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-classicagentsmrklbaseMRKLChainfrom_chains
    Methodā—Since v1.0

    from_chains

    Copy
    from_chains(
      cls,
      llm: BaseLanguageModel,
      chains: list[ChainConfig],
      **kwargs: Any
    View source on GitHub
    =
    {
    }
    )
    ->
    AgentExecutor

    Parameters

    NameTypeDescription
    llm*BaseLanguageModel
    chains*list[ChainConfig]
    **kwargsAny
    Default:{}

    User-friendly way to initialize the MRKL chain.

    This is intended to be an easy way to get up and running with the MRKL chain.

    The LLM to use as the agent LLM.

    The chains the MRKL system has access to.

    parameters to be passed to initialization.