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
    โŒ˜I

    Chat LangChain

    What can I help with?

    Enter to sendยทShift+Enter new line

    Menu

    MCP Adapters
    Standard Tests
    Text Splitters
    OverviewAgentsCallbacksChainsChat modelsEmbeddingsEvaluationGlobalsHubMemoryOutput parsersRetrieversRunnablesLangSmithStorage
    Language
    Theme
    Pythonlangchain-classicagentsagentAgentget_full_inputs
    Methodโ—Since v1.5

    get_full_inputs

    Copy
    get_full_inputs(
      self,
      intermediate_steps: list[tuple[AgentAction, str]],
      kwargs: Any
    View source on GitHub
    =
    {
    }
    )
    ->
    builtins
    .
    dict
    [
    str
    ,
    Any
    ]

    Parameters

    NameTypeDescription
    intermediate_steps*list[tuple[AgentAction, str]]
    **kwargsAny
    Default:{}

    Create the full inputs for the LLMChain from intermediate steps.

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

    User inputs.