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

    LangChain Assistant

    Ask a question to get started

    Enter to send•Shift+Enter new line

    Menu

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

    aplan

    Copy
    aplan(
      self,
      intermediate_steps: list[tuple[AgentAction, str]],
      callbacks: Callbacks
    View source on GitHub
    =
    None
    ,
    **
    kwargs
    :
    Any
    =
    {
    }
    )
    ->
    list
    [
    AgentAction
    ]
    |
    AgentFinish

    Parameters

    NameTypeDescription
    intermediate_steps*list[tuple[AgentAction, str]]

    Steps the LLM has taken to date, along with observations.

    callbacksCallbacks
    Default:None

    Callbacks to run.

    **kwargsAny
    Default:{}

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

    User inputs.