LangChain Reference home pageLangChain ReferenceLangChain Reference
  • GitHub
  • Main Docs
Deep Agents
LangChain
LangGraph
Integrations
LangSmith
  • Overview
  • MCP Adapters
    Standard Tests
    Text Splitters
    • Overview
    • Agents
    • Callbacks
    • Chains
    • Chat models
    • Embeddings
    • Evaluation
    • Globals
    • Hub
    • Memory
    • Output parsers
    • Retrievers
    • Runnables
    • LangSmith
    • Storage
    ⌘I

    LangChain Assistant

    Ask a question to get started

    Enter to send•Shift+Enter new line

    Menu

    MCP Adapters
    Standard Tests
    Text Splitters
    OverviewAgentsCallbacksChainsChat modelsEmbeddingsEvaluationGlobalsHubMemoryOutput parsersRetrieversRunnablesLangSmithStorage
    Language
    Theme
    Pythonlangchain-classicagentsagentRunnableMultiActionAgent
    Class●Since v1.0

    RunnableMultiActionAgent

    Copy
    RunnableMultiActionAgent()

    Bases

    BaseMultiActionAgent

    Attributes

    Methods

    Inherited fromBaseMultiActionAgent

    Methods

    Mget_allowed_tools
    —

    Get allowed tools.

    Mreturn_stopped_response
    —

    Return response when agent has been stopped due to max iterations.

    Mdict
    —

    Return dictionary representation of agent.

    M
    View source on GitHub
    save
    —

    Save the agent.

    Mtool_run_logging_kwargs
    —

    Return logging kwargs for tool run.

    attribute
    runnable: Runnable[dict, list[AgentAction] | AgentFinish]
    attribute
    input_keys_arg: list[str]
    attribute
    return_keys_arg: list[str]
    attribute
    stream_runnable: bool
    attribute
    model_config
    attribute
    return_values: list[str]
    attribute
    input_keys: list[str]
    method
    plan
    method
    aplan

    Agent powered by Runnables.

    Runnable to call to get agent actions.

    Whether to stream from the runnable or not.

    If True then underlying LLM is invoked in a streaming fashion to make it possible to get access to the individual LLM tokens when using stream_log with the AgentExecutor. If False then LLM is invoked in a non-streaming fashion and individual LLM tokens will not be available in stream_log.

    Return values of the agent.

    Return the input keys.

    Based on past history and current inputs, decide what to do.

    Async based on past history and current inputs, decide what to do.