langchain.tools.retriever.create_retriever_tool

langchain.tools.retriever.create_retriever_tool(retriever: BaseRetriever, name: str, description: str, *, document_prompt: Optional[BasePromptTemplate] = None, document_separator: str = '\n\n') → Tool

Create a tool to do retrieval of documents.

Parameters

• retriever (BaseRetriever) – The retriever to use for the retrieval

• name (str) – The name for the tool. This will be passed to the language model, so should be unique and somewhat descriptive.

• description (str) – The description for the tool. This will be passed to the language model, so should be descriptive.

• document_prompt (Optional[BasePromptTemplate]) –

• document_separator (str) –

Returns

Tool class to pass to an agent

Return type

Tool

Examples using create_retriever_tool

• Conversational Retrieval Agent

• SQL

• Set env var OPENAI_API_KEY or load from a .env file

• Xata chat memory