create_vectorstore_router_agent() — langchain Function Reference

Source Code

libs/langchain/langchain_classic/agents/agent_toolkits/vectorstore/base.py lines 133–230

def create_vectorstore_router_agent(
    llm: BaseLanguageModel,
    toolkit: VectorStoreRouterToolkit,
    callback_manager: BaseCallbackManager | None = None,
    prefix: str = ROUTER_PREFIX,
    verbose: bool = False,  # noqa: FBT001,FBT002
    agent_executor_kwargs: dict[str, Any] | None = None,
    **kwargs: Any,
) -> AgentExecutor:
    """Construct a VectorStore router agent from an LLM and tools.

    !!! note
        This class is deprecated. See below for a replacement that uses tool calling
        methods and LangGraph. Install LangGraph with:

        ```bash
        pip install -U langgraph
        ```

        ```python
        from langchain_core.tools import create_retriever_tool
        from langchain_core.vectorstores import InMemoryVectorStore
        from langchain_openai import ChatOpenAI, OpenAIEmbeddings
        from langgraph.prebuilt import create_react_agent

        model = ChatOpenAI(model="gpt-4o-mini", temperature=0)

        pet_vector_store = InMemoryVectorStore.from_texts(
            [
                "Dogs are great companions, known for their loyalty and friendliness.",
                "Cats are independent pets that often enjoy their own space.",
            ],
            OpenAIEmbeddings(),
        )

        food_vector_store = InMemoryVectorStore.from_texts(
            [
                "Carrots are orange and delicious.",
                "Apples are red and delicious.",
            ],
            OpenAIEmbeddings(),
        )

        tools = [
            create_retriever_tool(
                pet_vector_store.as_retriever(),
                "pet_information_retriever",
                "Fetches information about pets.",
            ),
            create_retriever_tool(
                food_vector_store.as_retriever(),
                "food_information_retriever",
                "Fetches information about food.",
            ),
        ]

        agent = create_react_agent(model, tools)

        for step in agent.stream(
            {"messages": [("human", "Tell me about carrots.")]},
            stream_mode="values",
        ):
            step["messages"][-1].pretty_print()
        ```

    Args:
        llm: LLM that will be used by the agent
        toolkit: Set of tools for the agent which have routing capability with multiple
            vector stores
        callback_manager: Object to handle the callback
        prefix: The prefix prompt for the router agent.
            If not provided uses default `ROUTER_PREFIX`.
        verbose: If you want to see the content of the scratchpad.
        agent_executor_kwargs: If there is any other parameter you want to send to the
            agent.
        kwargs: Additional named parameters to pass to the `ZeroShotAgent`.

    Returns:
        Returns a callable `AgentExecutor` object.
        Either you can call it or use run method with the query to get the response.