
|
"selected": false,
|
|
"source": "ChatInput-7W1BE",
|
|
"sourceHandle": "{œdataTypeœ:œChatInputœ,œidœ:œChatInput-7W1BEœ,œnameœ:œmessageœ,œoutput_typesœ:[œMessageœ]}",
|
|
"target": "Prompt Template-Wo6kR",
|
|
"targetHandle": "{œfieldNameœ:œpromptœ,œidœ:œPrompt Template-Wo6kRœ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "Prompt Template",
|
|
"id": "Prompt Template-Wo6kR",
|
|
"name": "prompt",
|
|
"output_types": [
|
|
"Message"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "input_value",
|
|
"id": "LanguageModelComponent-KdXf9",
|
|
"inputTypes": [
|
|
"Message"
|
|
],
|
|
"type": "str"
|
|
}
|
|
},
|
|
"id": "xy-edge__Prompt Template-Wo6kR{œdataTypeœ:œPrompt Templateœ,œidœ:œPrompt Template-Wo6kRœ,œnameœ:œpromptœ,œoutput_typesœ:[œMessageœ]}-LanguageModelComponent-KdXf9{œfieldNameœ:œinput_valueœ,œidœ:œLanguageModelComponent-KdXf9œ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
|
|
"selected": false,
|
|
"source": "Prompt Template-Wo6kR",
|
|
"sourceHandle": "{œdataTypeœ:œPrompt Templateœ,œidœ:œPrompt Template-Wo6kRœ,œnameœ:œpromptœ,œoutput_typesœ:[œMessageœ]}",
|
|
"target": "LanguageModelComponent-KdXf9",
|
|
"targetHandle": "{œfieldNameœ:œinput_valueœ,œidœ:œLanguageModelComponent-KdXf9œ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "LanguageModelComponent",
|
|
"id": "LanguageModelComponent-KdXf9",
|
|
"name": "text_output",
|
|
"output_types": [
|
|
"Message"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "input_value",
|
|
"id": "ChatOutput-axewE",
|
|
"inputTypes": [
|
|
"Data",
|
|
"DataFrame",
|
|
"Message"
|
|
],
|
|
"type": "other"
|
|
}
|
|
},
|
|
"id": "xy-edge__LanguageModelComponent-KdXf9{œdataTypeœ:œLanguageModelComponentœ,œidœ:œLanguageModelComponent-KdXf9œ,œnameœ:œtext_outputœ,œoutput_typesœ:[œMessageœ]}-ChatOutput-axewE{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-axewEœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}",
|
|
"selected": false,
|
|
"source": "LanguageModelComponent-KdXf9",
|
|
"sourceHandle": "{œdataTypeœ:œLanguageModelComponentœ,œidœ:œLanguageModelComponent-KdXf9œ,œnameœ:œtext_outputœ,œoutput_typesœ:[œMessageœ]}",
|
|
"target": "ChatOutput-axewE",
|
|
"targetHandle": "{œfieldNameœ:œinput_valueœ,œidœ:œChatOutput-axewEœ,œinputTypesœ:[œDataœ,œDataFrameœ,œMessageœ],œtypeœ:œotherœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "EmbeddingModel",
|
|
"id": "EmbeddingModel-ooLFP",
|
|
"name": "embeddings",
|
|
"output_types": [
|
|
"Embeddings"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "embedding",
|
|
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"inputTypes": [
|
|
"Embeddings"
|
|
],
|
|
"type": "other"
|
|
}
|
|
},
|
|
"id": "xy-edge__EmbeddingModel-ooLFP{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-ooLFPœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
|
|
"selected": false,
|
|
"source": "EmbeddingModel-ooLFP",
|
|
"sourceHandle": "{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-ooLFPœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}",
|
|
"target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"targetHandle": "{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "EmbeddingModel",
|
|
"id": "EmbeddingModel-EzcW6",
|
|
"name": "embeddings",
|
|
"output_types": [
|
|
"Embeddings"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "embedding",
|
|
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"inputTypes": [
|
|
"Embeddings"
|
|
],
|
|
"type": "other"
|
|
}
|
|
},
|
|
"id": "xy-edge__EmbeddingModel-EzcW6{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-EzcW6œ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
|
|
"selected": false,
|
|
"source": "EmbeddingModel-EzcW6",
|
|
"sourceHandle": "{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-EzcW6œ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}",
|
|
"target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"targetHandle": "{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "EmbeddingModel",
|
|
"id": "EmbeddingModel-cONxU",
|
|
"name": "embeddings",
|
|
"output_types": [
|
|
"Embeddings"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "embedding",
|
|
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"inputTypes": [
|
|
"Embeddings"
|
|
],
|
|
"type": "other"
|
|
}
|
|
},
|
|
"id": "xy-edge__EmbeddingModel-cONxU{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-cONxUœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}",
|
|
"selected": false,
|
|
"source": "EmbeddingModel-cONxU",
|
|
"sourceHandle": "{œdataTypeœ:œEmbeddingModelœ,œidœ:œEmbeddingModel-cONxUœ,œnameœ:œembeddingsœ,œoutput_typesœ:[œEmbeddingsœ]}",
|
|
"target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"targetHandle": "{œfieldNameœ:œembeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œinputTypesœ:[œEmbeddingsœ],œtypeœ:œotherœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"className": "",
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding",
|
|
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"name": "dataframe",
|
|
"output_types": [
|
|
"DataFrame"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "input_data",
|
|
"id": "ParserComponent-tZs7s",
|
|
"inputTypes": [
|
|
"DataFrame",
|
|
"Data"
|
|
],
|
|
"type": "other"
|
|
}
|
|
},
|
|
"id": "xy-edge__OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3{œdataTypeœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}-ParserComponent-tZs7s{œfieldNameœ:œinput_dataœ,œidœ:œParserComponent-tZs7sœ,œinputTypesœ:[œDataFrameœ,œDataœ],œtypeœ:œotherœ}",
|
|
"selected": false,
|
|
"source": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"sourceHandle": "{œdataTypeœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbeddingœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œnameœ:œdataframeœ,œoutput_typesœ:[œDataFrameœ]}",
|
|
"target": "ParserComponent-tZs7s",
|
|
"targetHandle": "{œfieldNameœ:œinput_dataœ,œidœ:œParserComponent-tZs7sœ,œinputTypesœ:[œDataFrameœ,œDataœ],œtypeœ:œotherœ}"
|
|
},
|
|
{
|
|
"animated": false,
|
|
"data": {
|
|
"sourceHandle": {
|
|
"dataType": "TextInput",
|
|
"id": "TextInput-4cEHx",
|
|
"name": "text",
|
|
"output_types": [
|
|
"Message"
|
|
]
|
|
},
|
|
"targetHandle": {
|
|
"fieldName": "filter_expression",
|
|
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"inputTypes": [
|
|
"Message"
|
|
],
|
|
"type": "str"
|
|
}
|
|
},
|
|
"id": "xy-edge__TextInput-4cEHx{œdataTypeœ:œTextInputœ,œidœ:œTextInput-4cEHxœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}-OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3{œfieldNameœ:œfilter_expressionœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}",
|
|
"selected": false,
|
|
"source": "TextInput-4cEHx",
|
|
"sourceHandle": "{œdataTypeœ:œTextInputœ,œidœ:œTextInput-4cEHxœ,œnameœ:œtextœ,œoutput_typesœ:[œMessageœ]}",
|
|
"target": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"targetHandle": "{œfieldNameœ:œfilter_expressionœ,œidœ:œOpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3œ,œinputTypesœ:[œMessageœ],œtypeœ:œstrœ}"
|
|
}
|
|
],
|
|
"nodes": [
|
|
{
|
|
"data": {
|
|
"id": "Prompt Template-Wo6kR",
|
|
"node": {
|
|
"base_classes": [
|
|
"Message"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {
|
|
"template": [
|
|
"prompt",
|
|
"docs"
|
|
]
|
|
},
|
|
"description": "Create a prompt template with dynamic variables.",
|
|
"display_name": "Prompt Template",
|
|
"documentation": "https://docs.langflow.org/components-prompts",
|
|
"edited": false,
|
|
"field_order": [
|
|
"template",
|
|
"tool_placeholder"
|
|
],
|
|
"frozen": false,
|
|
"icon": "braces",
|
|
"legacy": false,
|
|
"lf_version": "1.7.0.dev21",
|
|
"metadata": {
|
|
"code_hash": "7382d03ce412",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "lfx",
|
|
"version": null
|
|
}
|
|
],
|
|
"total_dependencies": 1
|
|
},
|
|
"module": "custom_components.prompt_template"
|
|
},
|
|
"minimized": false,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Prompt",
|
|
"group_outputs": false,
|
|
"hidden": null,
|
|
"method": "build_prompt",
|
|
"name": "prompt",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "Message",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"Message"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"priority": 0,
|
|
"template": {
|
|
"_type": "Component",
|
|
"code": {
|
|
"advanced": true,
|
|
"dynamic": true,
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "code",
|
|
"password": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "code",
|
|
"value": "from lfx.base.prompts.api_utils import process_prompt_template\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.inputs.inputs import DefaultPromptField\nfrom lfx.io import MessageTextInput, Output, PromptInput\nfrom lfx.schema.message import Message\nfrom lfx.template.utils import update_template_values\n\n\nclass PromptComponent(Component):\n display_name: str = \"Prompt Template\"\n description: str = \"Create a prompt template with dynamic variables.\"\n documentation: str = \"https://docs.langflow.org/components-prompts\"\n icon = \"braces\"\n trace_type = \"prompt\"\n name = \"Prompt Template\"\n priority = 0 # Set priority to 0 to make it appear first\n\n inputs = [\n PromptInput(name=\"template\", display_name=\"Template\"),\n MessageTextInput(\n name=\"tool_placeholder\",\n display_name=\"Tool Placeholder\",\n tool_mode=True,\n advanced=True,\n info=\"A placeholder input for tool mode.\",\n ),\n ]\n\n outputs = [\n Output(display_name=\"Prompt\", name=\"prompt\", method=\"build_prompt\"),\n ]\n\n async def build_prompt(self) -> Message:\n prompt = Message.from_template(**self._attributes)\n self.status = prompt.text\n return prompt\n\n def _update_template(self, frontend_node: dict):\n prompt_template = frontend_node[\"template\"][\"template\"][\"value\"]\n custom_fields = frontend_node[\"custom_fields\"]\n frontend_node_template = frontend_node[\"template\"]\n _ = process_prompt_template(\n template=prompt_template,\n name=\"template\",\n custom_fields=custom_fields,\n frontend_node_template=frontend_node_template,\n )\n return frontend_node\n\n async def update_frontend_node(self, new_frontend_node: dict, current_frontend_node: dict):\n \"\"\"This function is called after the code validation is done.\"\"\"\n frontend_node = await super().update_frontend_node(new_frontend_node, current_frontend_node)\n template = frontend_node[\"template\"][\"template\"][\"value\"]\n # Kept it duplicated for backwards compatibility\n _ = process_prompt_template(\n template=template,\n name=\"template\",\n custom_fields=frontend_node[\"custom_fields\"],\n frontend_node_template=frontend_node[\"template\"],\n )\n # Now that template is updated, we need to grab any values that were set in the current_frontend_node\n # and update the frontend_node with those values\n update_template_values(new_template=frontend_node, previous_template=current_frontend_node[\"template\"])\n return frontend_node\n\n def _get_fallback_input(self, **kwargs):\n return DefaultPromptField(**kwargs)\n"
|
|
},
|
|
"docs": {
|
|
"advanced": false,
|
|
"display_name": "docs",
|
|
"dynamic": false,
|
|
"field_type": "str",
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "docs",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"prompt": {
|
|
"advanced": false,
|
|
"display_name": "prompt",
|
|
"dynamic": false,
|
|
"field_type": "str",
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "prompt",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"template": {
|
|
"_input_type": "PromptInput",
|
|
"advanced": false,
|
|
"display_name": "Template",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "template",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"type": "prompt",
|
|
"value": "You are generating prompt nudges to help a user explore a corpus.\n\nTask:\n1) Skim the documents to infer common themes, entities, or tasks.\n2) Propose exactly three concise, distinct prompt nudges that encourage useful next queries.\n3) If the chat history is provided, use it to generate new questions that the user might have, based on the llm's response to his previous query. DO NOT repeat user questions.\n4) Make the nudges concise, close to 40 characters.\n5) The nudges are questions or commands that the user can make to the chatbot, which will respond looking at the corpus.\n4) Return strings only, separating the nudges by a newline. Don't include quotation marks.\n5) If any error occured, return blank. This will be used in production, so don't ask for more info or confirm a info like you're talking to me still. If, for some reason, you can't provide the nudges, your job failed and you just return blank.\nRules: Be brief. No duplicates. No explanations outside the strings of the nudges. English only.\n\nExamples:\n Show me this quarter's top 10 deals\n Summarize recent client interactions\n Search OpenSearch for mentions of our competitors\n\nChat history:\n{prompt}\n\nDocuments:\n{docs}\n\n"
|
|
},
|
|
"tool_placeholder": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Tool Placeholder",
|
|
"dynamic": false,
|
|
"info": "A placeholder input for tool mode.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "tool_placeholder",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": true,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"type": "str",
|
|
"value": ""
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"showNode": true,
|
|
"type": "Prompt Template"
|
|
},
|
|
"dragging": false,
|
|
"id": "Prompt Template-Wo6kR",
|
|
"measured": {
|
|
"height": 449,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": 1321.0365272581178,
|
|
"y": 1260.1086273287026
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"description": "Extracts text using a template.",
|
|
"display_name": "Parser",
|
|
"id": "ParserComponent-tZs7s",
|
|
"node": {
|
|
"base_classes": [
|
|
"Message"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {},
|
|
"description": "Extracts text using a template.",
|
|
"display_name": "Parser",
|
|
"documentation": "https://docs.langflow.org/parser",
|
|
"edited": false,
|
|
"field_order": [
|
|
"input_data",
|
|
"mode",
|
|
"pattern",
|
|
"sep"
|
|
],
|
|
"frozen": false,
|
|
"icon": "braces",
|
|
"legacy": false,
|
|
"lf_version": "1.7.0.dev21",
|
|
"metadata": {
|
|
"code_hash": "3cda25c3f7b5",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "lfx",
|
|
"version": null
|
|
}
|
|
],
|
|
"total_dependencies": 1
|
|
},
|
|
"module": "custom_components.parser"
|
|
},
|
|
"minimized": false,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Parsed Text",
|
|
"group_outputs": false,
|
|
"loop_types": null,
|
|
"method": "parse_combined_text",
|
|
"name": "parsed_text",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "Message",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"Message"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"template": {
|
|
"_type": "Component",
|
|
"code": {
|
|
"advanced": true,
|
|
"dynamic": true,
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "code",
|
|
"password": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "code",
|
|
"value": "from lfx.custom.custom_component.component import Component\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, HandleInput, MessageTextInput, MultilineInput, TabInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.template.field.base import Output\n\n\nclass ParserComponent(Component):\n display_name = \"Parser\"\n description = \"Extracts text using a template.\"\n documentation: str = \"https://docs.langflow.org/parser\"\n icon = \"braces\"\n\n inputs = [\n HandleInput(\n name=\"input_data\",\n display_name=\"Data or DataFrame\",\n input_types=[\"DataFrame\", \"Data\"],\n info=\"Accepts either a DataFrame or a Data object.\",\n required=True,\n ),\n TabInput(\n name=\"mode\",\n display_name=\"Mode\",\n options=[\"Parser\", \"Stringify\"],\n value=\"Parser\",\n info=\"Convert into raw string instead of using a template.\",\n real_time_refresh=True,\n ),\n MultilineInput(\n name=\"pattern\",\n display_name=\"Template\",\n info=(\n \"Use variables within curly brackets to extract column values for DataFrames \"\n \"or key values for Data.\"\n \"For example: `Name: {Name}, Age: {Age}, Country: {Country}`\"\n ),\n value=\"Text: {text}\", # Example default\n dynamic=True,\n show=True,\n required=True,\n ),\n MessageTextInput(\n name=\"sep\",\n display_name=\"Separator\",\n advanced=True,\n value=\"\\n\",\n info=\"String used to separate rows/items.\",\n ),\n ]\n\n outputs = [\n Output(\n display_name=\"Parsed Text\",\n name=\"parsed_text\",\n info=\"Formatted text output.\",\n method=\"parse_combined_text\",\n ),\n ]\n\n def update_build_config(self, build_config, field_value, field_name=None):\n \"\"\"Dynamically hide/show `template` and enforce requirement based on `stringify`.\"\"\"\n if field_name == \"mode\":\n build_config[\"pattern\"][\"show\"] = self.mode == \"Parser\"\n build_config[\"pattern\"][\"required\"] = self.mode == \"Parser\"\n if field_value:\n clean_data = BoolInput(\n name=\"clean_data\",\n display_name=\"Clean Data\",\n info=(\n \"Enable to clean the data by removing empty rows and lines \"\n \"in each cell of the DataFrame/ Data object.\"\n ),\n value=True,\n advanced=True,\n required=False,\n )\n build_config[\"clean_data\"] = clean_data.to_dict()\n else:\n build_config.pop(\"clean_data\", None)\n\n return build_config\n\n def _clean_args(self):\n \"\"\"Prepare arguments based on input type.\"\"\"\n input_data = self.input_data\n\n match input_data:\n case list() if all(isinstance(item, Data) for item in input_data):\n msg = \"List of Data objects is not supported.\"\n raise ValueError(msg)\n case DataFrame():\n return input_data, None\n case Data():\n return None, input_data\n case dict() if \"data\" in input_data:\n try:\n if \"columns\" in input_data: # Likely a DataFrame\n return DataFrame.from_dict(input_data), None\n # Likely a Data object\n return None, Data(**input_data)\n except (TypeError, ValueError, KeyError) as e:\n msg = f\"Invalid structured input provided: {e!s}\"\n raise ValueError(msg) from e\n case _:\n msg = f\"Unsupported input type: {type(input_data)}. Expected DataFrame or Data.\"\n raise ValueError(msg)\n\n def parse_combined_text(self) -> Message:\n \"\"\"Parse all rows/items into a single text or convert input to string if `stringify` is enabled.\"\"\"\n # Early return for stringify option\n if self.mode == \"Stringify\":\n return self.convert_to_string()\n\n df, data = self._clean_args()\n\n lines = []\n if df is not None:\n for _, row in df.iterrows():\n formatted_text = self.pattern.format(**row.to_dict())\n lines.append(formatted_text)\n elif data is not None:\n # Use format_map with a dict that returns default_value for missing keys\n class DefaultDict(dict):\n def __missing__(self, key):\n return data.default_value or \"\"\n\n formatted_text = self.pattern.format_map(DefaultDict(data.data))\n lines.append(formatted_text)\n\n combined_text = self.sep.join(lines)\n self.status = combined_text\n return Message(text=combined_text)\n\n def convert_to_string(self) -> Message:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n result = \"\"\n if isinstance(self.input_data, list):\n result = \"\\n\".join([safe_convert(item, clean_data=self.clean_data or False) for item in self.input_data])\n else:\n result = safe_convert(self.input_data or False)\n self.log(f\"Converted to string with length: {len(result)}\")\n\n message = Message(text=result)\n self.status = message\n return message\n"
|
|
},
|
|
"input_data": {
|
|
"_input_type": "HandleInput",
|
|
"advanced": false,
|
|
"display_name": "Data or DataFrame",
|
|
"dynamic": false,
|
|
"info": "Accepts either a DataFrame or a Data object.",
|
|
"input_types": [
|
|
"DataFrame",
|
|
"Data"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "input_data",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "other",
|
|
"value": ""
|
|
},
|
|
"mode": {
|
|
"_input_type": "TabInput",
|
|
"advanced": false,
|
|
"display_name": "Mode",
|
|
"dynamic": false,
|
|
"info": "Convert into raw string instead of using a template.",
|
|
"name": "mode",
|
|
"options": [
|
|
"Parser",
|
|
"Stringify"
|
|
],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "tab",
|
|
"value": "Parser"
|
|
},
|
|
"pattern": {
|
|
"_input_type": "MultilineInput",
|
|
"advanced": false,
|
|
"ai_enabled": false,
|
|
"copy_field": false,
|
|
"display_name": "Template",
|
|
"dynamic": true,
|
|
"info": "Use variables within curly brackets to extract column values for DataFrames or key values for Data.For example: `Name: {Name}, Age: {Age}, Country: {Country}`",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "pattern",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "{text}"
|
|
},
|
|
"sep": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Separator",
|
|
"dynamic": false,
|
|
"info": "String used to separate rows/items.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "sep",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "\n"
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"showNode": true,
|
|
"type": "ParserComponent"
|
|
},
|
|
"dragging": false,
|
|
"id": "ParserComponent-tZs7s",
|
|
"measured": {
|
|
"height": 329,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": 854.0613788430787,
|
|
"y": 1204.2200355777322
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"description": "Get chat inputs from the Playground.",
|
|
"display_name": "Chat Input",
|
|
"id": "ChatInput-7W1BE",
|
|
"node": {
|
|
"base_classes": [
|
|
"Message"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {},
|
|
"description": "Get chat inputs from the Playground.",
|
|
"display_name": "Chat Input",
|
|
"documentation": "https://docs.langflow.org/chat-input-and-output",
|
|
"edited": false,
|
|
"field_order": [
|
|
"input_value",
|
|
"should_store_message",
|
|
"sender",
|
|
"sender_name",
|
|
"session_id",
|
|
"context_id",
|
|
"files"
|
|
],
|
|
"frozen": false,
|
|
"icon": "MessagesSquare",
|
|
"legacy": false,
|
|
"lf_version": "1.7.0.dev21",
|
|
"metadata": {
|
|
"code_hash": "7a26c54d89ed",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "lfx",
|
|
"version": null
|
|
}
|
|
],
|
|
"total_dependencies": 1
|
|
},
|
|
"module": "custom_components.chat_input"
|
|
},
|
|
"minimized": true,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Chat Message",
|
|
"group_outputs": false,
|
|
"loop_types": null,
|
|
"method": "message_response",
|
|
"name": "message",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "Message",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"Message"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"template": {
|
|
"_type": "Component",
|
|
"code": {
|
|
"advanced": true,
|
|
"dynamic": true,
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "code",
|
|
"password": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "code",
|
|
"value": "from lfx.base.data.utils import IMG_FILE_TYPES, TEXT_FILE_TYPES\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.inputs.inputs import BoolInput\nfrom lfx.io import (\n DropdownInput,\n FileInput,\n MessageTextInput,\n MultilineInput,\n Output,\n)\nfrom lfx.schema.message import Message\nfrom lfx.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_USER,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatInput(ChatComponent):\n display_name = \"Chat Input\"\n description = \"Get chat inputs from the Playground.\"\n documentation: str = \"https://docs.langflow.org/chat-input-and-output\"\n icon = \"MessagesSquare\"\n name = \"ChatInput\"\n minimized = True\n\n inputs = [\n MultilineInput(\n name=\"input_value\",\n display_name=\"Input Text\",\n value=\"\",\n info=\"Message to be passed as input.\",\n input_types=[],\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_USER,\n info=\"Type of sender.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_USER,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n FileInput(\n name=\"files\",\n display_name=\"Files\",\n file_types=TEXT_FILE_TYPES + IMG_FILE_TYPES,\n info=\"Files to be sent with the message.\",\n advanced=True,\n is_list=True,\n temp_file=True,\n ),\n ]\n outputs = [\n Output(display_name=\"Chat Message\", name=\"message\", method=\"message_response\"),\n ]\n\n async def message_response(self) -> Message:\n # Ensure files is a list and filter out empty/None values\n files = self.files if self.files else []\n if files and not isinstance(files, list):\n files = [files]\n # Filter out None/empty values\n files = [f for f in files if f is not None and f != \"\"]\n\n session_id = self.session_id or self.graph.session_id or \"\"\n message = await Message.create(\n text=self.input_value,\n sender=self.sender,\n sender_name=self.sender_name,\n session_id=session_id,\n context_id=self.context_id,\n files=files,\n )\n if session_id and isinstance(message, Message) and self.should_store_message:\n stored_message = await self.send_message(\n message,\n )\n self.message.value = stored_message\n message = stored_message\n\n self.status = message\n return message\n"
|
|
},
|
|
"context_id": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Context ID",
|
|
"dynamic": false,
|
|
"info": "The context ID of the chat. Adds an extra layer to the local memory.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "context_id",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"files": {
|
|
"_input_type": "FileInput",
|
|
"advanced": true,
|
|
"display_name": "Files",
|
|
"dynamic": false,
|
|
"fileTypes": [
|
|
"csv",
|
|
"json",
|
|
"pdf",
|
|
"txt",
|
|
"md",
|
|
"mdx",
|
|
"yaml",
|
|
"yml",
|
|
"xml",
|
|
"html",
|
|
"htm",
|
|
"docx",
|
|
"py",
|
|
"sh",
|
|
"sql",
|
|
"js",
|
|
"ts",
|
|
"tsx",
|
|
"jpg",
|
|
"jpeg",
|
|
"png",
|
|
"bmp",
|
|
"image"
|
|
],
|
|
"file_path": "",
|
|
"info": "Files to be sent with the message.",
|
|
"list": true,
|
|
"list_add_label": "Add More",
|
|
"name": "files",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"temp_file": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "file",
|
|
"value": ""
|
|
},
|
|
"input_value": {
|
|
"_input_type": "MultilineInput",
|
|
"advanced": false,
|
|
"ai_enabled": false,
|
|
"copy_field": false,
|
|
"display_name": "Input Text",
|
|
"dynamic": false,
|
|
"info": "Message to be passed as input.",
|
|
"input_types": [],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "input_value",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"sender": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": true,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Sender Type",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Type of sender.",
|
|
"name": "sender",
|
|
"options": [
|
|
"Machine",
|
|
"User"
|
|
],
|
|
"options_metadata": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "User"
|
|
},
|
|
"sender_name": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Sender Name",
|
|
"dynamic": false,
|
|
"info": "Name of the sender.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "sender_name",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "User"
|
|
},
|
|
"session_id": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Session ID",
|
|
"dynamic": false,
|
|
"info": "The session ID of the chat. If empty, the current session ID parameter will be used.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "session_id",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"should_store_message": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Store Messages",
|
|
"dynamic": false,
|
|
"info": "Store the message in the history.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "should_store_message",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": true
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"showNode": false,
|
|
"type": "ChatInput"
|
|
},
|
|
"dragging": false,
|
|
"id": "ChatInput-7W1BE",
|
|
"measured": {
|
|
"height": 48,
|
|
"width": 192
|
|
},
|
|
"position": {
|
|
"x": 980.6037146218582,
|
|
"y": 1642.0144323522718
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"description": "Display a chat message in the Playground.",
|
|
"display_name": "Chat Output",
|
|
"id": "ChatOutput-axewE",
|
|
"node": {
|
|
"base_classes": [
|
|
"Message"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {},
|
|
"description": "Display a chat message in the Playground.",
|
|
"display_name": "Chat Output",
|
|
"documentation": "https://docs.langflow.org/chat-input-and-output",
|
|
"edited": false,
|
|
"field_order": [
|
|
"input_value",
|
|
"should_store_message",
|
|
"sender",
|
|
"sender_name",
|
|
"session_id",
|
|
"context_id",
|
|
"data_template",
|
|
"clean_data"
|
|
],
|
|
"frozen": false,
|
|
"icon": "MessagesSquare",
|
|
"legacy": false,
|
|
"metadata": {
|
|
"code_hash": "cae45e2d53f6",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "orjson",
|
|
"version": "3.10.15"
|
|
},
|
|
{
|
|
"name": "fastapi",
|
|
"version": "0.120.0"
|
|
},
|
|
{
|
|
"name": "lfx",
|
|
"version": null
|
|
}
|
|
],
|
|
"total_dependencies": 3
|
|
},
|
|
"module": "custom_components.chat_output"
|
|
},
|
|
"minimized": true,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Output Message",
|
|
"group_outputs": false,
|
|
"loop_types": null,
|
|
"method": "message_response",
|
|
"name": "message",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "Message",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"Message"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"template": {
|
|
"_type": "Component",
|
|
"clean_data": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Basic Clean Data",
|
|
"dynamic": false,
|
|
"info": "Whether to clean data before converting to string.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "clean_data",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": true
|
|
},
|
|
"code": {
|
|
"advanced": true,
|
|
"dynamic": true,
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "code",
|
|
"password": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "code",
|
|
"value": "from collections.abc import Generator\nfrom typing import Any\n\nimport orjson\nfrom fastapi.encoders import jsonable_encoder\n\nfrom lfx.base.io.chat import ChatComponent\nfrom lfx.helpers.data import safe_convert\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, MessageTextInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.schema.properties import Source\nfrom lfx.template.field.base import Output\nfrom lfx.utils.constants import (\n MESSAGE_SENDER_AI,\n MESSAGE_SENDER_NAME_AI,\n MESSAGE_SENDER_USER,\n)\n\n\nclass ChatOutput(ChatComponent):\n display_name = \"Chat Output\"\n description = \"Display a chat message in the Playground.\"\n documentation: str = \"https://docs.langflow.org/chat-input-and-output\"\n icon = \"MessagesSquare\"\n name = \"ChatOutput\"\n minimized = True\n\n inputs = [\n HandleInput(\n name=\"input_value\",\n display_name=\"Inputs\",\n info=\"Message to be passed as output.\",\n input_types=[\"Data\", \"DataFrame\", \"Message\"],\n required=True,\n ),\n BoolInput(\n name=\"should_store_message\",\n display_name=\"Store Messages\",\n info=\"Store the message in the history.\",\n value=True,\n advanced=True,\n ),\n DropdownInput(\n name=\"sender\",\n display_name=\"Sender Type\",\n options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER],\n value=MESSAGE_SENDER_AI,\n advanced=True,\n info=\"Type of sender.\",\n ),\n MessageTextInput(\n name=\"sender_name\",\n display_name=\"Sender Name\",\n info=\"Name of the sender.\",\n value=MESSAGE_SENDER_NAME_AI,\n advanced=True,\n ),\n MessageTextInput(\n name=\"session_id\",\n display_name=\"Session ID\",\n info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"context_id\",\n display_name=\"Context ID\",\n info=\"The context ID of the chat. Adds an extra layer to the local memory.\",\n value=\"\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"data_template\",\n display_name=\"Data Template\",\n value=\"{text}\",\n advanced=True,\n info=\"Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.\",\n ),\n BoolInput(\n name=\"clean_data\",\n display_name=\"Basic Clean Data\",\n value=True,\n advanced=True,\n info=\"Whether to clean data before converting to string.\",\n ),\n ]\n outputs = [\n Output(\n display_name=\"Output Message\",\n name=\"message\",\n method=\"message_response\",\n ),\n ]\n\n def _build_source(self, id_: str | None, display_name: str | None, source: str | None) -> Source:\n source_dict = {}\n if id_:\n source_dict[\"id\"] = id_\n if display_name:\n source_dict[\"display_name\"] = display_name\n if source:\n # Handle case where source is a ChatOpenAI object\n if hasattr(source, \"model_name\"):\n source_dict[\"source\"] = source.model_name\n elif hasattr(source, \"model\"):\n source_dict[\"source\"] = str(source.model)\n else:\n source_dict[\"source\"] = str(source)\n return Source(**source_dict)\n\n async def message_response(self) -> Message:\n # First convert the input to string if needed\n text = self.convert_to_string()\n\n # Get source properties\n source, _, display_name, source_id = self.get_properties_from_source_component()\n\n # Create or use existing Message object\n if isinstance(self.input_value, Message) and not self.is_connected_to_chat_input():\n message = self.input_value\n # Update message properties\n message.text = text\n else:\n message = Message(text=text)\n\n # Set message properties\n message.sender = self.sender\n message.sender_name = self.sender_name\n message.session_id = self.session_id or self.graph.session_id or \"\"\n message.context_id = self.context_id\n message.flow_id = self.graph.flow_id if hasattr(self, \"graph\") else None\n message.properties.source = self._build_source(source_id, display_name, source)\n\n # Store message if needed\n if message.session_id and self.should_store_message:\n stored_message = await self.send_message(message)\n self.message.value = stored_message\n message = stored_message\n\n self.status = message\n return message\n\n def _serialize_data(self, data: Data) -> str:\n \"\"\"Serialize Data object to JSON string.\"\"\"\n # Convert data.data to JSON-serializable format\n serializable_data = jsonable_encoder(data.data)\n # Serialize with orjson, enabling pretty printing with indentation\n json_bytes = orjson.dumps(serializable_data, option=orjson.OPT_INDENT_2)\n # Convert bytes to string and wrap in Markdown code blocks\n return \"```json\\n\" + json_bytes.decode(\"utf-8\") + \"\\n```\"\n\n def _validate_input(self) -> None:\n \"\"\"Validate the input data and raise ValueError if invalid.\"\"\"\n if self.input_value is None:\n msg = \"Input data cannot be None\"\n raise ValueError(msg)\n if isinstance(self.input_value, list) and not all(\n isinstance(item, Message | Data | DataFrame | str) for item in self.input_value\n ):\n invalid_types = [\n type(item).__name__\n for item in self.input_value\n if not isinstance(item, Message | Data | DataFrame | str)\n ]\n msg = f\"Expected Data or DataFrame or Message or str, got {invalid_types}\"\n raise TypeError(msg)\n if not isinstance(\n self.input_value,\n Message | Data | DataFrame | str | list | Generator | type(None),\n ):\n type_name = type(self.input_value).__name__\n msg = f\"Expected Data or DataFrame or Message or str, Generator or None, got {type_name}\"\n raise TypeError(msg)\n\n def convert_to_string(self) -> str | Generator[Any, None, None]:\n \"\"\"Convert input data to string with proper error handling.\"\"\"\n self._validate_input()\n if isinstance(self.input_value, list):\n clean_data: bool = getattr(self, \"clean_data\", False)\n return \"\\n\".join([safe_convert(item, clean_data=clean_data) for item in self.input_value])\n if isinstance(self.input_value, Generator):\n return self.input_value\n return safe_convert(self.input_value)\n"
|
|
},
|
|
"context_id": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Context ID",
|
|
"dynamic": false,
|
|
"info": "The context ID of the chat. Adds an extra layer to the local memory.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "context_id",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"data_template": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Data Template",
|
|
"dynamic": false,
|
|
"info": "Template to convert Data to Text. If left empty, it will be dynamically set to the Data's text key.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "data_template",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "{text}"
|
|
},
|
|
"input_value": {
|
|
"_input_type": "HandleInput",
|
|
"advanced": false,
|
|
"display_name": "Inputs",
|
|
"dynamic": false,
|
|
"info": "Message to be passed as output.",
|
|
"input_types": [
|
|
"Data",
|
|
"DataFrame",
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "input_value",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "other",
|
|
"value": ""
|
|
},
|
|
"sender": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": true,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Sender Type",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Type of sender.",
|
|
"name": "sender",
|
|
"options": [
|
|
"Machine",
|
|
"User"
|
|
],
|
|
"options_metadata": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "Machine"
|
|
},
|
|
"sender_name": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Sender Name",
|
|
"dynamic": false,
|
|
"info": "Name of the sender.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "sender_name",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "AI"
|
|
},
|
|
"session_id": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "Session ID",
|
|
"dynamic": false,
|
|
"info": "The session ID of the chat. If empty, the current session ID parameter will be used.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "session_id",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"should_store_message": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Store Messages",
|
|
"dynamic": false,
|
|
"info": "Store the message in the history.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "should_store_message",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": true
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"showNode": false,
|
|
"type": "ChatOutput"
|
|
},
|
|
"dragging": false,
|
|
"id": "ChatOutput-axewE",
|
|
"measured": {
|
|
"height": 48,
|
|
"width": 192
|
|
},
|
|
"position": {
|
|
"x": 2262.464573109284,
|
|
"y": 1514.0186854555118
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"id": "LanguageModelComponent-KdXf9",
|
|
"node": {
|
|
"base_classes": [
|
|
"LanguageModel",
|
|
"Message"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {},
|
|
"description": "Runs a language model given a specified provider.",
|
|
"display_name": "Language Model",
|
|
"documentation": "https://docs.langflow.org/components-models",
|
|
"edited": false,
|
|
"field_order": [
|
|
"provider",
|
|
"model_name",
|
|
"api_key",
|
|
"base_url_ibm_watsonx",
|
|
"project_id",
|
|
"ollama_base_url",
|
|
"input_value",
|
|
"system_message",
|
|
"stream",
|
|
"temperature"
|
|
],
|
|
"frozen": false,
|
|
"icon": "brain-circuit",
|
|
"last_updated": "2025-12-02T21:32:07.567Z",
|
|
"legacy": false,
|
|
"lf_version": "1.7.0.dev21",
|
|
"metadata": {
|
|
"code_hash": "694ffc4b17b8",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "requests",
|
|
"version": "2.32.5"
|
|
},
|
|
{
|
|
"name": "langchain_anthropic",
|
|
"version": "0.3.14"
|
|
},
|
|
{
|
|
"name": "langchain_ibm",
|
|
"version": "0.3.19"
|
|
},
|
|
{
|
|
"name": "langchain_ollama",
|
|
"version": "0.3.10"
|
|
},
|
|
{
|
|
"name": "langchain_openai",
|
|
"version": "0.3.23"
|
|
},
|
|
{
|
|
"name": "pydantic",
|
|
"version": "2.10.6"
|
|
},
|
|
{
|
|
"name": "lfx",
|
|
"version": null
|
|
}
|
|
],
|
|
"total_dependencies": 7
|
|
},
|
|
"keywords": [
|
|
"model",
|
|
"llm",
|
|
"language model",
|
|
"large language model"
|
|
],
|
|
"module": "lfx.components.models.language_model.LanguageModelComponent"
|
|
},
|
|
"minimized": false,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Model Response",
|
|
"group_outputs": false,
|
|
"loop_types": null,
|
|
"method": "text_response",
|
|
"name": "text_output",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "Message",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"Message"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
},
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Language Model",
|
|
"group_outputs": false,
|
|
"loop_types": null,
|
|
"method": "build_model",
|
|
"name": "model_output",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "LanguageModel",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"LanguageModel"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"priority": 0,
|
|
"template": {
|
|
"_frontend_node_flow_id": {
|
|
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
|
|
},
|
|
"_frontend_node_folder_id": {
|
|
"value": "69a7745e-dfb8-40a7-b5cb-5da3af0b10b6"
|
|
},
|
|
"_type": "Component",
|
|
"api_key": {
|
|
"_input_type": "SecretStrInput",
|
|
"advanced": false,
|
|
"display_name": "OpenAI API Key",
|
|
"dynamic": false,
|
|
"info": "Model Provider API key",
|
|
"input_types": [],
|
|
"load_from_db": true,
|
|
"name": "api_key",
|
|
"password": true,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "str",
|
|
"value": "OPENAI_API_KEY"
|
|
},
|
|
"base_url_ibm_watsonx": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "watsonx API Endpoint",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "The base URL of the API (IBM watsonx.ai only)",
|
|
"name": "base_url_ibm_watsonx",
|
|
"options": [
|
|
"https://us-south.ml.cloud.ibm.com",
|
|
"https://eu-de.ml.cloud.ibm.com",
|
|
"https://eu-gb.ml.cloud.ibm.com",
|
|
"https://au-syd.ml.cloud.ibm.com",
|
|
"https://jp-tok.ml.cloud.ibm.com",
|
|
"https://ca-tor.ml.cloud.ibm.com"
|
|
],
|
|
"options_metadata": [],
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"type": "str",
|
|
"value": "https://us-south.ml.cloud.ibm.com"
|
|
},
|
|
"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\nimport requests\nfrom langchain_anthropic import ChatAnthropic\nfrom langchain_ibm import ChatWatsonx\nfrom langchain_ollama import ChatOllama\nfrom langchain_openai import ChatOpenAI\nfrom pydantic.v1 import SecretStr\n\nfrom lfx.base.models.anthropic_constants import ANTHROPIC_MODELS\nfrom lfx.base.models.google_generative_ai_constants import GOOGLE_GENERATIVE_AI_MODELS\nfrom lfx.base.models.google_generative_ai_model import ChatGoogleGenerativeAIFixed\nfrom lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.model_utils import get_ollama_models, is_valid_ollama_url\nfrom lfx.base.models.openai_constants import OPENAI_CHAT_MODEL_NAMES, OPENAI_REASONING_MODEL_NAMES\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, MessageTextInput, StrInput\nfrom lfx.io import DropdownInput, MessageInput, MultilineInput, SecretStrInput, SliderInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.utils.util import transform_localhost_url\n\n# IBM watsonx.ai constants\nIBM_WATSONX_DEFAULT_MODELS = [\"ibm/granite-3-2b-instruct\", \"ibm/granite-3-8b-instruct\", \"ibm/granite-13b-instruct-v2\"]\nIBM_WATSONX_URLS = [\n \"https://us-south.ml.cloud.ibm.com\",\n \"https://eu-de.ml.cloud.ibm.com\",\n \"https://eu-gb.ml.cloud.ibm.com\",\n \"https://au-syd.ml.cloud.ibm.com\",\n \"https://jp-tok.ml.cloud.ibm.com\",\n \"https://ca-tor.ml.cloud.ibm.com\",\n]\n\n# Ollama API constants\nHTTP_STATUS_OK = 200\nJSON_MODELS_KEY = \"models\"\nJSON_NAME_KEY = \"name\"\nJSON_CAPABILITIES_KEY = \"capabilities\"\nDESIRED_CAPABILITY = \"completion\"\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n display_name = \"Language Model\"\n description = \"Runs a language model given a specified provider.\"\n documentation: str = \"https://docs.langflow.org/components-models\"\n icon = \"brain-circuit\"\n category = \"models\"\n priority = 0 # Set priority to 0 to make it appear first\n\n @staticmethod\n def fetch_ibm_models(base_url: str) -> list[str]:\n \"\"\"Fetch available models from the watsonx.ai API.\"\"\"\n try:\n endpoint = f\"{base_url}/ml/v1/foundation_model_specs\"\n params = {\"version\": \"2024-09-16\", \"filters\": \"function_text_chat,!lifecycle_withdrawn\"}\n response = requests.get(endpoint, params=params, timeout=10)\n response.raise_for_status()\n data = response.json()\n models = [model[\"model_id\"] for model in data.get(\"resources\", [])]\n return sorted(models)\n except Exception: # noqa: BLE001\n logger.exception(\"Error fetching IBM watsonx models. Using default models.\")\n return IBM_WATSONX_DEFAULT_MODELS\n\n inputs = [\n DropdownInput(\n name=\"provider\",\n display_name=\"Model Provider\",\n options=[\"OpenAI\", \"Anthropic\", \"Google\", \"IBM watsonx.ai\", \"Ollama\"],\n value=\"OpenAI\",\n info=\"Select the model provider\",\n real_time_refresh=True,\n options_metadata=[\n {\"icon\": \"OpenAI\"},\n {\"icon\": \"Anthropic\"},\n {\"icon\": \"GoogleGenerativeAI\"},\n {\"icon\": \"WatsonxAI\"},\n {\"icon\": \"Ollama\"},\n ],\n ),\n DropdownInput(\n name=\"model_name\",\n display_name=\"Model Name\",\n options=OPENAI_CHAT_MODEL_NAMES + OPENAI_REASONING_MODEL_NAMES,\n value=OPENAI_CHAT_MODEL_NAMES[0],\n info=\"Select the model to use\",\n real_time_refresh=True,\n refresh_button=True,\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"Model Provider API key\",\n required=False,\n show=True,\n real_time_refresh=True,\n ),\n DropdownInput(\n name=\"base_url_ibm_watsonx\",\n display_name=\"watsonx API Endpoint\",\n info=\"The base URL of the API (IBM watsonx.ai only)\",\n options=IBM_WATSONX_URLS,\n value=IBM_WATSONX_URLS[0],\n show=False,\n real_time_refresh=True,\n ),\n StrInput(\n name=\"project_id\",\n display_name=\"watsonx Project ID\",\n info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n show=False,\n required=False,\n ),\n MessageTextInput(\n name=\"ollama_base_url\",\n display_name=\"Ollama API URL\",\n info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n value=DEFAULT_OLLAMA_URL,\n show=False,\n real_time_refresh=True,\n load_from_db=True,\n ),\n MessageInput(\n name=\"input_value\",\n display_name=\"Input\",\n info=\"The input text to send to the model\",\n ),\n MultilineInput(\n name=\"system_message\",\n display_name=\"System Message\",\n info=\"A system message that helps set the behavior of the assistant\",\n advanced=False,\n ),\n BoolInput(\n name=\"stream\",\n display_name=\"Stream\",\n info=\"Whether to stream the response\",\n value=False,\n advanced=True,\n ),\n SliderInput(\n name=\"temperature\",\n display_name=\"Temperature\",\n value=0.1,\n info=\"Controls randomness in responses\",\n range_spec=RangeSpec(min=0, max=1, step=0.01),\n advanced=True,\n ),\n ]\n\n def build_model(self) -> LanguageModel:\n provider = self.provider\n model_name = self.model_name\n temperature = self.temperature\n stream = self.stream\n\n if provider == \"OpenAI\":\n if not self.api_key:\n msg = \"OpenAI API key is required when using OpenAI provider\"\n raise ValueError(msg)\n\n if model_name in OPENAI_REASONING_MODEL_NAMES:\n # reasoning models do not support temperature (yet)\n temperature = None\n\n return ChatOpenAI(\n model_name=model_name,\n temperature=temperature,\n streaming=stream,\n openai_api_key=self.api_key,\n )\n if provider == \"Anthropic\":\n if not self.api_key:\n msg = \"Anthropic API key is required when using Anthropic provider\"\n raise ValueError(msg)\n return ChatAnthropic(\n model=model_name,\n temperature=temperature,\n streaming=stream,\n anthropic_api_key=self.api_key,\n )\n if provider == \"Google\":\n if not self.api_key:\n msg = \"Google API key is required when using Google provider\"\n raise ValueError(msg)\n return ChatGoogleGenerativeAIFixed(\n model=model_name,\n temperature=temperature,\n streaming=stream,\n google_api_key=self.api_key,\n )\n if provider == \"IBM watsonx.ai\":\n if not self.api_key:\n msg = \"IBM API key is required when using IBM watsonx.ai provider\"\n raise ValueError(msg)\n if not self.base_url_ibm_watsonx:\n msg = \"IBM watsonx API Endpoint is required when using IBM watsonx.ai provider\"\n raise ValueError(msg)\n if not self.project_id:\n msg = \"IBM watsonx Project ID is required when using IBM watsonx.ai provider\"\n raise ValueError(msg)\n return ChatWatsonx(\n apikey=SecretStr(self.api_key).get_secret_value(),\n url=self.base_url_ibm_watsonx,\n project_id=self.project_id,\n model_id=model_name,\n params={\n \"temperature\": temperature,\n },\n streaming=stream,\n )\n if provider == \"Ollama\":\n if not self.ollama_base_url:\n msg = \"Ollama API URL is required when using Ollama provider\"\n raise ValueError(msg)\n if not model_name:\n msg = \"Model name is required when using Ollama provider\"\n raise ValueError(msg)\n\n transformed_base_url = transform_localhost_url(self.ollama_base_url)\n\n # Check if URL contains /v1 suffix (OpenAI-compatible mode)\n if transformed_base_url and transformed_base_url.rstrip(\"/\").endswith(\"/v1\"):\n # Strip /v1 suffix and log warning\n transformed_base_url = transformed_base_url.rstrip(\"/\").removesuffix(\"/v1\")\n logger.warning(\n \"Detected '/v1' suffix in base URL. The Ollama component uses the native Ollama API, \"\n \"not the OpenAI-compatible API. The '/v1' suffix has been automatically removed. \"\n \"If you want to use the OpenAI-compatible API, please use the OpenAI component instead. \"\n \"Learn more at https://docs.ollama.com/openai#openai-compatibility\"\n )\n\n return ChatOllama(\n base_url=transformed_base_url,\n model=model_name,\n temperature=temperature,\n )\n msg = f\"Unknown provider: {provider}\"\n raise ValueError(msg)\n\n async def update_build_config(\n self, build_config: dotdict, field_value: Any, field_name: str | None = None\n ) -> dotdict:\n if field_name == \"provider\":\n if field_value == \"OpenAI\":\n build_config[\"model_name\"][\"options\"] = OPENAI_CHAT_MODEL_NAMES + OPENAI_REASONING_MODEL_NAMES\n build_config[\"model_name\"][\"value\"] = OPENAI_CHAT_MODEL_NAMES[0]\n build_config[\"api_key\"][\"display_name\"] = \"OpenAI API Key\"\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"ollama_base_url\"][\"show\"] = False\n elif field_value == \"Anthropic\":\n build_config[\"model_name\"][\"options\"] = ANTHROPIC_MODELS\n build_config[\"model_name\"][\"value\"] = ANTHROPIC_MODELS[0]\n build_config[\"api_key\"][\"display_name\"] = \"Anthropic API Key\"\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"ollama_base_url\"][\"show\"] = False\n elif field_value == \"Google\":\n build_config[\"model_name\"][\"options\"] = GOOGLE_GENERATIVE_AI_MODELS\n build_config[\"model_name\"][\"value\"] = GOOGLE_GENERATIVE_AI_MODELS[0]\n build_config[\"api_key\"][\"display_name\"] = \"Google API Key\"\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"ollama_base_url\"][\"show\"] = False\n elif field_value == \"IBM watsonx.ai\":\n build_config[\"model_name\"][\"options\"] = IBM_WATSONX_DEFAULT_MODELS\n build_config[\"model_name\"][\"value\"] = IBM_WATSONX_DEFAULT_MODELS[0]\n build_config[\"api_key\"][\"display_name\"] = \"IBM API Key\"\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = True\n build_config[\"project_id\"][\"show\"] = True\n build_config[\"ollama_base_url\"][\"show\"] = False\n elif field_value == \"Ollama\":\n # Fetch Ollama models from the API\n build_config[\"api_key\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"ollama_base_url\"][\"show\"] = True\n\n # Try multiple sources to get the URL (in order of preference):\n # 1. Instance attribute (already resolved from global/db)\n # 2. Build config value (may be a global variable reference)\n # 3. Default value\n ollama_url = getattr(self, \"ollama_base_url\", None)\n if not ollama_url:\n config_value = build_config[\"ollama_base_url\"].get(\"value\", DEFAULT_OLLAMA_URL)\n # If config_value looks like a variable name (all caps with underscores), use default\n is_variable_ref = (\n config_value\n and isinstance(config_value, str)\n and config_value.isupper()\n and \"_\" in config_value\n )\n if is_variable_ref:\n await logger.adebug(\n f\"Config value appears to be a variable reference: {config_value}, using default\"\n )\n ollama_url = DEFAULT_OLLAMA_URL\n else:\n ollama_url = config_value\n\n await logger.adebug(f\"Fetching Ollama models for provider switch. URL: {ollama_url}\")\n if await is_valid_ollama_url(url=ollama_url):\n try:\n models = await get_ollama_models(\n base_url_value=ollama_url,\n desired_capability=DESIRED_CAPABILITY,\n json_models_key=JSON_MODELS_KEY,\n json_name_key=JSON_NAME_KEY,\n json_capabilities_key=JSON_CAPABILITIES_KEY,\n )\n build_config[\"model_name\"][\"options\"] = models\n build_config[\"model_name\"][\"value\"] = models[0] if models else \"\"\n except ValueError:\n await logger.awarning(\"Failed to fetch Ollama models. Setting empty options.\")\n build_config[\"model_name\"][\"options\"] = []\n build_config[\"model_name\"][\"value\"] = \"\"\n else:\n await logger.awarning(f\"Invalid Ollama URL: {ollama_url}\")\n build_config[\"model_name\"][\"options\"] = []\n build_config[\"model_name\"][\"value\"] = \"\"\n elif (\n field_name == \"base_url_ibm_watsonx\"\n and field_value\n and hasattr(self, \"provider\")\n and self.provider == \"IBM watsonx.ai\"\n ):\n # Fetch IBM models when base_url changes\n try:\n models = self.fetch_ibm_models(base_url=field_value)\n build_config[\"model_name\"][\"options\"] = models\n build_config[\"model_name\"][\"value\"] = models[0] if models else IBM_WATSONX_DEFAULT_MODELS[0]\n info_message = f\"Updated model options: {len(models)} models found in {field_value}\"\n logger.info(info_message)\n except Exception: # noqa: BLE001\n logger.exception(\"Error updating IBM model options.\")\n elif field_name == \"ollama_base_url\":\n # Fetch Ollama models when ollama_base_url changes\n # Use the field_value directly since this is triggered when the field changes\n logger.debug(\n f\"Fetching Ollama models from updated URL: {build_config['ollama_base_url']} \\\n and value {self.ollama_base_url}\",\n )\n await logger.adebug(f\"Fetching Ollama models from updated URL: {self.ollama_base_url}\")\n if await is_valid_ollama_url(url=self.ollama_base_url):\n try:\n models = await get_ollama_models(\n base_url_value=self.ollama_base_url,\n desired_capability=DESIRED_CAPABILITY,\n json_models_key=JSON_MODELS_KEY,\n json_name_key=JSON_NAME_KEY,\n json_capabilities_key=JSON_CAPABILITIES_KEY,\n )\n build_config[\"model_name\"][\"options\"] = models\n build_config[\"model_name\"][\"value\"] = models[0] if models else \"\"\n info_message = f\"Updated model options: {len(models)} models found in {self.ollama_base_url}\"\n await logger.ainfo(info_message)\n except ValueError:\n await logger.awarning(\"Error updating Ollama model options.\")\n build_config[\"model_name\"][\"options\"] = []\n build_config[\"model_name\"][\"value\"] = \"\"\n else:\n await logger.awarning(f\"Invalid Ollama URL: {self.ollama_base_url}\")\n build_config[\"model_name\"][\"options\"] = []\n build_config[\"model_name\"][\"value\"] = \"\"\n elif field_name == \"model_name\":\n # Refresh Ollama models when model_name field is accessed\n if hasattr(self, \"provider\") and self.provider == \"Ollama\":\n ollama_url = getattr(self, \"ollama_base_url\", DEFAULT_OLLAMA_URL)\n if await is_valid_ollama_url(url=ollama_url):\n try:\n models = await get_ollama_models(\n base_url_value=ollama_url,\n desired_capability=DESIRED_CAPABILITY,\n json_models_key=JSON_MODELS_KEY,\n json_name_key=JSON_NAME_KEY,\n json_capabilities_key=JSON_CAPABILITIES_KEY,\n )\n build_config[\"model_name\"][\"options\"] = models\n except ValueError:\n await logger.awarning(\"Failed to refresh Ollama models.\")\n build_config[\"model_name\"][\"options\"] = []\n else:\n build_config[\"model_name\"][\"options\"] = []\n\n # Hide system_message for o1 models - currently unsupported\n if field_value and field_value.startswith(\"o1\") and hasattr(self, \"provider\") and self.provider == \"OpenAI\":\n if \"system_message\" in build_config:\n build_config[\"system_message\"][\"show\"] = False\n elif \"system_message\" in build_config:\n build_config[\"system_message\"][\"show\"] = True\n return build_config\n"
|
|
},
|
|
"input_value": {
|
|
"_input_type": "MessageInput",
|
|
"advanced": false,
|
|
"display_name": "Input",
|
|
"dynamic": false,
|
|
"info": "The input text to send to the model",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "input_value",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"is_refresh": false,
|
|
"model_name": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Model Name",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Select the model to use",
|
|
"name": "model_name",
|
|
"options": [
|
|
"gpt-4o-mini",
|
|
"gpt-4o",
|
|
"gpt-4.1",
|
|
"gpt-4.1-mini",
|
|
"gpt-4.1-nano",
|
|
"gpt-4-turbo",
|
|
"gpt-4-turbo-preview",
|
|
"gpt-4",
|
|
"gpt-3.5-turbo",
|
|
"gpt-5.1",
|
|
"gpt-5",
|
|
"gpt-5-mini",
|
|
"gpt-5-nano",
|
|
"gpt-5-chat-latest",
|
|
"o1",
|
|
"o3-mini",
|
|
"o3",
|
|
"o3-pro",
|
|
"o4-mini",
|
|
"o4-mini-high"
|
|
],
|
|
"options_metadata": [],
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"refresh_button": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"type": "str",
|
|
"value": "gpt-4o-mini"
|
|
},
|
|
"ollama_base_url": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": false,
|
|
"display_name": "Ollama API URL",
|
|
"dynamic": false,
|
|
"info": "Endpoint of the Ollama API (Ollama only). Defaults to http://localhost:11434",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "ollama_base_url",
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"project_id": {
|
|
"_input_type": "StrInput",
|
|
"advanced": false,
|
|
"display_name": "watsonx Project ID",
|
|
"dynamic": false,
|
|
"info": "The project ID associated with the foundation model (IBM watsonx.ai only)",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "project_id",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"provider": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Model Provider",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Select the model provider",
|
|
"name": "provider",
|
|
"options": [
|
|
"OpenAI",
|
|
"Anthropic",
|
|
"Google",
|
|
"IBM watsonx.ai",
|
|
"Ollama"
|
|
],
|
|
"options_metadata": [
|
|
{
|
|
"icon": "OpenAI"
|
|
},
|
|
{
|
|
"icon": "Anthropic"
|
|
},
|
|
{
|
|
"icon": "GoogleGenerativeAI"
|
|
},
|
|
{
|
|
"icon": "WatsonxAI"
|
|
},
|
|
{
|
|
"icon": "Ollama"
|
|
}
|
|
],
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"selected_metadata": {
|
|
"icon": "OpenAI"
|
|
},
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"type": "str",
|
|
"value": "OpenAI"
|
|
},
|
|
"stream": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Stream",
|
|
"dynamic": false,
|
|
"info": "Whether to stream the response",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "stream",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"type": "bool",
|
|
"value": false
|
|
},
|
|
"system_message": {
|
|
"_input_type": "MultilineInput",
|
|
"advanced": false,
|
|
"copy_field": false,
|
|
"display_name": "System Message",
|
|
"dynamic": false,
|
|
"info": "A system message that helps set the behavior of the assistant",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "system_message",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"temperature": {
|
|
"_input_type": "SliderInput",
|
|
"advanced": true,
|
|
"display_name": "Temperature",
|
|
"dynamic": false,
|
|
"info": "Controls randomness in responses",
|
|
"max_label": "",
|
|
"max_label_icon": "",
|
|
"min_label": "",
|
|
"min_label_icon": "",
|
|
"name": "temperature",
|
|
"placeholder": "",
|
|
"range_spec": {
|
|
"max": 1,
|
|
"min": 0,
|
|
"step": 0.01,
|
|
"step_type": "float"
|
|
},
|
|
"required": false,
|
|
"show": true,
|
|
"slider_buttons": false,
|
|
"slider_buttons_options": [],
|
|
"slider_input": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"type": "slider",
|
|
"value": 0.1
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"selected_output": "text_output",
|
|
"showNode": true,
|
|
"type": "LanguageModelComponent"
|
|
},
|
|
"dragging": false,
|
|
"id": "LanguageModelComponent-KdXf9",
|
|
"measured": {
|
|
"height": 534,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": 1791.7120459180214,
|
|
"y": 1163.865305192517
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"id": "TextInput-4cEHx",
|
|
"node": {
|
|
"base_classes": [
|
|
"Message"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {},
|
|
"description": "Get user text inputs.",
|
|
"display_name": "Text Input",
|
|
"documentation": "https://docs.langflow.org/components-io#text-input",
|
|
"edited": true,
|
|
"field_order": [
|
|
"input_value"
|
|
],
|
|
"frozen": false,
|
|
"icon": "type",
|
|
"legacy": false,
|
|
"lf_version": "1.7.0.dev21",
|
|
"metadata": {
|
|
"code_hash": "7b91454fe0f3",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "lfx",
|
|
"version": null
|
|
}
|
|
],
|
|
"total_dependencies": 1
|
|
},
|
|
"module": "custom_components.text_input"
|
|
},
|
|
"minimized": false,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Output Text",
|
|
"group_outputs": false,
|
|
"hidden": null,
|
|
"method": "text_response",
|
|
"name": "text",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "Message",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"Message"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"template": {
|
|
"_type": "Component",
|
|
"code": {
|
|
"advanced": true,
|
|
"dynamic": true,
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "code",
|
|
"password": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "code",
|
|
"value": "from lfx.base.io.text import TextComponent\nfrom lfx.io import StrInput, Output\nfrom lfx.schema.message import Message\n\n\nclass TextInputComponent(TextComponent):\n display_name = \"Text Input\"\n description = \"Get user text inputs.\"\n documentation: str = \"https://docs.langflow.org/components-io#text-input\"\n icon = \"type\"\n name = \"TextInput\"\n\n inputs = [\n StrInput(\n name=\"input_value\",\n display_name=\"Text\",\n info=\"Text to be passed as input.\",\n ),\n ]\n outputs = [\n Output(display_name=\"Output Text\", name=\"text\", method=\"text_response\"),\n ]\n\n def text_response(self) -> Message:\n return Message(\n text=self.input_value,\n )\n"
|
|
},
|
|
"input_value": {
|
|
"_input_type": "StrInput",
|
|
"advanced": false,
|
|
"display_name": "Text",
|
|
"dynamic": false,
|
|
"info": "Text to be passed as input.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": true,
|
|
"name": "input_value",
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"type": "str",
|
|
"value": "OPENRAG-QUERY-FILTER"
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"showNode": true,
|
|
"type": "TextInput"
|
|
},
|
|
"dragging": false,
|
|
"id": "TextInput-4cEHx",
|
|
"measured": {
|
|
"height": 204,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": -262.4138400422388,
|
|
"y": 1630.3486582843238
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"description": "Generate embeddings using a specified provider.",
|
|
"display_name": "Embedding Model",
|
|
"id": "EmbeddingModel-ooLFP",
|
|
"node": {
|
|
"base_classes": [
|
|
"Embeddings"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {},
|
|
"description": "Generate embeddings using a specified provider.",
|
|
"display_name": "Embedding Model",
|
|
"documentation": "https://docs.langflow.org/components-embedding-models",
|
|
"edited": true,
|
|
"field_order": [
|
|
"provider",
|
|
"api_base",
|
|
"ollama_base_url",
|
|
"base_url_ibm_watsonx",
|
|
"model",
|
|
"api_key",
|
|
"project_id",
|
|
"dimensions",
|
|
"chunk_size",
|
|
"request_timeout",
|
|
"max_retries",
|
|
"show_progress_bar",
|
|
"model_kwargs",
|
|
"truncate_input_tokens",
|
|
"input_text",
|
|
"fail_safe_mode"
|
|
],
|
|
"frozen": false,
|
|
"icon": "binary",
|
|
"last_updated": "2025-12-02T21:24:52.479Z",
|
|
"legacy": false,
|
|
"lf_version": "1.7.0.dev21",
|
|
"metadata": {
|
|
"code_hash": "0e2d6fe67a26",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "requests",
|
|
"version": "2.32.5"
|
|
},
|
|
{
|
|
"name": "ibm_watsonx_ai",
|
|
"version": "1.4.2"
|
|
},
|
|
{
|
|
"name": "langchain_openai",
|
|
"version": "0.3.23"
|
|
},
|
|
{
|
|
"name": "lfx",
|
|
"version": "0.2.0.dev21"
|
|
},
|
|
{
|
|
"name": "langchain_ollama",
|
|
"version": "0.3.10"
|
|
},
|
|
{
|
|
"name": "langchain_community",
|
|
"version": "0.3.21"
|
|
},
|
|
{
|
|
"name": "langchain_ibm",
|
|
"version": "0.3.19"
|
|
}
|
|
],
|
|
"total_dependencies": 7
|
|
},
|
|
"module": "custom_components.embedding_model"
|
|
},
|
|
"minimized": false,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Embedding Model",
|
|
"group_outputs": false,
|
|
"hidden": null,
|
|
"loop_types": null,
|
|
"method": "build_embeddings",
|
|
"name": "embeddings",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "Embeddings",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"Embeddings"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"template": {
|
|
"_frontend_node_flow_id": {
|
|
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
|
|
},
|
|
"_frontend_node_folder_id": {
|
|
"value": "69a7745e-dfb8-40a7-b5cb-5da3af0b10b6"
|
|
},
|
|
"_type": "Component",
|
|
"api_base": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": false,
|
|
"display_name": "OpenAI API Base URL",
|
|
"dynamic": false,
|
|
"info": "Base URL for the API. Leave empty for default.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "api_base",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"api_key": {
|
|
"_input_type": "SecretStrInput",
|
|
"advanced": false,
|
|
"display_name": "OpenAI API Key",
|
|
"dynamic": false,
|
|
"info": "Model Provider API key",
|
|
"input_types": [],
|
|
"load_from_db": true,
|
|
"name": "api_key",
|
|
"override_skip": false,
|
|
"password": true,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "OPENAI_API_KEY"
|
|
},
|
|
"base_url_ibm_watsonx": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "watsonx API Endpoint",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "The base URL of the API (IBM watsonx.ai only)",
|
|
"name": "base_url_ibm_watsonx",
|
|
"options": [
|
|
"https://us-south.ml.cloud.ibm.com",
|
|
"https://eu-de.ml.cloud.ibm.com",
|
|
"https://eu-gb.ml.cloud.ibm.com",
|
|
"https://au-syd.ml.cloud.ibm.com",
|
|
"https://jp-tok.ml.cloud.ibm.com",
|
|
"https://ca-tor.ml.cloud.ibm.com"
|
|
],
|
|
"options_metadata": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "https://us-south.ml.cloud.ibm.com"
|
|
},
|
|
"chunk_size": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Chunk Size",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "chunk_size",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 1000
|
|
},
|
|
"code": {
|
|
"advanced": true,
|
|
"dynamic": true,
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "code",
|
|
"password": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "code",
|
|
"value": "from typing import Any\n\nimport requests\nfrom ibm_watsonx_ai.metanames import EmbedTextParamsMetaNames\nfrom langchain_openai import OpenAIEmbeddings\n\nfrom lfx.base.embeddings.embeddings_class import EmbeddingsWithModels\nfrom lfx.base.embeddings.model import LCEmbeddingsModel\nfrom lfx.base.models.model_utils import get_ollama_models, is_valid_ollama_url\nfrom lfx.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom lfx.base.models.watsonx_constants import (\n IBM_WATSONX_URLS,\n WATSONX_EMBEDDING_MODEL_NAMES,\n)\nfrom lfx.field_typing import Embeddings\nfrom lfx.io import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n MessageTextInput,\n SecretStrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.utils.util import transform_localhost_url\n\n# Ollama API constants\nHTTP_STATUS_OK = 200\nJSON_MODELS_KEY = \"models\"\nJSON_NAME_KEY = \"name\"\nJSON_CAPABILITIES_KEY = \"capabilities\"\nDESIRED_CAPABILITY = \"embedding\"\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass EmbeddingModelComponent(LCEmbeddingsModel):\n display_name = \"Embedding Model\"\n description = \"Generate embeddings using a specified provider.\"\n documentation: str = \"https://docs.langflow.org/components-embedding-models\"\n icon = \"binary\"\n name = \"EmbeddingModel\"\n category = \"models\"\n\n inputs = [\n DropdownInput(\n name=\"provider\",\n display_name=\"Model Provider\",\n options=[\"OpenAI\", \"Ollama\", \"IBM watsonx.ai\"],\n value=\"OpenAI\",\n info=\"Select the embedding model provider\",\n real_time_refresh=True,\n options_metadata=[{\"icon\": \"OpenAI\"}, {\"icon\": \"Ollama\"}, {\"icon\": \"WatsonxAI\"}],\n ),\n MessageTextInput(\n name=\"api_base\",\n display_name=\"API Base URL\",\n info=\"Base URL for the API. Leave empty for default.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"ollama_base_url\",\n display_name=\"Ollama API URL\",\n info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n value=DEFAULT_OLLAMA_URL,\n show=False,\n real_time_refresh=True,\n load_from_db=True,\n ),\n DropdownInput(\n name=\"base_url_ibm_watsonx\",\n display_name=\"watsonx API Endpoint\",\n info=\"The base URL of the API (IBM watsonx.ai only)\",\n options=IBM_WATSONX_URLS,\n value=IBM_WATSONX_URLS[0],\n show=False,\n real_time_refresh=True,\n ),\n DropdownInput(\n name=\"model\",\n display_name=\"Model Name\",\n options=OPENAI_EMBEDDING_MODEL_NAMES,\n value=OPENAI_EMBEDDING_MODEL_NAMES[0],\n info=\"Select the embedding model to use\",\n real_time_refresh=True,\n refresh_button=True,\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"Model Provider API key\",\n required=True,\n show=True,\n real_time_refresh=True,\n ),\n # Watson-specific inputs\n MessageTextInput(\n name=\"project_id\",\n display_name=\"Project ID\",\n info=\"IBM watsonx.ai Project ID (required for IBM watsonx.ai)\",\n show=False,\n ),\n IntInput(\n name=\"dimensions\",\n display_name=\"Dimensions\",\n info=\"The number of dimensions the resulting output embeddings should have. \"\n \"Only supported by certain models.\",\n advanced=True,\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", advanced=True, value=3),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n DictInput(\n name=\"model_kwargs\",\n display_name=\"Model Kwargs\",\n advanced=True,\n info=\"Additional keyword arguments to pass to the model.\",\n ),\n IntInput(\n name=\"truncate_input_tokens\",\n display_name=\"Truncate Input Tokens\",\n advanced=True,\n value=200,\n show=False,\n ),\n BoolInput(\n name=\"input_text\",\n display_name=\"Include the original text in the output\",\n value=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"fail_safe_mode\",\n display_name=\"Fail-Safe Mode\",\n value=False,\n advanced=True,\n info=\"When enabled, errors will be logged instead of raising exceptions. \"\n \"The component will return None on error.\",\n real_time_refresh=True,\n ),\n ]\n\n @staticmethod\n def fetch_ibm_models(base_url: str) -> list[str]:\n \"\"\"Fetch available models from the watsonx.ai API.\"\"\"\n try:\n endpoint = f\"{base_url}/ml/v1/foundation_model_specs\"\n params = {\n \"version\": \"2024-09-16\",\n \"filters\": \"function_embedding,!lifecycle_withdrawn:and\",\n }\n response = requests.get(endpoint, params=params, timeout=10)\n response.raise_for_status()\n data = response.json()\n models = [model[\"model_id\"] for model in data.get(\"resources\", [])]\n return sorted(models)\n except Exception: # noqa: BLE001\n logger.exception(\"Error fetching models\")\n return WATSONX_EMBEDDING_MODEL_NAMES\n async def fetch_ollama_models(self) -> list[str]:\n try:\n return await get_ollama_models(\n base_url_value=self.ollama_base_url,\n desired_capability=DESIRED_CAPABILITY,\n json_models_key=JSON_MODELS_KEY,\n json_name_key=JSON_NAME_KEY,\n json_capabilities_key=JSON_CAPABILITIES_KEY,\n )\n except Exception: # noqa: BLE001\n\n logger.exception(\"Error fetching models\")\n return []\n async def build_embeddings(self) -> Embeddings:\n provider = self.provider\n model = self.model\n api_key = self.api_key\n api_base = self.api_base\n base_url_ibm_watsonx = self.base_url_ibm_watsonx\n ollama_base_url = self.ollama_base_url\n dimensions = self.dimensions\n chunk_size = self.chunk_size\n request_timeout = self.request_timeout\n max_retries = self.max_retries\n show_progress_bar = self.show_progress_bar\n model_kwargs = self.model_kwargs or {}\n\n if provider == \"OpenAI\":\n if not api_key:\n msg = \"OpenAI API key is required when using OpenAI provider\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n try:\n # Create the primary embedding instance\n embeddings_instance = OpenAIEmbeddings(\n model=model,\n dimensions=dimensions or None,\n base_url=api_base or None,\n api_key=api_key,\n chunk_size=chunk_size,\n max_retries=max_retries,\n timeout=request_timeout or None,\n show_progress_bar=show_progress_bar,\n model_kwargs=model_kwargs,\n )\n\n # Create dedicated instances for each available model\n available_models_dict = {}\n for model_name in OPENAI_EMBEDDING_MODEL_NAMES:\n available_models_dict[model_name] = OpenAIEmbeddings(\n model=model_name,\n dimensions=dimensions or None, # Use same dimensions config for all\n base_url=api_base or None,\n api_key=api_key,\n chunk_size=chunk_size,\n max_retries=max_retries,\n timeout=request_timeout or None,\n show_progress_bar=show_progress_bar,\n model_kwargs=model_kwargs,\n )\n\n return EmbeddingsWithModels(\n embeddings=embeddings_instance,\n available_models=available_models_dict,\n )\n except Exception as e:\n msg = f\"Failed to initialize OpenAI embeddings: {e}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise\n\n if provider == \"Ollama\":\n try:\n from langchain_ollama import OllamaEmbeddings\n except ImportError:\n try:\n from langchain_community.embeddings import OllamaEmbeddings\n except ImportError:\n msg = \"Please install langchain-ollama: pip install langchain-ollama\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ImportError(msg) from None\n\n try:\n transformed_base_url = transform_localhost_url(ollama_base_url)\n\n # Check if URL contains /v1 suffix (OpenAI-compatible mode)\n if transformed_base_url and transformed_base_url.rstrip(\"/\").endswith(\"/v1\"):\n # Strip /v1 suffix and log warning\n transformed_base_url = transformed_base_url.rstrip(\"/\").removesuffix(\"/v1\")\n logger.warning(\n \"Detected '/v1' suffix in base URL. The Ollama component uses the native Ollama API, \"\n \"not the OpenAI-compatible API. The '/v1' suffix has been automatically removed. \"\n \"If you want to use the OpenAI-compatible API, please use the OpenAI component instead. \"\n \"Learn more at https://docs.ollama.com/openai#openai-compatibility\"\n )\n\n final_base_url = transformed_base_url or \"http://localhost:11434\"\n\n # Create the primary embedding instance\n embeddings_instance = OllamaEmbeddings(\n model=model,\n base_url=final_base_url,\n **model_kwargs,\n )\n\n # Fetch available Ollama models\n available_model_names = await self.fetch_ollama_models()\n\n # Create dedicated instances for each available model\n available_models_dict = {}\n for model_name in available_model_names:\n available_models_dict[model_name] = OllamaEmbeddings(\n model=model_name,\n base_url=final_base_url,\n **model_kwargs,\n )\n\n return EmbeddingsWithModels(\n embeddings=embeddings_instance,\n available_models=available_models_dict,\n )\n except Exception as e:\n msg = f\"Failed to initialize Ollama embeddings: {e}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise\n\n if provider == \"IBM watsonx.ai\":\n try:\n from langchain_ibm import WatsonxEmbeddings\n except ImportError:\n msg = \"Please install langchain-ibm: pip install langchain-ibm\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ImportError(msg) from None\n\n if not api_key:\n msg = \"IBM watsonx.ai API key is required when using IBM watsonx.ai provider\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n project_id = self.project_id\n\n if not project_id:\n msg = \"Project ID is required for IBM watsonx.ai provider\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n try:\n from ibm_watsonx_ai import APIClient, Credentials\n\n final_url = base_url_ibm_watsonx or \"https://us-south.ml.cloud.ibm.com\"\n\n credentials = Credentials(\n api_key=self.api_key,\n url=final_url,\n )\n\n api_client = APIClient(credentials)\n\n params = {\n EmbedTextParamsMetaNames.TRUNCATE_INPUT_TOKENS: self.truncate_input_tokens,\n EmbedTextParamsMetaNames.RETURN_OPTIONS: {\"input_text\": self.input_text},\n }\n\n # Create the primary embedding instance\n embeddings_instance = WatsonxEmbeddings(\n model_id=model,\n params=params,\n watsonx_client=api_client,\n project_id=project_id,\n )\n\n # Fetch available IBM watsonx.ai models\n available_model_names = self.fetch_ibm_models(final_url)\n\n # Create dedicated instances for each available model\n available_models_dict = {}\n for model_name in available_model_names:\n available_models_dict[model_name] = WatsonxEmbeddings(\n model_id=model_name,\n params=params,\n watsonx_client=api_client,\n project_id=project_id,\n )\n\n return EmbeddingsWithModels(\n embeddings=embeddings_instance,\n available_models=available_models_dict,\n )\n except Exception as e:\n msg = f\"Failed to authenticate with IBM watsonx.ai: {e}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise\n\n msg = f\"Unknown provider: {provider}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n async def update_build_config(\n self, build_config: dotdict, field_value: Any, field_name: str | None = None\n ) -> dotdict:\n # Handle fail_safe_mode changes first - set all required fields to False if enabled\n if field_name == \"fail_safe_mode\":\n if field_value: # If fail_safe_mode is enabled\n build_config[\"api_key\"][\"required\"] = False\n elif hasattr(self, \"provider\"):\n # If fail_safe_mode is disabled, restore required flags based on provider\n if self.provider in [\"OpenAI\", \"IBM watsonx.ai\"]:\n build_config[\"api_key\"][\"required\"] = True\n else: # Ollama\n build_config[\"api_key\"][\"required\"] = False\n\n if field_name == \"provider\":\n if field_value == \"OpenAI\":\n build_config[\"model\"][\"options\"] = OPENAI_EMBEDDING_MODEL_NAMES\n build_config[\"model\"][\"value\"] = OPENAI_EMBEDDING_MODEL_NAMES[0]\n build_config[\"api_key\"][\"display_name\"] = \"OpenAI API Key\"\n # Only set required=True if fail_safe_mode is not enabled\n build_config[\"api_key\"][\"required\"] = not (hasattr(self, \"fail_safe_mode\") and self.fail_safe_mode)\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"api_base\"][\"display_name\"] = \"OpenAI API Base URL\"\n build_config[\"api_base\"][\"advanced\"] = True\n build_config[\"api_base\"][\"show\"] = True\n build_config[\"ollama_base_url\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n build_config[\"truncate_input_tokens\"][\"show\"] = False\n build_config[\"input_text\"][\"show\"] = False\n elif field_value == \"Ollama\":\n build_config[\"ollama_base_url\"][\"show\"] = True\n\n if await is_valid_ollama_url(url=self.ollama_base_url):\n try:\n models = await self.fetch_ollama_models()\n build_config[\"model\"][\"options\"] = models\n build_config[\"model\"][\"value\"] = models[0] if models else \"\"\n except ValueError:\n build_config[\"model\"][\"options\"] = []\n build_config[\"model\"][\"value\"] = \"\"\n else:\n build_config[\"model\"][\"options\"] = []\n build_config[\"model\"][\"value\"] = \"\"\n build_config[\"truncate_input_tokens\"][\"show\"] = False\n build_config[\"input_text\"][\"show\"] = False\n build_config[\"api_key\"][\"display_name\"] = \"API Key (Optional)\"\n build_config[\"api_key\"][\"required\"] = False\n build_config[\"api_key\"][\"show\"] = False\n build_config[\"api_base\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n\n elif field_value == \"IBM watsonx.ai\":\n build_config[\"model\"][\"options\"] = self.fetch_ibm_models(base_url=self.base_url_ibm_watsonx)\n build_config[\"model\"][\"value\"] = self.fetch_ibm_models(base_url=self.base_url_ibm_watsonx)[0]\n build_config[\"api_key\"][\"display_name\"] = \"IBM watsonx.ai API Key\"\n # Only set required=True if fail_safe_mode is not enabled\n build_config[\"api_key\"][\"required\"] = not (hasattr(self, \"fail_safe_mode\") and self.fail_safe_mode)\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"api_base\"][\"show\"] = False\n build_config[\"ollama_base_url\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = True\n build_config[\"project_id\"][\"show\"] = True\n build_config[\"truncate_input_tokens\"][\"show\"] = True\n build_config[\"input_text\"][\"show\"] = True\n elif field_name == \"base_url_ibm_watsonx\":\n build_config[\"model\"][\"options\"] = self.fetch_ibm_models(base_url=field_value)\n build_config[\"model\"][\"value\"] = self.fetch_ibm_models(base_url=field_value)[0]\n elif field_name == \"ollama_base_url\":\n # # Refresh Ollama models when base URL changes\n # if hasattr(self, \"provider\") and self.provider == \"Ollama\":\n # Use field_value if provided, otherwise fall back to instance attribute\n ollama_url = self.ollama_base_url\n if await is_valid_ollama_url(url=ollama_url):\n try:\n models = await self.fetch_ollama_models()\n build_config[\"model\"][\"options\"] = models\n build_config[\"model\"][\"value\"] = models[0] if models else \"\"\n except ValueError:\n await logger.awarning(\"Failed to fetch Ollama embedding models.\")\n build_config[\"model\"][\"options\"] = []\n build_config[\"model\"][\"value\"] = \"\"\n\n elif field_name == \"model\" and self.provider == \"Ollama\":\n ollama_url = self.ollama_base_url\n if await is_valid_ollama_url(url=ollama_url):\n try:\n models = await self.fetch_ollama_models()\n build_config[\"model\"][\"options\"] = models\n except ValueError:\n await logger.awarning(\"Failed to refresh Ollama embedding models.\")\n build_config[\"model\"][\"options\"] = []\n\n return build_config\n"
|
|
},
|
|
"dimensions": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Dimensions",
|
|
"dynamic": false,
|
|
"info": "The number of dimensions the resulting output embeddings should have. Only supported by certain models.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "dimensions",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": ""
|
|
},
|
|
"fail_safe_mode": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Fail-Safe Mode",
|
|
"dynamic": false,
|
|
"info": "When enabled, errors will be logged instead of raising exceptions. The component will return None on error.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "fail_safe_mode",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": true
|
|
},
|
|
"input_text": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Include the original text in the output",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "input_text",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": true
|
|
},
|
|
"is_refresh": false,
|
|
"max_retries": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Max Retries",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "max_retries",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 3
|
|
},
|
|
"model": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Model Name",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Select the embedding model to use",
|
|
"name": "model",
|
|
"options": [
|
|
"text-embedding-3-small"
|
|
],
|
|
"options_metadata": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"refresh_button": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "text-embedding-3-small"
|
|
},
|
|
"model_kwargs": {
|
|
"_input_type": "DictInput",
|
|
"advanced": true,
|
|
"display_name": "Model Kwargs",
|
|
"dynamic": false,
|
|
"info": "Additional keyword arguments to pass to the model.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "model_kwargs",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"track_in_telemetry": false,
|
|
"type": "dict",
|
|
"value": {}
|
|
},
|
|
"ollama_base_url": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": false,
|
|
"display_name": "Ollama API URL",
|
|
"dynamic": false,
|
|
"info": "Endpoint of the Ollama API (Ollama only). Defaults to http://localhost:11434",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "ollama_base_url",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"project_id": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": false,
|
|
"display_name": "Project ID",
|
|
"dynamic": false,
|
|
"info": "IBM watsonx.ai Project ID (required for IBM watsonx.ai)",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "project_id",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"provider": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Model Provider",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Select the embedding model provider",
|
|
"name": "provider",
|
|
"options": [
|
|
"OpenAI",
|
|
"Ollama",
|
|
"IBM watsonx.ai"
|
|
],
|
|
"options_metadata": [
|
|
{
|
|
"icon": "OpenAI"
|
|
},
|
|
{
|
|
"icon": "Ollama"
|
|
},
|
|
{
|
|
"icon": "WatsonxAI"
|
|
}
|
|
],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"selected_metadata": {
|
|
"icon": "OpenAI"
|
|
},
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "OpenAI"
|
|
},
|
|
"request_timeout": {
|
|
"_input_type": "FloatInput",
|
|
"advanced": true,
|
|
"display_name": "Request Timeout",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "request_timeout",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": 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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": false
|
|
},
|
|
"truncate_input_tokens": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Truncate Input Tokens",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "truncate_input_tokens",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 200
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"showNode": true,
|
|
"type": "EmbeddingModel"
|
|
},
|
|
"dragging": false,
|
|
"id": "EmbeddingModel-ooLFP",
|
|
"measured": {
|
|
"height": 451,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": -1091.341314577015,
|
|
"y": 1237.2170349466728
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"node": {
|
|
"base_classes": [
|
|
"Data",
|
|
"DataFrame",
|
|
"VectorStore"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {},
|
|
"description": "Store and search documents using OpenSearch with multi-model hybrid semantic and keyword search.",
|
|
"display_name": "OpenSearch (Multi-Model Multi-Embedding)",
|
|
"documentation": "",
|
|
"edited": true,
|
|
"field_order": [
|
|
"docs_metadata",
|
|
"opensearch_url",
|
|
"index_name",
|
|
"engine",
|
|
"space_type",
|
|
"ef_construction",
|
|
"m",
|
|
"num_candidates",
|
|
"ingest_data",
|
|
"search_query",
|
|
"should_cache_vector_store",
|
|
"embedding",
|
|
"embedding_model_name",
|
|
"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",
|
|
"last_updated": "2025-12-02T21:30:53.860Z",
|
|
"legacy": false,
|
|
"lf_version": "1.7.0.dev21",
|
|
"metadata": {
|
|
"code_hash": "db60433453a8",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "opensearchpy",
|
|
"version": "2.8.0"
|
|
},
|
|
{
|
|
"name": "lfx",
|
|
"version": "0.2.0.dev21"
|
|
}
|
|
],
|
|
"total_dependencies": 2
|
|
},
|
|
"module": "custom_components.opensearch_multimodel_multiembedding"
|
|
},
|
|
"minimized": false,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Search Results",
|
|
"group_outputs": false,
|
|
"hidden": null,
|
|
"loop_types": 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,
|
|
"loop_types": 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,
|
|
"loop_types": null,
|
|
"method": "as_vector_store",
|
|
"name": "vectorstoreconnection",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "VectorStore",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"VectorStore"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"template": {
|
|
"_frontend_node_flow_id": {
|
|
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
|
|
},
|
|
"_frontend_node_folder_id": {
|
|
"value": "69a7745e-dfb8-40a7-b5cb-5da3af0b10b6"
|
|
},
|
|
"_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": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": 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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": 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 copy\nimport json\nimport time\nimport uuid\nfrom concurrent.futures import ThreadPoolExecutor, as_completed\nfrom typing import Any\n\nfrom opensearchpy import OpenSearch, helpers\nfrom opensearchpy.exceptions import OpenSearchException, RequestError\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\ndef normalize_model_name(model_name: str) -> str:\n \"\"\"Normalize embedding model name for use as field suffix.\n\n Converts model names to valid OpenSearch field names by replacing\n special characters and ensuring alphanumeric format.\n\n Args:\n model_name: Original embedding model name (e.g., \"text-embedding-3-small\")\n\n Returns:\n Normalized field suffix (e.g., \"text_embedding_3_small\")\n \"\"\"\n normalized = model_name.lower()\n # Replace common separators with underscores\n normalized = normalized.replace(\"-\", \"_\").replace(\":\", \"_\").replace(\"/\", \"_\").replace(\".\", \"_\")\n # Remove any non-alphanumeric characters except underscores\n normalized = \"\".join(c if c.isalnum() or c == \"_\" else \"_\" for c in normalized)\n # Remove duplicate underscores\n while \"__\" in normalized:\n normalized = normalized.replace(\"__\", \"_\")\n return normalized.strip(\"_\")\n\n\ndef get_embedding_field_name(model_name: str) -> str:\n \"\"\"Get the dynamic embedding field name for a model.\n\n Args:\n model_name: Embedding model name\n\n Returns:\n Field name in format: chunk_embedding_{normalized_model_name}\n \"\"\"\n logger.info(f\"chunk_embedding_{normalize_model_name(model_name)}\")\n return f\"chunk_embedding_{normalize_model_name(model_name)}\"\n\n\n@vector_store_connection\nclass OpenSearchVectorStoreComponentMultimodalMultiEmbedding(LCVectorStoreComponent):\n \"\"\"OpenSearch Vector Store Component with Multi-Model 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:\n - Multiple embedding models per index with dynamic field names\n - Automatic detection and querying of all available embedding models\n - Parallel embedding generation for multi-model search\n - Document ingestion with model tracking\n - Advanced filtering and aggregations\n - Flexible authentication options\n\n Features:\n - Multi-model vector storage with dynamic fields (chunk_embedding_{model_name})\n - Hybrid search combining multiple KNN queries (dis_max) + keyword matching\n - Auto-detection of available models in the index\n - Parallel query embedding generation for all detected models\n - Vector storage with configurable engines (jvector, nmslib, faiss, lucene)\n - Flexible authentication (Basic auth, JWT tokens)\n\n Model Name Resolution:\n - Priority: deployment > model > model_name attributes\n - This ensures correct matching between embedding objects and index fields\n - When multiple embeddings are provided, specify embedding_model_name to select which one to use\n - During search, each detected model in the index is matched to its corresponding embedding object\n \"\"\"\n\n display_name: str = \"OpenSearch (Multi-Model Multi-Embedding)\"\n icon: str = \"OpenSearch\"\n description: str = (\n \"Store and search documents using OpenSearch with multi-model hybrid semantic and keyword search.\"\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 \"embedding_model_name\",\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 \"num_candidates\",\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 input_types=[\"Data\"],\n ),\n StrInput(\n name=\"opensearch_url\",\n display_name=\"OpenSearch URL\",\n value=\"http://localhost:9200\",\n info=(\n \"The connection URL for your OpenSearch cluster \"\n \"(e.g., http://localhost:9200 for local development or your cloud endpoint).\"\n ),\n ),\n StrInput(\n name=\"index_name\",\n display_name=\"Index Name\",\n value=\"langflow\",\n info=(\n \"The OpenSearch index name where documents will be stored and searched. \"\n \"Will be created automatically if it doesn't exist.\"\n ),\n ),\n DropdownInput(\n name=\"engine\",\n display_name=\"Vector Engine\",\n options=[\"jvector\", \"nmslib\", \"faiss\", \"lucene\"],\n value=\"jvector\",\n info=(\n \"Vector search engine for similarity calculations. 'jvector' is recommended for most use cases. \"\n \"Note: Amazon OpenSearch Serverless only supports 'nmslib' or 'faiss'.\"\n ),\n advanced=True,\n ),\n DropdownInput(\n name=\"space_type\",\n display_name=\"Distance Metric\",\n options=[\"l2\", \"l1\", \"cosinesimil\", \"linf\", \"innerproduct\"],\n value=\"l2\",\n info=(\n \"Distance metric for calculating vector similarity. 'l2' (Euclidean) is most common, \"\n \"'cosinesimil' for cosine similarity, 'innerproduct' for dot product.\"\n ),\n advanced=True,\n ),\n IntInput(\n name=\"ef_construction\",\n display_name=\"EF Construction\",\n value=512,\n info=(\n \"Size of the dynamic candidate list during index construction. \"\n \"Higher values improve recall but increase indexing time and memory usage.\"\n ),\n advanced=True,\n ),\n IntInput(\n name=\"m\",\n display_name=\"M Parameter\",\n value=16,\n info=(\n \"Number of bidirectional connections for each vector in the HNSW graph. \"\n \"Higher values improve search quality but increase memory usage and indexing time.\"\n ),\n advanced=True,\n ),\n IntInput(\n name=\"num_candidates\",\n display_name=\"Candidate Pool Size\",\n value=1000,\n info=(\n \"Number of approximate neighbors to consider for each KNN query. \"\n \"Some OpenSearch deployments do not support this parameter; set to 0 to disable.\"\n ),\n advanced=True,\n ),\n *LCVectorStoreComponent.inputs, # includes search_query, add_documents, etc.\n HandleInput(name=\"embedding\", display_name=\"Embedding\", input_types=[\"Embeddings\"], is_list=True),\n StrInput(\n name=\"embedding_model_name\",\n display_name=\"Embedding Model Name\",\n value=\"\",\n info=(\n \"Name of the embedding model to use for ingestion. This selects which embedding from the list \"\n \"will be used to embed documents. Matches on deployment, model, model_id, or model_name. \"\n \"For duplicate deployments, use combined format: 'deployment:model' \"\n \"(e.g., 'text-embedding-ada-002:text-embedding-3-large'). \"\n \"Leave empty to use the first embedding. Error message will show all available identifiers.\"\n ),\n advanced=False,\n ),\n StrInput(\n name=\"vector_field\",\n display_name=\"Legacy Vector Field Name\",\n value=\"chunk_embedding\",\n advanced=True,\n info=(\n \"Legacy field name for backward compatibility. New documents use dynamic fields \"\n \"(chunk_embedding_{model_name}) based on the embedding_model_name.\"\n ),\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=True,\n ),\n SecretStrInput(\n name=\"password\",\n display_name=\"OpenSearch Password\",\n value=\"admin\",\n show=True,\n ),\n SecretStrInput(\n name=\"jwt_token\",\n display_name=\"JWT Token\",\n value=\"JWT\",\n load_from_db=False,\n show=False,\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 def _get_embedding_model_name(self, embedding_obj=None) -> str:\n \"\"\"Get the embedding model name from component config or embedding object.\n\n Priority: deployment > model > model_id > model_name\n This ensures we use the actual model being deployed, not just the configured model.\n Supports multiple embedding providers (OpenAI, Watsonx, Cohere, etc.)\n\n Args:\n embedding_obj: Specific embedding object to get name from (optional)\n\n Returns:\n Embedding model name\n\n Raises:\n ValueError: If embedding model name cannot be determined\n \"\"\"\n # First try explicit embedding_model_name input\n if hasattr(self, \"embedding_model_name\") and self.embedding_model_name:\n return self.embedding_model_name.strip()\n\n # Try to get from provided embedding object\n if embedding_obj:\n # Priority: deployment > model > model_id > model_name\n if hasattr(embedding_obj, \"deployment\") and embedding_obj.deployment:\n return str(embedding_obj.deployment)\n if hasattr(embedding_obj, \"model\") and embedding_obj.model:\n return str(embedding_obj.model)\n if hasattr(embedding_obj, \"model_id\") and embedding_obj.model_id:\n return str(embedding_obj.model_id)\n if hasattr(embedding_obj, \"model_name\") and embedding_obj.model_name:\n return str(embedding_obj.model_name)\n\n # Try to get from embedding component (legacy single embedding)\n if hasattr(self, \"embedding\") and self.embedding:\n # Handle list of embeddings\n if isinstance(self.embedding, list) and len(self.embedding) > 0:\n first_emb = self.embedding[0]\n if hasattr(first_emb, \"deployment\") and first_emb.deployment:\n return str(first_emb.deployment)\n if hasattr(first_emb, \"model\") and first_emb.model:\n return str(first_emb.model)\n if hasattr(first_emb, \"model_id\") and first_emb.model_id:\n return str(first_emb.model_id)\n if hasattr(first_emb, \"model_name\") and first_emb.model_name:\n return str(first_emb.model_name)\n # Handle single embedding\n elif not isinstance(self.embedding, list):\n if hasattr(self.embedding, \"deployment\") and self.embedding.deployment:\n return str(self.embedding.deployment)\n if hasattr(self.embedding, \"model\") and self.embedding.model:\n return str(self.embedding.model)\n if hasattr(self.embedding, \"model_id\") and self.embedding.model_id:\n return str(self.embedding.model_id)\n if hasattr(self.embedding, \"model_name\") and self.embedding.model_name:\n return str(self.embedding.model_name)\n\n msg = (\n \"Could not determine embedding model name. \"\n \"Please set the 'embedding_model_name' field or ensure the embedding component \"\n \"has a 'deployment', 'model', 'model_id', or 'model_name' attribute.\"\n )\n raise ValueError(msg)\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 Includes the embedding_model keyword field for tracking which model was used.\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 \"embedding_model\": {\"type\": \"keyword\"}, # Track which model was used\n \"embedding_dimensions\": {\"type\": \"integer\"},\n }\n },\n }\n\n def _ensure_embedding_field_mapping(\n self,\n client: OpenSearch,\n index_name: str,\n field_name: str,\n dim: int,\n engine: str,\n space_type: str,\n ef_construction: int,\n m: int,\n ) -> None:\n \"\"\"Lazily add a dynamic embedding field to the index if it doesn't exist.\n\n This allows adding new embedding models without recreating the entire index.\n Also ensures the embedding_model tracking field exists.\n\n Args:\n client: OpenSearch client instance\n index_name: Target index name\n field_name: Dynamic field name for this embedding model\n dim: Vector dimensionality\n engine: Vector search engine\n space_type: Distance metric\n ef_construction: Construction parameter\n m: HNSW parameter\n \"\"\"\n try:\n mapping = {\n \"properties\": {\n field_name: {\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 # Also ensure the embedding_model tracking field exists as keyword\n \"embedding_model\": {\"type\": \"keyword\"},\n \"embedding_dimensions\": {\"type\": \"integer\"},\n }\n }\n client.indices.put_mapping(index=index_name, body=mapping)\n logger.info(f\"Added/updated embedding field mapping: {field_name}\")\n except Exception as e:\n logger.warning(f\"Could not add embedding field mapping for {field_name}: {e}\")\n raise\n\n properties = self._get_index_properties(client)\n if not self._is_knn_vector_field(properties, field_name):\n msg = f\"Field '{field_name}' is not mapped as knn_vector. Current mapping: {properties.get(field_name)}\"\n logger.aerror(msg)\n raise ValueError(msg)\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 embedding_model: str = \"unknown\",\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. Each document\n is tagged with the embedding_model name for tracking.\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 embedding_model: Name of the embedding model used\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 vector_dimensions = len(embeddings[0]) if embeddings else None\n\n for i, text in enumerate(texts):\n metadata = metadatas[i] if metadatas else {}\n if vector_dimensions is not None and \"embedding_dimensions\" not in metadata:\n metadata = {**metadata, \"embedding_dimensions\": vector_dimensions}\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 \"embedding_model\": embedding_model, # Track which model was used\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 client = self.build_client()\n\n # Check if we're in ingestion-only mode (no search query)\n has_search_query = bool((self.search_query or \"\").strip())\n if not has_search_query:\n logger.debug(\"Ingestion-only mode activated: search operations will be skipped\")\n logger.debug(\"Starting ingestion mode...\")\n\n logger.warning(f\"Embedding: {self.embedding}\")\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 using the selected model\n - Creates appropriate index mappings with dynamic field names\n - Bulk inserts documents with vectors and model tracking\n\n Args:\n client: OpenSearch client for performing operations\n \"\"\"\n logger.debug(\"[INGESTION] _add_documents_to_vector_store called\")\n # Convert DataFrame to Data if needed using parent's method\n self.ingest_data = self._prepare_ingest_data()\n\n logger.debug(\n f\"[INGESTION] ingest_data type: \"\n f\"{type(self.ingest_data)}, length: {len(self.ingest_data) if self.ingest_data else 0}\"\n )\n logger.debug(\n f\"[INGESTION] ingest_data content: \"\n f\"{self.ingest_data[:2] if self.ingest_data and len(self.ingest_data) > 0 else 'empty'}\"\n )\n\n docs = self.ingest_data or []\n if not docs:\n logger.debug(\"Ingestion complete: No documents provided\")\n return\n\n if not self.embedding:\n msg = \"Embedding handle is required to embed documents.\"\n raise ValueError(msg)\n\n # Normalize embedding to list first\n embeddings_list = self.embedding if isinstance(self.embedding, list) else [self.embedding]\n\n # Filter out None values (fail-safe mode) - do this BEFORE checking if empty\n embeddings_list = [e for e in embeddings_list if e is not None]\n\n # NOW check if we have any valid embeddings left after filtering\n if not embeddings_list:\n logger.warning(\"All embeddings returned None (fail-safe mode enabled). Skipping document ingestion.\")\n self.log(\"Embedding returned None (fail-safe mode enabled). Skipping document ingestion.\")\n return\n\n logger.debug(f\"[INGESTION] Valid embeddings after filtering: {len(embeddings_list)}\")\n self.log(f\"Available embedding models: {len(embeddings_list)}\")\n\n # Select the embedding to use for ingestion\n selected_embedding = None\n embedding_model = None\n\n # If embedding_model_name is specified, find matching embedding\n if hasattr(self, \"embedding_model_name\") and self.embedding_model_name and self.embedding_model_name.strip():\n target_model_name = self.embedding_model_name.strip()\n self.log(f\"Looking for embedding model: {target_model_name}\")\n\n for emb_obj in embeddings_list:\n # Check all possible model identifiers (deployment, model, model_id, model_name)\n # Also check available_models list from EmbeddingsWithModels\n possible_names = []\n deployment = getattr(emb_obj, \"deployment\", None)\n model = getattr(emb_obj, \"model\", None)\n model_id = getattr(emb_obj, \"model_id\", None)\n model_name = getattr(emb_obj, \"model_name\", None)\n available_models_attr = getattr(emb_obj, \"available_models\", None)\n\n if deployment:\n possible_names.append(str(deployment))\n if model:\n possible_names.append(str(model))\n if model_id:\n possible_names.append(str(model_id))\n if model_name:\n possible_names.append(str(model_name))\n\n # Also add combined identifier\n if deployment and model and deployment != model:\n possible_names.append(f\"{deployment}:{model}\")\n\n # Add all models from available_models dict\n if available_models_attr and isinstance(available_models_attr, dict):\n possible_names.extend(\n str(model_key).strip()\n for model_key in available_models_attr\n if model_key and str(model_key).strip()\n )\n\n # Match if target matches any of the possible names\n if target_model_name in possible_names:\n # Check if target is in available_models dict - use dedicated instance\n if (\n available_models_attr\n and isinstance(available_models_attr, dict)\n and target_model_name in available_models_attr\n ):\n # Use the dedicated embedding instance from the dict\n selected_embedding = available_models_attr[target_model_name]\n embedding_model = target_model_name\n self.log(f\"Found dedicated embedding instance for '{embedding_model}' in available_models dict\")\n else:\n # Traditional identifier match\n selected_embedding = emb_obj\n embedding_model = self._get_embedding_model_name(emb_obj)\n self.log(f\"Found matching embedding model: {embedding_model} (matched on: {target_model_name})\")\n break\n\n if not selected_embedding:\n # Build detailed list of available embeddings with all their identifiers\n available_info = []\n for idx, emb in enumerate(embeddings_list):\n emb_type = type(emb).__name__\n identifiers = []\n deployment = getattr(emb, \"deployment\", None)\n model = getattr(emb, \"model\", None)\n model_id = getattr(emb, \"model_id\", None)\n model_name = getattr(emb, \"model_name\", None)\n available_models_attr = getattr(emb, \"available_models\", None)\n\n if deployment:\n identifiers.append(f\"deployment='{deployment}'\")\n if model:\n identifiers.append(f\"model='{model}'\")\n if model_id:\n identifiers.append(f\"model_id='{model_id}'\")\n if model_name:\n identifiers.append(f\"model_name='{model_name}'\")\n\n # Add combined identifier as an option\n if deployment and model and deployment != model:\n identifiers.append(f\"combined='{deployment}:{model}'\")\n\n # Add available_models dict if present\n if available_models_attr and isinstance(available_models_attr, dict):\n identifiers.append(f\"available_models={list(available_models_attr.keys())}\")\n\n available_info.append(\n f\" [{idx}] {emb_type}: {', '.join(identifiers) if identifiers else 'No identifiers'}\"\n )\n\n msg = (\n f\"Embedding model '{target_model_name}' not found in available embeddings.\\n\\n\"\n f\"Available embeddings:\\n\" + \"\\n\".join(available_info) + \"\\n\\n\"\n \"Please set 'embedding_model_name' to one of the identifier values shown above \"\n \"(use the value after the '=' sign, without quotes).\\n\"\n \"For duplicate deployments, use the 'combined' format.\\n\"\n \"Or leave it empty to use the first embedding.\"\n )\n raise ValueError(msg)\n else:\n # Use first embedding if no model name specified\n selected_embedding = embeddings_list[0]\n embedding_model = self._get_embedding_model_name(selected_embedding)\n self.log(f\"No embedding_model_name specified, using first embedding: {embedding_model}\")\n\n dynamic_field_name = get_embedding_field_name(embedding_model)\n\n logger.info(f\"Selected embedding model for ingestion: '{embedding_model}'\")\n self.log(f\"Using embedding model for ingestion: {embedding_model}\")\n self.log(f\"Dynamic vector field: {dynamic_field_name}\")\n\n # Log embedding details for debugging\n if hasattr(selected_embedding, \"deployment\"):\n logger.info(f\"Embedding deployment: {selected_embedding.deployment}\")\n if hasattr(selected_embedding, \"model\"):\n logger.info(f\"Embedding model: {selected_embedding.model}\")\n if hasattr(selected_embedding, \"model_id\"):\n logger.info(f\"Embedding model_id: {selected_embedding.model_id}\")\n if hasattr(selected_embedding, \"dimensions\"):\n logger.info(f\"Embedding dimensions: {selected_embedding.dimensions}\")\n if hasattr(selected_embedding, \"available_models\"):\n logger.info(f\"Embedding available_models: {selected_embedding.available_models}\")\n\n # No model switching needed - each model in available_models has its own dedicated instance\n # The selected_embedding is already configured correctly for the target model\n logger.info(f\"Using embedding instance for '{embedding_model}' - pre-configured and ready to use\")\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 logger.debug(f\"[LF] Docs metadata {self.docs_metadata}\")\n if hasattr(self, \"docs_metadata\") and self.docs_metadata:\n logger.info(f\"[LF] Docs metadata {self.docs_metadata}\")\n if isinstance(self.docs_metadata[-1], Data):\n logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n self.docs_metadata = self.docs_metadata[-1].data\n logger.info(f\"[LF] Docs metadata is a Data object {self.docs_metadata}\")\n additional_metadata.update(self.docs_metadata)\n else:\n for item in self.docs_metadata:\n if isinstance(item, dict) and \"key\" in item and \"value\" in item:\n additional_metadata[item[\"key\"]] = item[\"value\"]\n # Replace string \"None\" values with actual None\n for key, value in additional_metadata.items():\n if value == \"None\":\n additional_metadata[key] = None\n logger.info(f\"[LF] Additional metadata {additional_metadata}\")\n for doc_obj in docs:\n data_copy = json.loads(doc_obj.model_dump_json())\n text = data_copy.pop(doc_obj.text_key, doc_obj.default_value)\n texts.append(text)\n\n # Merge additional metadata from table input\n data_copy.update(additional_metadata)\n\n metadatas.append(data_copy)\n self.log(metadatas)\n\n # Generate embeddings with rate-limit-aware retry logic using tenacity\n from tenacity import (\n retry,\n retry_if_exception,\n stop_after_attempt,\n wait_exponential,\n )\n\n def is_rate_limit_error(exception: Exception) -> bool:\n \"\"\"Check if exception is a rate limit error (429).\"\"\"\n error_str = str(exception).lower()\n return \"429\" in error_str or \"rate_limit\" in error_str or \"rate limit\" in error_str\n\n def is_other_retryable_error(exception: Exception) -> bool:\n \"\"\"Check if exception is retryable but not a rate limit error.\"\"\"\n # Retry on most exceptions except for specific non-retryable ones\n # Add other non-retryable exceptions here if needed\n return not is_rate_limit_error(exception)\n\n # Create retry decorator for rate limit errors (longer backoff)\n retry_on_rate_limit = retry(\n retry=retry_if_exception(is_rate_limit_error),\n stop=stop_after_attempt(5),\n wait=wait_exponential(multiplier=2, min=2, max=30),\n reraise=True,\n before_sleep=lambda retry_state: logger.warning(\n f\"Rate limit hit for chunk (attempt {retry_state.attempt_number}/5), \"\n f\"backing off for {retry_state.next_action.sleep:.1f}s\"\n ),\n )\n\n # Create retry decorator for other errors (shorter backoff)\n retry_on_other_errors = retry(\n retry=retry_if_exception(is_other_retryable_error),\n stop=stop_after_attempt(3),\n wait=wait_exponential(multiplier=1, min=1, max=8),\n reraise=True,\n before_sleep=lambda retry_state: logger.warning(\n f\"Error embedding chunk (attempt {retry_state.attempt_number}/3), \"\n f\"retrying in {retry_state.next_action.sleep:.1f}s: {retry_state.outcome.exception()}\"\n ),\n )\n\n def embed_chunk_with_retry(chunk_text: str, chunk_idx: int) -> list[float]:\n \"\"\"Embed a single chunk with rate-limit-aware retry logic.\"\"\"\n\n @retry_on_rate_limit\n @retry_on_other_errors\n def _embed(text: str) -> list[float]:\n return selected_embedding.embed_documents([text])[0]\n\n try:\n return _embed(chunk_text)\n except Exception as e:\n logger.error(\n f\"Failed to embed chunk {chunk_idx} after all retries: {e}\",\n error=str(e),\n )\n raise\n\n # Restrict concurrency for IBM/Watsonx models to avoid rate limits\n is_ibm = (embedding_model and \"ibm\" in str(embedding_model).lower()) or (\n selected_embedding and \"watsonx\" in type(selected_embedding).__name__.lower()\n )\n logger.debug(f\"Is IBM: {is_ibm}\")\n\n # For IBM models, use sequential processing with rate limiting\n # For other models, use parallel processing\n vectors: list[list[float]] = [None] * len(texts)\n\n if is_ibm:\n # Sequential processing with inter-request delay for IBM models\n inter_request_delay = 0.6 # ~1.67 req/s, safely under 2 req/s limit\n logger.info(\n f\"Using sequential processing for IBM model with {inter_request_delay}s delay between requests\"\n )\n\n for idx, chunk in enumerate(texts):\n if idx > 0:\n # Add delay between requests (but not before the first one)\n time.sleep(inter_request_delay)\n vectors[idx] = embed_chunk_with_retry(chunk, idx)\n else:\n # Parallel processing for non-IBM models\n max_workers = min(max(len(texts), 1), 8)\n logger.debug(f\"Using parallel processing with {max_workers} workers\")\n\n with ThreadPoolExecutor(max_workers=max_workers) as executor:\n futures = {executor.submit(embed_chunk_with_retry, chunk, idx): idx for idx, chunk in enumerate(texts)}\n for future in as_completed(futures):\n idx = futures[future]\n vectors[idx] = future.result()\n\n if not vectors:\n self.log(f\"No vectors generated from documents for model {embedding_model}.\")\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=dynamic_field_name, # Use dynamic field name\n )\n\n # Ensure index exists with baseline mapping\n try:\n if not client.indices.exists(index=self.index_name):\n self.log(f\"Creating index '{self.index_name}' with base mapping\")\n client.indices.create(index=self.index_name, body=mapping)\n except RequestError as creation_error:\n if creation_error.error != \"resource_already_exists_exception\":\n logger.warning(f\"Failed to create index '{self.index_name}': {creation_error}\")\n\n # Ensure the dynamic field exists in the index\n self._ensure_embedding_field_mapping(\n client=client,\n index_name=self.index_name,\n field_name=dynamic_field_name,\n dim=dim,\n engine=engine,\n space_type=space_type,\n ef_construction=ef_construction,\n m=m,\n )\n\n self.log(f\"Indexing {len(texts)} documents into '{self.index_name}' with model '{embedding_model}'...\")\n logger.info(f\"Will store embeddings in field: {dynamic_field_name}\")\n logger.info(f\"Will tag documents with embedding_model: {embedding_model}\")\n\n # Use the bulk ingestion with model tracking\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=dynamic_field_name, # Use dynamic field name\n text_field=\"text\",\n embedding_model=embedding_model, # Track the model\n mapping=mapping,\n is_aoss=is_aoss,\n )\n self.log(metadatas)\n\n logger.info(\n f\"Ingestion complete: Successfully indexed {len(return_ids)} documents with model '{embedding_model}'\"\n )\n self.log(f\"Successfully indexed {len(return_ids)} documents with model {embedding_model}.\")\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 def _detect_available_models(self, client: OpenSearch, filter_clauses: list[dict] | None = None) -> list[str]:\n \"\"\"Detect which embedding models have documents in the index.\n\n Uses aggregation to find all unique embedding_model values, optionally\n filtered to only documents matching the user's filter criteria.\n\n Args:\n client: OpenSearch client instance\n filter_clauses: Optional filter clauses to scope model detection\n\n Returns:\n List of embedding model names found in the index\n \"\"\"\n try:\n agg_query = {\"size\": 0, \"aggs\": {\"embedding_models\": {\"terms\": {\"field\": \"embedding_model\", \"size\": 10}}}}\n\n # Apply filters to model detection if any exist\n if filter_clauses:\n agg_query[\"query\"] = {\"bool\": {\"filter\": filter_clauses}}\n\n logger.debug(f\"Model detection query: {agg_query}\")\n result = client.search(\n index=self.index_name,\n body=agg_query,\n params={\"terminate_after\": 0},\n )\n buckets = result.get(\"aggregations\", {}).get(\"embedding_models\", {}).get(\"buckets\", [])\n models = [b[\"key\"] for b in buckets if b[\"key\"]]\n\n # Log detailed bucket info for debugging\n logger.info(\n f\"Detected embedding models in corpus: {models}\"\n + (f\" (with {len(filter_clauses)} filters)\" if filter_clauses else \"\")\n )\n if not models:\n total_hits = result.get(\"hits\", {}).get(\"total\", {})\n total_count = total_hits.get(\"value\", 0) if isinstance(total_hits, dict) else total_hits\n logger.warning(\n f\"No embedding_model values found in index '{self.index_name}'. \"\n f\"Total docs in index: {total_count}. \"\n f\"This may indicate documents were indexed without the embedding_model field.\"\n )\n except (OpenSearchException, KeyError, ValueError) as e:\n logger.warning(f\"Failed to detect embedding models: {e}\")\n # Fallback to current model\n fallback_model = self._get_embedding_model_name()\n logger.info(f\"Using fallback model: {fallback_model}\")\n return [fallback_model]\n else:\n return models\n\n def _get_index_properties(self, client: OpenSearch) -> dict[str, Any] | None:\n \"\"\"Retrieve flattened mapping properties for the current index.\"\"\"\n try:\n mapping = client.indices.get_mapping(index=self.index_name)\n except OpenSearchException as e:\n logger.warning(\n f\"Failed to fetch mapping for index '{self.index_name}': {e}. Proceeding without mapping metadata.\"\n )\n return None\n\n properties: dict[str, Any] = {}\n for index_data in mapping.values():\n props = index_data.get(\"mappings\", {}).get(\"properties\", {})\n if isinstance(props, dict):\n properties.update(props)\n return properties\n\n def _is_knn_vector_field(self, properties: dict[str, Any] | None, field_name: str) -> bool:\n \"\"\"Check whether the field is mapped as a knn_vector.\"\"\"\n if not field_name:\n return False\n if properties is None:\n logger.warning(f\"Mapping metadata unavailable; assuming field '{field_name}' is usable.\")\n return True\n field_def = properties.get(field_name)\n if not isinstance(field_def, dict):\n return False\n if field_def.get(\"type\") == \"knn_vector\":\n return True\n\n nested_props = field_def.get(\"properties\")\n return bool(isinstance(nested_props, dict) and nested_props.get(\"type\") == \"knn_vector\")\n\n def _get_field_dimension(self, properties: dict[str, Any] | None, field_name: str) -> int | None:\n \"\"\"Get the dimension of a knn_vector field from the index mapping.\n\n Args:\n properties: Index properties from mapping\n field_name: Name of the vector field\n\n Returns:\n Dimension of the field, or None if not found\n \"\"\"\n if not field_name or properties is None:\n return None\n\n field_def = properties.get(field_name)\n if not isinstance(field_def, dict):\n return None\n\n # Check direct knn_vector field\n if field_def.get(\"type\") == \"knn_vector\":\n return field_def.get(\"dimension\")\n\n # Check nested properties\n nested_props = field_def.get(\"properties\")\n if isinstance(nested_props, dict) and nested_props.get(\"type\") == \"knn_vector\":\n return nested_props.get(\"dimension\")\n\n return None\n\n # ---------- search (multi-model hybrid) ----------\n def search(self, query: str | None = None) -> list[dict[str, Any]]:\n \"\"\"Perform multi-model hybrid search combining multiple vector similarities and keyword matching.\n\n This method executes a sophisticated search that:\n 1. Auto-detects all embedding models present in the index\n 2. Generates query embeddings for ALL detected models in parallel\n 3. Combines multiple KNN queries using dis_max (picks best match)\n 4. Adds keyword search with fuzzy matching (30% weight)\n 5. Applies optional filtering and score thresholds\n 6. Returns aggregations for faceted search\n\n Search weights:\n - Semantic search (dis_max across all models): 70%\n - Keyword search: 30%\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\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 # Check if embedding is None (fail-safe mode)\n if self.embedding is None or (isinstance(self.embedding, list) and all(e is None for e in self.embedding)):\n logger.error(\"Embedding returned None (fail-safe mode enabled). Cannot perform search.\")\n return []\n\n # Build filter clauses first so we can use them in model detection\n filter_clauses = self._coerce_filter_clauses(filter_obj)\n\n # Detect available embedding models in the index (scoped by filters)\n available_models = self._detect_available_models(client, filter_clauses)\n\n if not available_models:\n logger.warning(\"No embedding models found in index, using current model\")\n available_models = [self._get_embedding_model_name()]\n\n # Generate embeddings for ALL detected models\n query_embeddings = {}\n\n # Normalize embedding to list\n embeddings_list = self.embedding if isinstance(self.embedding, list) else [self.embedding]\n # Filter out None values (fail-safe mode)\n embeddings_list = [e for e in embeddings_list if e is not None]\n\n if not embeddings_list:\n logger.error(\n \"No valid embeddings available after filtering None values (fail-safe mode). Cannot perform search.\"\n )\n return []\n\n # Create a comprehensive map of model names to embedding objects\n # Check all possible identifiers (deployment, model, model_id, model_name)\n # Also leverage available_models list from EmbeddingsWithModels\n # Handle duplicate identifiers by creating combined keys\n embedding_by_model = {}\n identifier_conflicts = {} # Track which identifiers have conflicts\n\n for idx, emb_obj in enumerate(embeddings_list):\n # Get all possible identifiers for this embedding\n identifiers = []\n deployment = getattr(emb_obj, \"deployment\", None)\n model = getattr(emb_obj, \"model\", None)\n model_id = getattr(emb_obj, \"model_id\", None)\n model_name = getattr(emb_obj, \"model_name\", None)\n dimensions = getattr(emb_obj, \"dimensions\", None)\n available_models_attr = getattr(emb_obj, \"available_models\", None)\n\n logger.info(\n f\"Embedding object {idx}: deployment={deployment}, model={model}, \"\n f\"model_id={model_id}, model_name={model_name}, dimensions={dimensions}, \"\n f\"available_models={available_models_attr}\"\n )\n\n # If this embedding has available_models dict, map all models to their dedicated instances\n if available_models_attr and isinstance(available_models_attr, dict):\n logger.info(\n f\"Embedding object {idx} provides {len(available_models_attr)} models via available_models dict\"\n )\n for model_name_key, dedicated_embedding in available_models_attr.items():\n if model_name_key and str(model_name_key).strip():\n model_str = str(model_name_key).strip()\n if model_str not in embedding_by_model:\n # Use the dedicated embedding instance from the dict\n embedding_by_model[model_str] = dedicated_embedding\n logger.info(f\"Mapped available model '{model_str}' to dedicated embedding instance\")\n else:\n # Conflict detected - track it\n if model_str not in identifier_conflicts:\n identifier_conflicts[model_str] = [embedding_by_model[model_str]]\n identifier_conflicts[model_str].append(dedicated_embedding)\n logger.warning(f\"Available model '{model_str}' has conflict - used by multiple embeddings\")\n\n # Also map traditional identifiers (for backward compatibility)\n if deployment:\n identifiers.append(str(deployment))\n if model:\n identifiers.append(str(model))\n if model_id:\n identifiers.append(str(model_id))\n if model_name:\n identifiers.append(str(model_name))\n\n # Map all identifiers to this embedding object\n for identifier in identifiers:\n if identifier not in embedding_by_model:\n embedding_by_model[identifier] = emb_obj\n logger.info(f\"Mapped identifier '{identifier}' to embedding object {idx}\")\n else:\n # Conflict detected - track it\n if identifier not in identifier_conflicts:\n identifier_conflicts[identifier] = [embedding_by_model[identifier]]\n identifier_conflicts[identifier].append(emb_obj)\n logger.warning(f\"Identifier '{identifier}' has conflict - used by multiple embeddings\")\n\n # For embeddings with model+deployment, create combined identifier\n # This helps when deployment is the same but model differs\n if deployment and model and deployment != model:\n combined_id = f\"{deployment}:{model}\"\n if combined_id not in embedding_by_model:\n embedding_by_model[combined_id] = emb_obj\n logger.info(f\"Created combined identifier '{combined_id}' for embedding object {idx}\")\n\n # Log conflicts\n if identifier_conflicts:\n logger.warning(\n f\"Found {len(identifier_conflicts)} conflicting identifiers. \"\n f\"Consider using combined format 'deployment:model' or specifying unique model names.\"\n )\n for conflict_id, emb_list in identifier_conflicts.items():\n logger.warning(f\" Conflict on '{conflict_id}': {len(emb_list)} embeddings use this identifier\")\n\n logger.info(f\"Generating embeddings for {len(available_models)} models in index\")\n logger.info(f\"Available embedding identifiers: {list(embedding_by_model.keys())}\")\n self.log(f\"[SEARCH] Models detected in index: {available_models}\")\n self.log(f\"[SEARCH] Available embedding identifiers: {list(embedding_by_model.keys())}\")\n\n # Track matching status for debugging\n matched_models = []\n unmatched_models = []\n\n for model_name in available_models:\n try:\n # Check if we have an embedding object for this model\n if model_name in embedding_by_model:\n # Use the matching embedding object directly\n emb_obj = embedding_by_model[model_name]\n emb_deployment = getattr(emb_obj, \"deployment\", None)\n emb_model = getattr(emb_obj, \"model\", None)\n emb_model_id = getattr(emb_obj, \"model_id\", None)\n emb_dimensions = getattr(emb_obj, \"dimensions\", None)\n emb_available_models = getattr(emb_obj, \"available_models\", None)\n\n logger.info(\n f\"Using embedding object for model '{model_name}': \"\n f\"deployment={emb_deployment}, model={emb_model}, model_id={emb_model_id}, \"\n f\"dimensions={emb_dimensions}\"\n )\n\n # Check if this is a dedicated instance from available_models dict\n if emb_available_models and isinstance(emb_available_models, dict):\n logger.info(\n f\"Model '{model_name}' using dedicated instance from available_models dict \"\n f\"(pre-configured with correct model and dimensions)\"\n )\n\n # Use the embedding instance directly - no model switching needed!\n vec = emb_obj.embed_query(q)\n query_embeddings[model_name] = vec\n matched_models.append(model_name)\n logger.info(f\"Generated embedding for model: {model_name} (actual dimensions: {len(vec)})\")\n self.log(f\"[MATCH] Model '{model_name}' - generated {len(vec)}-dim embedding\")\n else:\n # No matching embedding found for this model\n unmatched_models.append(model_name)\n logger.warning(\n f\"No matching embedding found for model '{model_name}'. \"\n f\"This model will be skipped. Available identifiers: {list(embedding_by_model.keys())}\"\n )\n self.log(f\"[NO MATCH] Model '{model_name}' - available: {list(embedding_by_model.keys())}\")\n except (RuntimeError, ValueError, ConnectionError, TimeoutError, AttributeError, KeyError) as e:\n logger.warning(f\"Failed to generate embedding for {model_name}: {e}\")\n self.log(f\"[ERROR] Embedding generation failed for '{model_name}': {e}\")\n\n # Log summary of model matching\n logger.info(f\"Model matching summary: {len(matched_models)} matched, {len(unmatched_models)} unmatched\")\n self.log(f\"[SUMMARY] Model matching: {len(matched_models)} matched, {len(unmatched_models)} unmatched\")\n if unmatched_models:\n self.log(f\"[WARN] Unmatched models in index: {unmatched_models}\")\n\n if not query_embeddings:\n msg = (\n f\"Failed to generate embeddings for any model. \"\n f\"Index has models: {available_models}, but no matching embedding objects found. \"\n f\"Available embedding identifiers: {list(embedding_by_model.keys())}\"\n )\n self.log(f\"[FAIL] Search failed: {msg}\")\n raise ValueError(msg)\n\n index_properties = self._get_index_properties(client)\n legacy_vector_field = getattr(self, \"vector_field\", \"chunk_embedding\")\n\n # Build KNN queries for each model\n embedding_fields: list[str] = []\n knn_queries_with_candidates = []\n knn_queries_without_candidates = []\n\n raw_num_candidates = getattr(self, \"num_candidates\", 1000)\n try:\n num_candidates = int(raw_num_candidates) if raw_num_candidates is not None else 0\n except (TypeError, ValueError):\n num_candidates = 0\n use_num_candidates = num_candidates > 0\n\n for model_name, embedding_vector in query_embeddings.items():\n field_name = get_embedding_field_name(model_name)\n selected_field = field_name\n vector_dim = len(embedding_vector)\n\n # Only use the expected dynamic field - no legacy fallback\n # This prevents dimension mismatches between models\n if not self._is_knn_vector_field(index_properties, selected_field):\n logger.warning(\n f\"Skipping model {model_name}: field '{field_name}' is not mapped as knn_vector. \"\n f\"Documents must be indexed with this embedding model before querying.\"\n )\n self.log(f\"[SKIP] Field '{selected_field}' not a knn_vector - skipping model '{model_name}'\")\n continue\n\n # Validate vector dimensions match the field dimensions\n field_dim = self._get_field_dimension(index_properties, selected_field)\n if field_dim is not None and field_dim != vector_dim:\n logger.error(\n f\"Dimension mismatch for model '{model_name}': \"\n f\"Query vector has {vector_dim} dimensions but field '{selected_field}' expects {field_dim}. \"\n f\"Skipping this model to prevent search errors.\"\n )\n self.log(f\"[DIM MISMATCH] Model '{model_name}': query={vector_dim} vs field={field_dim} - skipping\")\n continue\n\n logger.info(\n f\"Adding KNN query for model '{model_name}': field='{selected_field}', \"\n f\"query_dims={vector_dim}, field_dims={field_dim or 'unknown'}\"\n )\n embedding_fields.append(selected_field)\n\n base_query = {\n \"knn\": {\n selected_field: {\n \"vector\": embedding_vector,\n \"k\": 50,\n }\n }\n }\n\n if use_num_candidates:\n query_with_candidates = copy.deepcopy(base_query)\n query_with_candidates[\"knn\"][selected_field][\"num_candidates\"] = num_candidates\n else:\n query_with_candidates = base_query\n\n knn_queries_with_candidates.append(query_with_candidates)\n knn_queries_without_candidates.append(base_query)\n\n if not knn_queries_with_candidates:\n # No valid fields found - this can happen when:\n # 1. Index is empty (no documents yet)\n # 2. Embedding model has changed and field doesn't exist yet\n # Return empty results instead of failing\n logger.warning(\n \"No valid knn_vector fields found for embedding models. \"\n \"This may indicate an empty index or missing field mappings. \"\n \"Returning empty search results.\"\n )\n self.log(\n f\"[WARN] No valid KNN queries could be built. \"\n f\"Query embeddings generated: {list(query_embeddings.keys())}, \"\n f\"but no matching knn_vector fields found in index.\"\n )\n return []\n\n # Build exists filter - document must have at least one embedding field\n exists_any_embedding = {\n \"bool\": {\"should\": [{\"exists\": {\"field\": f}} for f in set(embedding_fields)], \"minimum_should_match\": 1}\n }\n\n # Combine user filters with exists filter\n all_filters = [*filter_clauses, exists_any_embedding]\n\n # Get limit and score threshold\n limit = (filter_obj or {}).get(\"limit\", self.number_of_results)\n score_threshold = (filter_obj or {}).get(\"score_threshold\", 0)\n\n # Build multi-model hybrid query\n body = {\n \"query\": {\n \"bool\": {\n \"should\": [\n {\n \"dis_max\": {\n \"tie_breaker\": 0.0, # Take only the best match, no blending\n \"boost\": 0.7, # 70% weight for semantic search\n \"queries\": knn_queries_with_candidates,\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, # 30% weight for keyword search\n }\n },\n ],\n \"minimum_should_match\": 1,\n \"filter\": all_filters,\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 \"embedding_models\": {\"terms\": {\"field\": \"embedding_model\", \"size\": 10}},\n },\n \"_source\": [\n \"filename\",\n \"mimetype\",\n \"page\",\n \"text\",\n \"source_url\",\n \"owner\",\n \"embedding_model\",\n \"allowed_users\",\n \"allowed_groups\",\n ],\n \"size\": limit,\n }\n\n if isinstance(score_threshold, (int, float)) and score_threshold > 0:\n body[\"min_score\"] = score_threshold\n\n logger.info(\n f\"Executing multi-model hybrid search with {len(knn_queries_with_candidates)} embedding models: \"\n f\"{list(query_embeddings.keys())}\"\n )\n self.log(f\"[EXEC] Executing search with {len(knn_queries_with_candidates)} KNN queries, limit={limit}\")\n self.log(f\"[EXEC] Embedding models used: {list(query_embeddings.keys())}\")\n self.log(f\"[EXEC] KNN fields being queried: {embedding_fields}\")\n\n try:\n resp = client.search(index=self.index_name, body=body, params={\"terminate_after\": 0})\n except RequestError as e:\n error_message = str(e)\n lowered = error_message.lower()\n if use_num_candidates and \"num_candidates\" in lowered:\n logger.warning(\n \"Retrying search without num_candidates parameter due to cluster capabilities\",\n error=error_message,\n )\n fallback_body = copy.deepcopy(body)\n try:\n fallback_body[\"query\"][\"bool\"][\"should\"][0][\"dis_max\"][\"queries\"] = knn_queries_without_candidates\n except (KeyError, IndexError, TypeError) as inner_err:\n raise e from inner_err\n resp = client.search(\n index=self.index_name,\n body=fallback_body,\n params={\"terminate_after\": 0},\n )\n elif \"knn_vector\" in lowered or (\"field\" in lowered and \"knn\" in lowered):\n fallback_vector = next(iter(query_embeddings.values()), None)\n if fallback_vector is None:\n raise\n fallback_field = legacy_vector_field or \"chunk_embedding\"\n logger.warning(\n \"KNN search failed for dynamic fields; falling back to legacy field '%s'.\",\n fallback_field,\n )\n fallback_body = copy.deepcopy(body)\n fallback_body[\"query\"][\"bool\"][\"filter\"] = filter_clauses\n knn_fallback = {\n \"knn\": {\n fallback_field: {\n \"vector\": fallback_vector,\n \"k\": 50,\n }\n }\n }\n if use_num_candidates:\n knn_fallback[\"knn\"][fallback_field][\"num_candidates\"] = num_candidates\n fallback_body[\"query\"][\"bool\"][\"should\"][0][\"dis_max\"][\"queries\"] = [knn_fallback]\n resp = client.search(\n index=self.index_name,\n body=fallback_body,\n params={\"terminate_after\": 0},\n )\n else:\n raise\n hits = resp.get(\"hits\", {}).get(\"hits\", [])\n\n logger.info(f\"Found {len(hits)} results\")\n self.log(f\"[RESULT] Search complete: {len(hits)} results found\")\n\n if len(hits) == 0:\n self.log(\n f\"[EMPTY] Debug info: \"\n f\"models_in_index={available_models}, \"\n f\"matched_models={matched_models}, \"\n f\"knn_fields={embedding_fields}, \"\n f\"filters={len(filter_clauses)} clauses\"\n )\n\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 multi-model search using the\n configured search_query and returns results in Langflow's Data format.\n\n Always builds the vector store (triggering ingestion if needed), then performs\n search only if a query is provided.\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 # Always build/cache the vector store to ensure ingestion happens\n logger.info(f\"Search query: {self.search_query}\")\n if self._cached_vector_store is None:\n self.build_vector_store()\n\n # Only perform search if query is provided\n search_query = (self.search_query or \"\").strip()\n if not search_query:\n self.log(\"No search query provided - ingestion completed, returning empty results\")\n return []\n\n # Perform search with the provided query\n raw = self.search(search_query)\n return [Data(text=hit[\"page_content\"], **hit[\"metadata\"]) for hit in raw]\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 return build_config\n\n except (KeyError, ValueError) as e:\n self.log(f\"update_build_config error: {e}\")\n\n return build_config\n"
|
|
},
|
|
"docs_metadata": {
|
|
"_input_type": "TableInput",
|
|
"advanced": false,
|
|
"display_name": "Document Metadata",
|
|
"dynamic": false,
|
|
"info": "Additional metadata key-value pairs to be added to all ingested documents. Useful for tagging documents with source information, categories, or other custom attributes.",
|
|
"input_types": [
|
|
"Data"
|
|
],
|
|
"is_list": true,
|
|
"list_add_label": "Add More",
|
|
"name": "docs_metadata",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"table_icon": "Table",
|
|
"table_schema": [
|
|
{
|
|
"description": "Key name",
|
|
"display_name": "Key",
|
|
"formatter": "text",
|
|
"name": "key",
|
|
"type": "str"
|
|
},
|
|
{
|
|
"description": "Value of the metadata",
|
|
"display_name": "Value",
|
|
"formatter": "text",
|
|
"name": "value",
|
|
"type": "str"
|
|
}
|
|
],
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 512
|
|
},
|
|
"embedding": {
|
|
"_input_type": "HandleInput",
|
|
"advanced": false,
|
|
"display_name": "Embedding",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"input_types": [
|
|
"Embeddings"
|
|
],
|
|
"list": true,
|
|
"list_add_label": "Add More",
|
|
"name": "embedding",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "other",
|
|
"value": ""
|
|
},
|
|
"embedding_model_name": {
|
|
"_input_type": "StrInput",
|
|
"advanced": false,
|
|
"display_name": "Embedding Model Name",
|
|
"dynamic": false,
|
|
"info": "Name of the embedding model to use for ingestion. This selects which embedding from the list will be used to embed documents. Matches on deployment, model, model_id, or model_name. For duplicate deployments, use combined format: 'deployment:model' (e.g., 'text-embedding-ada-002:text-embedding-3-large'). Leave empty to use the first embedding. Error message will show all available identifiers.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": true,
|
|
"name": "embedding_model_name",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "SELECTED_EMBEDDING_MODEL"
|
|
},
|
|
"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'.",
|
|
"name": "engine",
|
|
"options": [
|
|
"jvector",
|
|
"nmslib",
|
|
"faiss",
|
|
"lucene"
|
|
],
|
|
"options_metadata": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "jvector"
|
|
},
|
|
"filter_expression": {
|
|
"_input_type": "MultilineInput",
|
|
"advanced": false,
|
|
"ai_enabled": 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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "other",
|
|
"value": ""
|
|
},
|
|
"is_refresh": false,
|
|
"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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"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",
|
|
"override_skip": false,
|
|
"password": true,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"track_in_telemetry": 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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 16
|
|
},
|
|
"num_candidates": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Candidate Pool Size",
|
|
"dynamic": false,
|
|
"info": "Number of approximate neighbors to consider for each KNN query. Some OpenSearch deployments do not support this parameter; set to 0 to disable.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "num_candidates",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 1000
|
|
},
|
|
"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",
|
|
"name": "number_of_results",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 10
|
|
},
|
|
"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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"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",
|
|
"override_skip": false,
|
|
"password": true,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "epC8FOOeq3$3t*VB"
|
|
},
|
|
"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",
|
|
"override_skip": false,
|
|
"placeholder": "Enter a query...",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": true,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": 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": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": 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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": 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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "admin"
|
|
},
|
|
"vector_field": {
|
|
"_input_type": "StrInput",
|
|
"advanced": true,
|
|
"display_name": "Legacy Vector Field Name",
|
|
"dynamic": false,
|
|
"info": "Legacy field name for backward compatibility. New documents use dynamic fields (chunk_embedding_{model_name}) based on the embedding_model_name.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "vector_field",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": false
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"selected_output": "dataframe",
|
|
"showNode": true,
|
|
"type": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding"
|
|
},
|
|
"dragging": false,
|
|
"id": "OpenSearchVectorStoreComponentMultimodalMultiEmbedding-0ByE3",
|
|
"measured": {
|
|
"height": 904,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": 387.88180968996585,
|
|
"y": 879.9328678310967
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"description": "Generate embeddings using a specified provider.",
|
|
"display_name": "Embedding Model",
|
|
"id": "EmbeddingModel-EzcW6",
|
|
"node": {
|
|
"base_classes": [
|
|
"Embeddings"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {},
|
|
"description": "Generate embeddings using a specified provider.",
|
|
"display_name": "Embedding Model",
|
|
"documentation": "https://docs.langflow.org/components-embedding-models",
|
|
"edited": true,
|
|
"field_order": [
|
|
"provider",
|
|
"api_base",
|
|
"ollama_base_url",
|
|
"base_url_ibm_watsonx",
|
|
"model",
|
|
"api_key",
|
|
"project_id",
|
|
"dimensions",
|
|
"chunk_size",
|
|
"request_timeout",
|
|
"max_retries",
|
|
"show_progress_bar",
|
|
"model_kwargs",
|
|
"truncate_input_tokens",
|
|
"input_text",
|
|
"fail_safe_mode"
|
|
],
|
|
"frozen": false,
|
|
"icon": "binary",
|
|
"last_updated": "2025-12-02T21:24:52.480Z",
|
|
"legacy": false,
|
|
"lf_version": "1.7.0.dev21",
|
|
"metadata": {
|
|
"code_hash": "0e2d6fe67a26",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "requests",
|
|
"version": "2.32.5"
|
|
},
|
|
{
|
|
"name": "ibm_watsonx_ai",
|
|
"version": "1.4.2"
|
|
},
|
|
{
|
|
"name": "langchain_openai",
|
|
"version": "0.3.23"
|
|
},
|
|
{
|
|
"name": "lfx",
|
|
"version": "0.2.0.dev21"
|
|
},
|
|
{
|
|
"name": "langchain_ollama",
|
|
"version": "0.3.10"
|
|
},
|
|
{
|
|
"name": "langchain_community",
|
|
"version": "0.3.21"
|
|
},
|
|
{
|
|
"name": "langchain_ibm",
|
|
"version": "0.3.19"
|
|
}
|
|
],
|
|
"total_dependencies": 7
|
|
},
|
|
"module": "custom_components.embedding_model"
|
|
},
|
|
"minimized": false,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Embedding Model",
|
|
"group_outputs": false,
|
|
"hidden": null,
|
|
"loop_types": null,
|
|
"method": "build_embeddings",
|
|
"name": "embeddings",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "Embeddings",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"Embeddings"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"template": {
|
|
"_frontend_node_flow_id": {
|
|
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
|
|
},
|
|
"_frontend_node_folder_id": {
|
|
"value": "69a7745e-dfb8-40a7-b5cb-5da3af0b10b6"
|
|
},
|
|
"_type": "Component",
|
|
"api_base": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "API Base URL",
|
|
"dynamic": false,
|
|
"info": "Base URL for the API. Leave empty for default.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "api_base",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"api_key": {
|
|
"_input_type": "SecretStrInput",
|
|
"advanced": false,
|
|
"display_name": "API Key (Optional)",
|
|
"dynamic": false,
|
|
"info": "Model Provider API key",
|
|
"input_types": [],
|
|
"load_from_db": true,
|
|
"name": "api_key",
|
|
"override_skip": false,
|
|
"password": true,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "OPENAI_API_KEY"
|
|
},
|
|
"base_url_ibm_watsonx": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "watsonx API Endpoint",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "The base URL of the API (IBM watsonx.ai only)",
|
|
"name": "base_url_ibm_watsonx",
|
|
"options": [
|
|
"https://us-south.ml.cloud.ibm.com",
|
|
"https://eu-de.ml.cloud.ibm.com",
|
|
"https://eu-gb.ml.cloud.ibm.com",
|
|
"https://au-syd.ml.cloud.ibm.com",
|
|
"https://jp-tok.ml.cloud.ibm.com",
|
|
"https://ca-tor.ml.cloud.ibm.com"
|
|
],
|
|
"options_metadata": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "https://us-south.ml.cloud.ibm.com"
|
|
},
|
|
"chunk_size": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Chunk Size",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "chunk_size",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 1000
|
|
},
|
|
"code": {
|
|
"advanced": true,
|
|
"dynamic": true,
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "code",
|
|
"password": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "code",
|
|
"value": "from typing import Any\n\nimport requests\nfrom ibm_watsonx_ai.metanames import EmbedTextParamsMetaNames\nfrom langchain_openai import OpenAIEmbeddings\n\nfrom lfx.base.embeddings.embeddings_class import EmbeddingsWithModels\nfrom lfx.base.embeddings.model import LCEmbeddingsModel\nfrom lfx.base.models.model_utils import get_ollama_models, is_valid_ollama_url\nfrom lfx.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom lfx.base.models.watsonx_constants import (\n IBM_WATSONX_URLS,\n WATSONX_EMBEDDING_MODEL_NAMES,\n)\nfrom lfx.field_typing import Embeddings\nfrom lfx.io import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n MessageTextInput,\n SecretStrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.utils.util import transform_localhost_url\n\n# Ollama API constants\nHTTP_STATUS_OK = 200\nJSON_MODELS_KEY = \"models\"\nJSON_NAME_KEY = \"name\"\nJSON_CAPABILITIES_KEY = \"capabilities\"\nDESIRED_CAPABILITY = \"embedding\"\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass EmbeddingModelComponent(LCEmbeddingsModel):\n display_name = \"Embedding Model\"\n description = \"Generate embeddings using a specified provider.\"\n documentation: str = \"https://docs.langflow.org/components-embedding-models\"\n icon = \"binary\"\n name = \"EmbeddingModel\"\n category = \"models\"\n\n inputs = [\n DropdownInput(\n name=\"provider\",\n display_name=\"Model Provider\",\n options=[\"OpenAI\", \"Ollama\", \"IBM watsonx.ai\"],\n value=\"OpenAI\",\n info=\"Select the embedding model provider\",\n real_time_refresh=True,\n options_metadata=[{\"icon\": \"OpenAI\"}, {\"icon\": \"Ollama\"}, {\"icon\": \"WatsonxAI\"}],\n ),\n MessageTextInput(\n name=\"api_base\",\n display_name=\"API Base URL\",\n info=\"Base URL for the API. Leave empty for default.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"ollama_base_url\",\n display_name=\"Ollama API URL\",\n info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n value=DEFAULT_OLLAMA_URL,\n show=False,\n real_time_refresh=True,\n load_from_db=True,\n ),\n DropdownInput(\n name=\"base_url_ibm_watsonx\",\n display_name=\"watsonx API Endpoint\",\n info=\"The base URL of the API (IBM watsonx.ai only)\",\n options=IBM_WATSONX_URLS,\n value=IBM_WATSONX_URLS[0],\n show=False,\n real_time_refresh=True,\n ),\n DropdownInput(\n name=\"model\",\n display_name=\"Model Name\",\n options=OPENAI_EMBEDDING_MODEL_NAMES,\n value=OPENAI_EMBEDDING_MODEL_NAMES[0],\n info=\"Select the embedding model to use\",\n real_time_refresh=True,\n refresh_button=True,\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"Model Provider API key\",\n required=True,\n show=True,\n real_time_refresh=True,\n ),\n # Watson-specific inputs\n MessageTextInput(\n name=\"project_id\",\n display_name=\"Project ID\",\n info=\"IBM watsonx.ai Project ID (required for IBM watsonx.ai)\",\n show=False,\n ),\n IntInput(\n name=\"dimensions\",\n display_name=\"Dimensions\",\n info=\"The number of dimensions the resulting output embeddings should have. \"\n \"Only supported by certain models.\",\n advanced=True,\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", advanced=True, value=3),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n DictInput(\n name=\"model_kwargs\",\n display_name=\"Model Kwargs\",\n advanced=True,\n info=\"Additional keyword arguments to pass to the model.\",\n ),\n IntInput(\n name=\"truncate_input_tokens\",\n display_name=\"Truncate Input Tokens\",\n advanced=True,\n value=200,\n show=False,\n ),\n BoolInput(\n name=\"input_text\",\n display_name=\"Include the original text in the output\",\n value=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"fail_safe_mode\",\n display_name=\"Fail-Safe Mode\",\n value=False,\n advanced=True,\n info=\"When enabled, errors will be logged instead of raising exceptions. \"\n \"The component will return None on error.\",\n real_time_refresh=True,\n ),\n ]\n\n @staticmethod\n def fetch_ibm_models(base_url: str) -> list[str]:\n \"\"\"Fetch available models from the watsonx.ai API.\"\"\"\n try:\n endpoint = f\"{base_url}/ml/v1/foundation_model_specs\"\n params = {\n \"version\": \"2024-09-16\",\n \"filters\": \"function_embedding,!lifecycle_withdrawn:and\",\n }\n response = requests.get(endpoint, params=params, timeout=10)\n response.raise_for_status()\n data = response.json()\n models = [model[\"model_id\"] for model in data.get(\"resources\", [])]\n return sorted(models)\n except Exception: # noqa: BLE001\n logger.exception(\"Error fetching models\")\n return WATSONX_EMBEDDING_MODEL_NAMES\n async def fetch_ollama_models(self) -> list[str]:\n try:\n return await get_ollama_models(\n base_url_value=self.ollama_base_url,\n desired_capability=DESIRED_CAPABILITY,\n json_models_key=JSON_MODELS_KEY,\n json_name_key=JSON_NAME_KEY,\n json_capabilities_key=JSON_CAPABILITIES_KEY,\n )\n except Exception: # noqa: BLE001\n\n logger.exception(\"Error fetching models\")\n return []\n async def build_embeddings(self) -> Embeddings:\n provider = self.provider\n model = self.model\n api_key = self.api_key\n api_base = self.api_base\n base_url_ibm_watsonx = self.base_url_ibm_watsonx\n ollama_base_url = self.ollama_base_url\n dimensions = self.dimensions\n chunk_size = self.chunk_size\n request_timeout = self.request_timeout\n max_retries = self.max_retries\n show_progress_bar = self.show_progress_bar\n model_kwargs = self.model_kwargs or {}\n\n if provider == \"OpenAI\":\n if not api_key:\n msg = \"OpenAI API key is required when using OpenAI provider\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n try:\n # Create the primary embedding instance\n embeddings_instance = OpenAIEmbeddings(\n model=model,\n dimensions=dimensions or None,\n base_url=api_base or None,\n api_key=api_key,\n chunk_size=chunk_size,\n max_retries=max_retries,\n timeout=request_timeout or None,\n show_progress_bar=show_progress_bar,\n model_kwargs=model_kwargs,\n )\n\n # Create dedicated instances for each available model\n available_models_dict = {}\n for model_name in OPENAI_EMBEDDING_MODEL_NAMES:\n available_models_dict[model_name] = OpenAIEmbeddings(\n model=model_name,\n dimensions=dimensions or None, # Use same dimensions config for all\n base_url=api_base or None,\n api_key=api_key,\n chunk_size=chunk_size,\n max_retries=max_retries,\n timeout=request_timeout or None,\n show_progress_bar=show_progress_bar,\n model_kwargs=model_kwargs,\n )\n\n return EmbeddingsWithModels(\n embeddings=embeddings_instance,\n available_models=available_models_dict,\n )\n except Exception as e:\n msg = f\"Failed to initialize OpenAI embeddings: {e}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise\n\n if provider == \"Ollama\":\n try:\n from langchain_ollama import OllamaEmbeddings\n except ImportError:\n try:\n from langchain_community.embeddings import OllamaEmbeddings\n except ImportError:\n msg = \"Please install langchain-ollama: pip install langchain-ollama\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ImportError(msg) from None\n\n try:\n transformed_base_url = transform_localhost_url(ollama_base_url)\n\n # Check if URL contains /v1 suffix (OpenAI-compatible mode)\n if transformed_base_url and transformed_base_url.rstrip(\"/\").endswith(\"/v1\"):\n # Strip /v1 suffix and log warning\n transformed_base_url = transformed_base_url.rstrip(\"/\").removesuffix(\"/v1\")\n logger.warning(\n \"Detected '/v1' suffix in base URL. The Ollama component uses the native Ollama API, \"\n \"not the OpenAI-compatible API. The '/v1' suffix has been automatically removed. \"\n \"If you want to use the OpenAI-compatible API, please use the OpenAI component instead. \"\n \"Learn more at https://docs.ollama.com/openai#openai-compatibility\"\n )\n\n final_base_url = transformed_base_url or \"http://localhost:11434\"\n\n # Create the primary embedding instance\n embeddings_instance = OllamaEmbeddings(\n model=model,\n base_url=final_base_url,\n **model_kwargs,\n )\n\n # Fetch available Ollama models\n available_model_names = await self.fetch_ollama_models()\n\n # Create dedicated instances for each available model\n available_models_dict = {}\n for model_name in available_model_names:\n available_models_dict[model_name] = OllamaEmbeddings(\n model=model_name,\n base_url=final_base_url,\n **model_kwargs,\n )\n\n return EmbeddingsWithModels(\n embeddings=embeddings_instance,\n available_models=available_models_dict,\n )\n except Exception as e:\n msg = f\"Failed to initialize Ollama embeddings: {e}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise\n\n if provider == \"IBM watsonx.ai\":\n try:\n from langchain_ibm import WatsonxEmbeddings\n except ImportError:\n msg = \"Please install langchain-ibm: pip install langchain-ibm\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ImportError(msg) from None\n\n if not api_key:\n msg = \"IBM watsonx.ai API key is required when using IBM watsonx.ai provider\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n project_id = self.project_id\n\n if not project_id:\n msg = \"Project ID is required for IBM watsonx.ai provider\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n try:\n from ibm_watsonx_ai import APIClient, Credentials\n\n final_url = base_url_ibm_watsonx or \"https://us-south.ml.cloud.ibm.com\"\n\n credentials = Credentials(\n api_key=self.api_key,\n url=final_url,\n )\n\n api_client = APIClient(credentials)\n\n params = {\n EmbedTextParamsMetaNames.TRUNCATE_INPUT_TOKENS: self.truncate_input_tokens,\n EmbedTextParamsMetaNames.RETURN_OPTIONS: {\"input_text\": self.input_text},\n }\n\n # Create the primary embedding instance\n embeddings_instance = WatsonxEmbeddings(\n model_id=model,\n params=params,\n watsonx_client=api_client,\n project_id=project_id,\n )\n\n # Fetch available IBM watsonx.ai models\n available_model_names = self.fetch_ibm_models(final_url)\n\n # Create dedicated instances for each available model\n available_models_dict = {}\n for model_name in available_model_names:\n available_models_dict[model_name] = WatsonxEmbeddings(\n model_id=model_name,\n params=params,\n watsonx_client=api_client,\n project_id=project_id,\n )\n\n return EmbeddingsWithModels(\n embeddings=embeddings_instance,\n available_models=available_models_dict,\n )\n except Exception as e:\n msg = f\"Failed to authenticate with IBM watsonx.ai: {e}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise\n\n msg = f\"Unknown provider: {provider}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n async def update_build_config(\n self, build_config: dotdict, field_value: Any, field_name: str | None = None\n ) -> dotdict:\n # Handle fail_safe_mode changes first - set all required fields to False if enabled\n if field_name == \"fail_safe_mode\":\n if field_value: # If fail_safe_mode is enabled\n build_config[\"api_key\"][\"required\"] = False\n elif hasattr(self, \"provider\"):\n # If fail_safe_mode is disabled, restore required flags based on provider\n if self.provider in [\"OpenAI\", \"IBM watsonx.ai\"]:\n build_config[\"api_key\"][\"required\"] = True\n else: # Ollama\n build_config[\"api_key\"][\"required\"] = False\n\n if field_name == \"provider\":\n if field_value == \"OpenAI\":\n build_config[\"model\"][\"options\"] = OPENAI_EMBEDDING_MODEL_NAMES\n build_config[\"model\"][\"value\"] = OPENAI_EMBEDDING_MODEL_NAMES[0]\n build_config[\"api_key\"][\"display_name\"] = \"OpenAI API Key\"\n # Only set required=True if fail_safe_mode is not enabled\n build_config[\"api_key\"][\"required\"] = not (hasattr(self, \"fail_safe_mode\") and self.fail_safe_mode)\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"api_base\"][\"display_name\"] = \"OpenAI API Base URL\"\n build_config[\"api_base\"][\"advanced\"] = True\n build_config[\"api_base\"][\"show\"] = True\n build_config[\"ollama_base_url\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n build_config[\"truncate_input_tokens\"][\"show\"] = False\n build_config[\"input_text\"][\"show\"] = False\n elif field_value == \"Ollama\":\n build_config[\"ollama_base_url\"][\"show\"] = True\n\n if await is_valid_ollama_url(url=self.ollama_base_url):\n try:\n models = await self.fetch_ollama_models()\n build_config[\"model\"][\"options\"] = models\n build_config[\"model\"][\"value\"] = models[0] if models else \"\"\n except ValueError:\n build_config[\"model\"][\"options\"] = []\n build_config[\"model\"][\"value\"] = \"\"\n else:\n build_config[\"model\"][\"options\"] = []\n build_config[\"model\"][\"value\"] = \"\"\n build_config[\"truncate_input_tokens\"][\"show\"] = False\n build_config[\"input_text\"][\"show\"] = False\n build_config[\"api_key\"][\"display_name\"] = \"API Key (Optional)\"\n build_config[\"api_key\"][\"required\"] = False\n build_config[\"api_key\"][\"show\"] = False\n build_config[\"api_base\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n\n elif field_value == \"IBM watsonx.ai\":\n build_config[\"model\"][\"options\"] = self.fetch_ibm_models(base_url=self.base_url_ibm_watsonx)\n build_config[\"model\"][\"value\"] = self.fetch_ibm_models(base_url=self.base_url_ibm_watsonx)[0]\n build_config[\"api_key\"][\"display_name\"] = \"IBM watsonx.ai API Key\"\n # Only set required=True if fail_safe_mode is not enabled\n build_config[\"api_key\"][\"required\"] = not (hasattr(self, \"fail_safe_mode\") and self.fail_safe_mode)\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"api_base\"][\"show\"] = False\n build_config[\"ollama_base_url\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = True\n build_config[\"project_id\"][\"show\"] = True\n build_config[\"truncate_input_tokens\"][\"show\"] = True\n build_config[\"input_text\"][\"show\"] = True\n elif field_name == \"base_url_ibm_watsonx\":\n build_config[\"model\"][\"options\"] = self.fetch_ibm_models(base_url=field_value)\n build_config[\"model\"][\"value\"] = self.fetch_ibm_models(base_url=field_value)[0]\n elif field_name == \"ollama_base_url\":\n # # Refresh Ollama models when base URL changes\n # if hasattr(self, \"provider\") and self.provider == \"Ollama\":\n # Use field_value if provided, otherwise fall back to instance attribute\n ollama_url = self.ollama_base_url\n if await is_valid_ollama_url(url=ollama_url):\n try:\n models = await self.fetch_ollama_models()\n build_config[\"model\"][\"options\"] = models\n build_config[\"model\"][\"value\"] = models[0] if models else \"\"\n except ValueError:\n await logger.awarning(\"Failed to fetch Ollama embedding models.\")\n build_config[\"model\"][\"options\"] = []\n build_config[\"model\"][\"value\"] = \"\"\n\n elif field_name == \"model\" and self.provider == \"Ollama\":\n ollama_url = self.ollama_base_url\n if await is_valid_ollama_url(url=ollama_url):\n try:\n models = await self.fetch_ollama_models()\n build_config[\"model\"][\"options\"] = models\n except ValueError:\n await logger.awarning(\"Failed to refresh Ollama embedding models.\")\n build_config[\"model\"][\"options\"] = []\n\n return build_config\n"
|
|
},
|
|
"dimensions": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Dimensions",
|
|
"dynamic": false,
|
|
"info": "The number of dimensions the resulting output embeddings should have. Only supported by certain models.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "dimensions",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": ""
|
|
},
|
|
"fail_safe_mode": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Fail-Safe Mode",
|
|
"dynamic": false,
|
|
"info": "When enabled, errors will be logged instead of raising exceptions. The component will return None on error.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "fail_safe_mode",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": true
|
|
},
|
|
"input_text": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Include the original text in the output",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "input_text",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": true
|
|
},
|
|
"is_refresh": false,
|
|
"max_retries": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Max Retries",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "max_retries",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 3
|
|
},
|
|
"model": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Model Name",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Select the embedding model to use",
|
|
"load_from_db": false,
|
|
"name": "model",
|
|
"options": [],
|
|
"options_metadata": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"refresh_button": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"model_kwargs": {
|
|
"_input_type": "DictInput",
|
|
"advanced": true,
|
|
"display_name": "Model Kwargs",
|
|
"dynamic": false,
|
|
"info": "Additional keyword arguments to pass to the model.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "model_kwargs",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"track_in_telemetry": false,
|
|
"type": "dict",
|
|
"value": {}
|
|
},
|
|
"ollama_base_url": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": false,
|
|
"display_name": "Ollama API URL",
|
|
"dynamic": false,
|
|
"info": "Endpoint of the Ollama API (Ollama only). Defaults to http://localhost:11434",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": true,
|
|
"name": "ollama_base_url",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "OLLAMA_BASE_URL"
|
|
},
|
|
"project_id": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": false,
|
|
"display_name": "Project ID",
|
|
"dynamic": false,
|
|
"info": "IBM watsonx.ai Project ID (required for IBM watsonx.ai)",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "project_id",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"provider": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Model Provider",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Select the embedding model provider",
|
|
"load_from_db": false,
|
|
"name": "provider",
|
|
"options": [
|
|
"OpenAI",
|
|
"Ollama",
|
|
"IBM watsonx.ai"
|
|
],
|
|
"options_metadata": [
|
|
{
|
|
"icon": "OpenAI"
|
|
},
|
|
{
|
|
"icon": "Ollama"
|
|
},
|
|
{
|
|
"icon": "WatsonxAI"
|
|
}
|
|
],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"selected_metadata": {
|
|
"icon": "Ollama"
|
|
},
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "Ollama"
|
|
},
|
|
"request_timeout": {
|
|
"_input_type": "FloatInput",
|
|
"advanced": true,
|
|
"display_name": "Request Timeout",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "request_timeout",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": 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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": false
|
|
},
|
|
"truncate_input_tokens": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Truncate Input Tokens",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "truncate_input_tokens",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 200
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"showNode": true,
|
|
"type": "EmbeddingModel"
|
|
},
|
|
"dragging": false,
|
|
"id": "EmbeddingModel-EzcW6",
|
|
"measured": {
|
|
"height": 369,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": -742.3027218520097,
|
|
"y": 1224.367844475079
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
},
|
|
{
|
|
"data": {
|
|
"description": "Generate embeddings using a specified provider.",
|
|
"display_name": "Embedding Model",
|
|
"id": "EmbeddingModel-cONxU",
|
|
"node": {
|
|
"base_classes": [
|
|
"Embeddings"
|
|
],
|
|
"beta": false,
|
|
"conditional_paths": [],
|
|
"custom_fields": {},
|
|
"description": "Generate embeddings using a specified provider.",
|
|
"display_name": "Embedding Model",
|
|
"documentation": "https://docs.langflow.org/components-embedding-models",
|
|
"edited": true,
|
|
"field_order": [
|
|
"provider",
|
|
"api_base",
|
|
"ollama_base_url",
|
|
"base_url_ibm_watsonx",
|
|
"model",
|
|
"api_key",
|
|
"project_id",
|
|
"dimensions",
|
|
"chunk_size",
|
|
"request_timeout",
|
|
"max_retries",
|
|
"show_progress_bar",
|
|
"model_kwargs",
|
|
"truncate_input_tokens",
|
|
"input_text",
|
|
"fail_safe_mode"
|
|
],
|
|
"frozen": false,
|
|
"icon": "binary",
|
|
"last_updated": "2025-12-02T21:24:52.481Z",
|
|
"legacy": false,
|
|
"lf_version": "1.7.0.dev21",
|
|
"metadata": {
|
|
"code_hash": "0e2d6fe67a26",
|
|
"dependencies": {
|
|
"dependencies": [
|
|
{
|
|
"name": "requests",
|
|
"version": "2.32.5"
|
|
},
|
|
{
|
|
"name": "ibm_watsonx_ai",
|
|
"version": "1.4.2"
|
|
},
|
|
{
|
|
"name": "langchain_openai",
|
|
"version": "0.3.23"
|
|
},
|
|
{
|
|
"name": "lfx",
|
|
"version": "0.2.0.dev21"
|
|
},
|
|
{
|
|
"name": "langchain_ollama",
|
|
"version": "0.3.10"
|
|
},
|
|
{
|
|
"name": "langchain_community",
|
|
"version": "0.3.21"
|
|
},
|
|
{
|
|
"name": "langchain_ibm",
|
|
"version": "0.3.19"
|
|
}
|
|
],
|
|
"total_dependencies": 7
|
|
},
|
|
"module": "custom_components.embedding_model"
|
|
},
|
|
"minimized": false,
|
|
"output_types": [],
|
|
"outputs": [
|
|
{
|
|
"allows_loop": false,
|
|
"cache": true,
|
|
"display_name": "Embedding Model",
|
|
"group_outputs": false,
|
|
"hidden": null,
|
|
"loop_types": null,
|
|
"method": "build_embeddings",
|
|
"name": "embeddings",
|
|
"options": null,
|
|
"required_inputs": null,
|
|
"selected": "Embeddings",
|
|
"tool_mode": true,
|
|
"types": [
|
|
"Embeddings"
|
|
],
|
|
"value": "__UNDEFINED__"
|
|
}
|
|
],
|
|
"pinned": false,
|
|
"template": {
|
|
"_frontend_node_flow_id": {
|
|
"value": "ebc01d31-1976-46ce-a385-b0240327226c"
|
|
},
|
|
"_frontend_node_folder_id": {
|
|
"value": "69a7745e-dfb8-40a7-b5cb-5da3af0b10b6"
|
|
},
|
|
"_type": "Component",
|
|
"api_base": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": true,
|
|
"display_name": "API Base URL",
|
|
"dynamic": false,
|
|
"info": "Base URL for the API. Leave empty for default.",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "api_base",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": ""
|
|
},
|
|
"api_key": {
|
|
"_input_type": "SecretStrInput",
|
|
"advanced": false,
|
|
"display_name": "IBM watsonx.ai API Key",
|
|
"dynamic": false,
|
|
"info": "Model Provider API key",
|
|
"input_types": [],
|
|
"load_from_db": true,
|
|
"name": "api_key",
|
|
"override_skip": false,
|
|
"password": true,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "WATSONX_API_KEY"
|
|
},
|
|
"base_url_ibm_watsonx": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "watsonx API Endpoint",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "The base URL of the API (IBM watsonx.ai only)",
|
|
"name": "base_url_ibm_watsonx",
|
|
"options": [
|
|
"https://us-south.ml.cloud.ibm.com",
|
|
"https://eu-de.ml.cloud.ibm.com",
|
|
"https://eu-gb.ml.cloud.ibm.com",
|
|
"https://au-syd.ml.cloud.ibm.com",
|
|
"https://jp-tok.ml.cloud.ibm.com",
|
|
"https://ca-tor.ml.cloud.ibm.com"
|
|
],
|
|
"options_metadata": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "https://us-south.ml.cloud.ibm.com"
|
|
},
|
|
"chunk_size": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Chunk Size",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "chunk_size",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 1000
|
|
},
|
|
"code": {
|
|
"advanced": true,
|
|
"dynamic": true,
|
|
"fileTypes": [],
|
|
"file_path": "",
|
|
"info": "",
|
|
"list": false,
|
|
"load_from_db": false,
|
|
"multiline": true,
|
|
"name": "code",
|
|
"password": false,
|
|
"placeholder": "",
|
|
"required": true,
|
|
"show": true,
|
|
"title_case": false,
|
|
"type": "code",
|
|
"value": "from typing import Any\n\nimport requests\nfrom ibm_watsonx_ai.metanames import EmbedTextParamsMetaNames\nfrom langchain_openai import OpenAIEmbeddings\n\nfrom lfx.base.embeddings.embeddings_class import EmbeddingsWithModels\nfrom lfx.base.embeddings.model import LCEmbeddingsModel\nfrom lfx.base.models.model_utils import get_ollama_models, is_valid_ollama_url\nfrom lfx.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom lfx.base.models.watsonx_constants import (\n IBM_WATSONX_URLS,\n WATSONX_EMBEDDING_MODEL_NAMES,\n)\nfrom lfx.field_typing import Embeddings\nfrom lfx.io import (\n BoolInput,\n DictInput,\n DropdownInput,\n FloatInput,\n IntInput,\n MessageTextInput,\n SecretStrInput,\n)\nfrom lfx.log.logger import logger\nfrom lfx.schema.dotdict import dotdict\nfrom lfx.utils.util import transform_localhost_url\n\n# Ollama API constants\nHTTP_STATUS_OK = 200\nJSON_MODELS_KEY = \"models\"\nJSON_NAME_KEY = \"name\"\nJSON_CAPABILITIES_KEY = \"capabilities\"\nDESIRED_CAPABILITY = \"embedding\"\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass EmbeddingModelComponent(LCEmbeddingsModel):\n display_name = \"Embedding Model\"\n description = \"Generate embeddings using a specified provider.\"\n documentation: str = \"https://docs.langflow.org/components-embedding-models\"\n icon = \"binary\"\n name = \"EmbeddingModel\"\n category = \"models\"\n\n inputs = [\n DropdownInput(\n name=\"provider\",\n display_name=\"Model Provider\",\n options=[\"OpenAI\", \"Ollama\", \"IBM watsonx.ai\"],\n value=\"OpenAI\",\n info=\"Select the embedding model provider\",\n real_time_refresh=True,\n options_metadata=[{\"icon\": \"OpenAI\"}, {\"icon\": \"Ollama\"}, {\"icon\": \"WatsonxAI\"}],\n ),\n MessageTextInput(\n name=\"api_base\",\n display_name=\"API Base URL\",\n info=\"Base URL for the API. Leave empty for default.\",\n advanced=True,\n ),\n MessageTextInput(\n name=\"ollama_base_url\",\n display_name=\"Ollama API URL\",\n info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n value=DEFAULT_OLLAMA_URL,\n show=False,\n real_time_refresh=True,\n load_from_db=True,\n ),\n DropdownInput(\n name=\"base_url_ibm_watsonx\",\n display_name=\"watsonx API Endpoint\",\n info=\"The base URL of the API (IBM watsonx.ai only)\",\n options=IBM_WATSONX_URLS,\n value=IBM_WATSONX_URLS[0],\n show=False,\n real_time_refresh=True,\n ),\n DropdownInput(\n name=\"model\",\n display_name=\"Model Name\",\n options=OPENAI_EMBEDDING_MODEL_NAMES,\n value=OPENAI_EMBEDDING_MODEL_NAMES[0],\n info=\"Select the embedding model to use\",\n real_time_refresh=True,\n refresh_button=True,\n ),\n SecretStrInput(\n name=\"api_key\",\n display_name=\"OpenAI API Key\",\n info=\"Model Provider API key\",\n required=True,\n show=True,\n real_time_refresh=True,\n ),\n # Watson-specific inputs\n MessageTextInput(\n name=\"project_id\",\n display_name=\"Project ID\",\n info=\"IBM watsonx.ai Project ID (required for IBM watsonx.ai)\",\n show=False,\n ),\n IntInput(\n name=\"dimensions\",\n display_name=\"Dimensions\",\n info=\"The number of dimensions the resulting output embeddings should have. \"\n \"Only supported by certain models.\",\n advanced=True,\n ),\n IntInput(name=\"chunk_size\", display_name=\"Chunk Size\", advanced=True, value=1000),\n FloatInput(name=\"request_timeout\", display_name=\"Request Timeout\", advanced=True),\n IntInput(name=\"max_retries\", display_name=\"Max Retries\", advanced=True, value=3),\n BoolInput(name=\"show_progress_bar\", display_name=\"Show Progress Bar\", advanced=True),\n DictInput(\n name=\"model_kwargs\",\n display_name=\"Model Kwargs\",\n advanced=True,\n info=\"Additional keyword arguments to pass to the model.\",\n ),\n IntInput(\n name=\"truncate_input_tokens\",\n display_name=\"Truncate Input Tokens\",\n advanced=True,\n value=200,\n show=False,\n ),\n BoolInput(\n name=\"input_text\",\n display_name=\"Include the original text in the output\",\n value=True,\n advanced=True,\n show=False,\n ),\n BoolInput(\n name=\"fail_safe_mode\",\n display_name=\"Fail-Safe Mode\",\n value=False,\n advanced=True,\n info=\"When enabled, errors will be logged instead of raising exceptions. \"\n \"The component will return None on error.\",\n real_time_refresh=True,\n ),\n ]\n\n @staticmethod\n def fetch_ibm_models(base_url: str) -> list[str]:\n \"\"\"Fetch available models from the watsonx.ai API.\"\"\"\n try:\n endpoint = f\"{base_url}/ml/v1/foundation_model_specs\"\n params = {\n \"version\": \"2024-09-16\",\n \"filters\": \"function_embedding,!lifecycle_withdrawn:and\",\n }\n response = requests.get(endpoint, params=params, timeout=10)\n response.raise_for_status()\n data = response.json()\n models = [model[\"model_id\"] for model in data.get(\"resources\", [])]\n return sorted(models)\n except Exception: # noqa: BLE001\n logger.exception(\"Error fetching models\")\n return WATSONX_EMBEDDING_MODEL_NAMES\n async def fetch_ollama_models(self) -> list[str]:\n try:\n return await get_ollama_models(\n base_url_value=self.ollama_base_url,\n desired_capability=DESIRED_CAPABILITY,\n json_models_key=JSON_MODELS_KEY,\n json_name_key=JSON_NAME_KEY,\n json_capabilities_key=JSON_CAPABILITIES_KEY,\n )\n except Exception: # noqa: BLE001\n\n logger.exception(\"Error fetching models\")\n return []\n async def build_embeddings(self) -> Embeddings:\n provider = self.provider\n model = self.model\n api_key = self.api_key\n api_base = self.api_base\n base_url_ibm_watsonx = self.base_url_ibm_watsonx\n ollama_base_url = self.ollama_base_url\n dimensions = self.dimensions\n chunk_size = self.chunk_size\n request_timeout = self.request_timeout\n max_retries = self.max_retries\n show_progress_bar = self.show_progress_bar\n model_kwargs = self.model_kwargs or {}\n\n if provider == \"OpenAI\":\n if not api_key:\n msg = \"OpenAI API key is required when using OpenAI provider\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n try:\n # Create the primary embedding instance\n embeddings_instance = OpenAIEmbeddings(\n model=model,\n dimensions=dimensions or None,\n base_url=api_base or None,\n api_key=api_key,\n chunk_size=chunk_size,\n max_retries=max_retries,\n timeout=request_timeout or None,\n show_progress_bar=show_progress_bar,\n model_kwargs=model_kwargs,\n )\n\n # Create dedicated instances for each available model\n available_models_dict = {}\n for model_name in OPENAI_EMBEDDING_MODEL_NAMES:\n available_models_dict[model_name] = OpenAIEmbeddings(\n model=model_name,\n dimensions=dimensions or None, # Use same dimensions config for all\n base_url=api_base or None,\n api_key=api_key,\n chunk_size=chunk_size,\n max_retries=max_retries,\n timeout=request_timeout or None,\n show_progress_bar=show_progress_bar,\n model_kwargs=model_kwargs,\n )\n\n return EmbeddingsWithModels(\n embeddings=embeddings_instance,\n available_models=available_models_dict,\n )\n except Exception as e:\n msg = f\"Failed to initialize OpenAI embeddings: {e}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise\n\n if provider == \"Ollama\":\n try:\n from langchain_ollama import OllamaEmbeddings\n except ImportError:\n try:\n from langchain_community.embeddings import OllamaEmbeddings\n except ImportError:\n msg = \"Please install langchain-ollama: pip install langchain-ollama\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ImportError(msg) from None\n\n try:\n transformed_base_url = transform_localhost_url(ollama_base_url)\n\n # Check if URL contains /v1 suffix (OpenAI-compatible mode)\n if transformed_base_url and transformed_base_url.rstrip(\"/\").endswith(\"/v1\"):\n # Strip /v1 suffix and log warning\n transformed_base_url = transformed_base_url.rstrip(\"/\").removesuffix(\"/v1\")\n logger.warning(\n \"Detected '/v1' suffix in base URL. The Ollama component uses the native Ollama API, \"\n \"not the OpenAI-compatible API. The '/v1' suffix has been automatically removed. \"\n \"If you want to use the OpenAI-compatible API, please use the OpenAI component instead. \"\n \"Learn more at https://docs.ollama.com/openai#openai-compatibility\"\n )\n\n final_base_url = transformed_base_url or \"http://localhost:11434\"\n\n # Create the primary embedding instance\n embeddings_instance = OllamaEmbeddings(\n model=model,\n base_url=final_base_url,\n **model_kwargs,\n )\n\n # Fetch available Ollama models\n available_model_names = await self.fetch_ollama_models()\n\n # Create dedicated instances for each available model\n available_models_dict = {}\n for model_name in available_model_names:\n available_models_dict[model_name] = OllamaEmbeddings(\n model=model_name,\n base_url=final_base_url,\n **model_kwargs,\n )\n\n return EmbeddingsWithModels(\n embeddings=embeddings_instance,\n available_models=available_models_dict,\n )\n except Exception as e:\n msg = f\"Failed to initialize Ollama embeddings: {e}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise\n\n if provider == \"IBM watsonx.ai\":\n try:\n from langchain_ibm import WatsonxEmbeddings\n except ImportError:\n msg = \"Please install langchain-ibm: pip install langchain-ibm\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ImportError(msg) from None\n\n if not api_key:\n msg = \"IBM watsonx.ai API key is required when using IBM watsonx.ai provider\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n project_id = self.project_id\n\n if not project_id:\n msg = \"Project ID is required for IBM watsonx.ai provider\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n try:\n from ibm_watsonx_ai import APIClient, Credentials\n\n final_url = base_url_ibm_watsonx or \"https://us-south.ml.cloud.ibm.com\"\n\n credentials = Credentials(\n api_key=self.api_key,\n url=final_url,\n )\n\n api_client = APIClient(credentials)\n\n params = {\n EmbedTextParamsMetaNames.TRUNCATE_INPUT_TOKENS: self.truncate_input_tokens,\n EmbedTextParamsMetaNames.RETURN_OPTIONS: {\"input_text\": self.input_text},\n }\n\n # Create the primary embedding instance\n embeddings_instance = WatsonxEmbeddings(\n model_id=model,\n params=params,\n watsonx_client=api_client,\n project_id=project_id,\n )\n\n # Fetch available IBM watsonx.ai models\n available_model_names = self.fetch_ibm_models(final_url)\n\n # Create dedicated instances for each available model\n available_models_dict = {}\n for model_name in available_model_names:\n available_models_dict[model_name] = WatsonxEmbeddings(\n model_id=model_name,\n params=params,\n watsonx_client=api_client,\n project_id=project_id,\n )\n\n return EmbeddingsWithModels(\n embeddings=embeddings_instance,\n available_models=available_models_dict,\n )\n except Exception as e:\n msg = f\"Failed to authenticate with IBM watsonx.ai: {e}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise\n\n msg = f\"Unknown provider: {provider}\"\n if self.fail_safe_mode:\n logger.error(msg)\n return None\n raise ValueError(msg)\n\n async def update_build_config(\n self, build_config: dotdict, field_value: Any, field_name: str | None = None\n ) -> dotdict:\n # Handle fail_safe_mode changes first - set all required fields to False if enabled\n if field_name == \"fail_safe_mode\":\n if field_value: # If fail_safe_mode is enabled\n build_config[\"api_key\"][\"required\"] = False\n elif hasattr(self, \"provider\"):\n # If fail_safe_mode is disabled, restore required flags based on provider\n if self.provider in [\"OpenAI\", \"IBM watsonx.ai\"]:\n build_config[\"api_key\"][\"required\"] = True\n else: # Ollama\n build_config[\"api_key\"][\"required\"] = False\n\n if field_name == \"provider\":\n if field_value == \"OpenAI\":\n build_config[\"model\"][\"options\"] = OPENAI_EMBEDDING_MODEL_NAMES\n build_config[\"model\"][\"value\"] = OPENAI_EMBEDDING_MODEL_NAMES[0]\n build_config[\"api_key\"][\"display_name\"] = \"OpenAI API Key\"\n # Only set required=True if fail_safe_mode is not enabled\n build_config[\"api_key\"][\"required\"] = not (hasattr(self, \"fail_safe_mode\") and self.fail_safe_mode)\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"api_base\"][\"display_name\"] = \"OpenAI API Base URL\"\n build_config[\"api_base\"][\"advanced\"] = True\n build_config[\"api_base\"][\"show\"] = True\n build_config[\"ollama_base_url\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n build_config[\"truncate_input_tokens\"][\"show\"] = False\n build_config[\"input_text\"][\"show\"] = False\n elif field_value == \"Ollama\":\n build_config[\"ollama_base_url\"][\"show\"] = True\n\n if await is_valid_ollama_url(url=self.ollama_base_url):\n try:\n models = await self.fetch_ollama_models()\n build_config[\"model\"][\"options\"] = models\n build_config[\"model\"][\"value\"] = models[0] if models else \"\"\n except ValueError:\n build_config[\"model\"][\"options\"] = []\n build_config[\"model\"][\"value\"] = \"\"\n else:\n build_config[\"model\"][\"options\"] = []\n build_config[\"model\"][\"value\"] = \"\"\n build_config[\"truncate_input_tokens\"][\"show\"] = False\n build_config[\"input_text\"][\"show\"] = False\n build_config[\"api_key\"][\"display_name\"] = \"API Key (Optional)\"\n build_config[\"api_key\"][\"required\"] = False\n build_config[\"api_key\"][\"show\"] = False\n build_config[\"api_base\"][\"show\"] = False\n build_config[\"project_id\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = False\n\n elif field_value == \"IBM watsonx.ai\":\n build_config[\"model\"][\"options\"] = self.fetch_ibm_models(base_url=self.base_url_ibm_watsonx)\n build_config[\"model\"][\"value\"] = self.fetch_ibm_models(base_url=self.base_url_ibm_watsonx)[0]\n build_config[\"api_key\"][\"display_name\"] = \"IBM watsonx.ai API Key\"\n # Only set required=True if fail_safe_mode is not enabled\n build_config[\"api_key\"][\"required\"] = not (hasattr(self, \"fail_safe_mode\") and self.fail_safe_mode)\n build_config[\"api_key\"][\"show\"] = True\n build_config[\"api_base\"][\"show\"] = False\n build_config[\"ollama_base_url\"][\"show\"] = False\n build_config[\"base_url_ibm_watsonx\"][\"show\"] = True\n build_config[\"project_id\"][\"show\"] = True\n build_config[\"truncate_input_tokens\"][\"show\"] = True\n build_config[\"input_text\"][\"show\"] = True\n elif field_name == \"base_url_ibm_watsonx\":\n build_config[\"model\"][\"options\"] = self.fetch_ibm_models(base_url=field_value)\n build_config[\"model\"][\"value\"] = self.fetch_ibm_models(base_url=field_value)[0]\n elif field_name == \"ollama_base_url\":\n # # Refresh Ollama models when base URL changes\n # if hasattr(self, \"provider\") and self.provider == \"Ollama\":\n # Use field_value if provided, otherwise fall back to instance attribute\n ollama_url = self.ollama_base_url\n if await is_valid_ollama_url(url=ollama_url):\n try:\n models = await self.fetch_ollama_models()\n build_config[\"model\"][\"options\"] = models\n build_config[\"model\"][\"value\"] = models[0] if models else \"\"\n except ValueError:\n await logger.awarning(\"Failed to fetch Ollama embedding models.\")\n build_config[\"model\"][\"options\"] = []\n build_config[\"model\"][\"value\"] = \"\"\n\n elif field_name == \"model\" and self.provider == \"Ollama\":\n ollama_url = self.ollama_base_url\n if await is_valid_ollama_url(url=ollama_url):\n try:\n models = await self.fetch_ollama_models()\n build_config[\"model\"][\"options\"] = models\n except ValueError:\n await logger.awarning(\"Failed to refresh Ollama embedding models.\")\n build_config[\"model\"][\"options\"] = []\n\n return build_config\n"
|
|
},
|
|
"dimensions": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Dimensions",
|
|
"dynamic": false,
|
|
"info": "The number of dimensions the resulting output embeddings should have. Only supported by certain models.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "dimensions",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": ""
|
|
},
|
|
"fail_safe_mode": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Fail-Safe Mode",
|
|
"dynamic": false,
|
|
"info": "When enabled, errors will be logged instead of raising exceptions. The component will return None on error.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": false,
|
|
"name": "fail_safe_mode",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": true
|
|
},
|
|
"input_text": {
|
|
"_input_type": "BoolInput",
|
|
"advanced": true,
|
|
"display_name": "Include the original text in the output",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "input_text",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": true
|
|
},
|
|
"is_refresh": false,
|
|
"max_retries": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Max Retries",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "max_retries",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 3
|
|
},
|
|
"model": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Model Name",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Select the embedding model to use",
|
|
"load_from_db": false,
|
|
"name": "model",
|
|
"options": [
|
|
"ibm/granite-embedding-278m-multilingual",
|
|
"ibm/slate-125m-english-rtrvr-v2",
|
|
"ibm/slate-30m-english-rtrvr-v2",
|
|
"intfloat/multilingual-e5-large",
|
|
"sentence-transformers/all-minilm-l6-v2"
|
|
],
|
|
"options_metadata": [],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"refresh_button": true,
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "ibm/granite-embedding-278m-multilingual"
|
|
},
|
|
"model_kwargs": {
|
|
"_input_type": "DictInput",
|
|
"advanced": true,
|
|
"display_name": "Model Kwargs",
|
|
"dynamic": false,
|
|
"info": "Additional keyword arguments to pass to the model.",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "model_kwargs",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"track_in_telemetry": false,
|
|
"type": "dict",
|
|
"value": {}
|
|
},
|
|
"ollama_base_url": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": false,
|
|
"display_name": "Ollama API URL",
|
|
"dynamic": false,
|
|
"info": "Endpoint of the Ollama API (Ollama only). Defaults to http://localhost:11434",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": true,
|
|
"name": "ollama_base_url",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"show": false,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "OLLAMA_BASE_URL"
|
|
},
|
|
"project_id": {
|
|
"_input_type": "MessageTextInput",
|
|
"advanced": false,
|
|
"display_name": "Project ID",
|
|
"dynamic": false,
|
|
"info": "IBM watsonx.ai Project ID (required for IBM watsonx.ai)",
|
|
"input_types": [
|
|
"Message"
|
|
],
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"load_from_db": true,
|
|
"name": "project_id",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_input": true,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": false,
|
|
"type": "str",
|
|
"value": "WATSONX_PROJECT_ID"
|
|
},
|
|
"provider": {
|
|
"_input_type": "DropdownInput",
|
|
"advanced": false,
|
|
"combobox": false,
|
|
"dialog_inputs": {},
|
|
"display_name": "Model Provider",
|
|
"dynamic": false,
|
|
"external_options": {},
|
|
"info": "Select the embedding model provider",
|
|
"load_from_db": false,
|
|
"name": "provider",
|
|
"options": [
|
|
"OpenAI",
|
|
"Ollama",
|
|
"IBM watsonx.ai"
|
|
],
|
|
"options_metadata": [
|
|
{
|
|
"icon": "OpenAI"
|
|
},
|
|
{
|
|
"icon": "Ollama"
|
|
},
|
|
{
|
|
"icon": "WatsonxAI"
|
|
}
|
|
],
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"real_time_refresh": true,
|
|
"required": false,
|
|
"selected_metadata": {
|
|
"icon": "WatsonxAI"
|
|
},
|
|
"show": true,
|
|
"title_case": false,
|
|
"toggle": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "str",
|
|
"value": "IBM watsonx.ai"
|
|
},
|
|
"request_timeout": {
|
|
"_input_type": "FloatInput",
|
|
"advanced": true,
|
|
"display_name": "Request Timeout",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "request_timeout",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": 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",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "bool",
|
|
"value": false
|
|
},
|
|
"truncate_input_tokens": {
|
|
"_input_type": "IntInput",
|
|
"advanced": true,
|
|
"display_name": "Truncate Input Tokens",
|
|
"dynamic": false,
|
|
"info": "",
|
|
"list": false,
|
|
"list_add_label": "Add More",
|
|
"name": "truncate_input_tokens",
|
|
"override_skip": false,
|
|
"placeholder": "",
|
|
"required": false,
|
|
"show": true,
|
|
"title_case": false,
|
|
"tool_mode": false,
|
|
"trace_as_metadata": true,
|
|
"track_in_telemetry": true,
|
|
"type": "int",
|
|
"value": 200
|
|
}
|
|
},
|
|
"tool_mode": false
|
|
},
|
|
"showNode": true,
|
|
"type": "EmbeddingModel"
|
|
},
|
|
"dragging": false,
|
|
"id": "EmbeddingModel-cONxU",
|
|
"measured": {
|
|
"height": 534,
|
|
"width": 320
|
|
},
|
|
"position": {
|
|
"x": -327.0926077774787,
|
|
"y": 909.1496086886345
|
|
},
|
|
"selected": false,
|
|
"type": "genericNode"
|
|
}
|
|
],
|
|
"viewport": {
|
|
"x": 470.8619752966712,
|
|
"y": -133.63346875696777,
|
|
"zoom": 0.36224591795587874
|
|
}
|
|
},
|
|
"description": "OpenRAG OpenSearch Nudges generator, based on the OpenSearch documents and the chat history.",
|
|
"endpoint_name": null,
|
|
"id": "ebc01d31-1976-46ce-a385-b0240327226c",
|
|
"is_component": false,
|
|
"locked": true,
|
|
"last_tested_version": "1.7.0.dev21",
|
|
"name": "OpenRAG OpenSearch Nudges Flow",
|
|
"tags": [
|
|
"assistants",
|
|
"agents"
|
|
]
|
|
}
|