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-classicagentsreactbaseReActDocstoreAgent
    Class●Since v1.0Deprecated

    ReActDocstoreAgent

    Agent for the ReAct chain.

    Copy
    ReActDocstoreAgent()

    Bases

    Agent

    Attributes

    attribute
    output_parser: AgentOutputParser
    attribute
    observation_prefix: str

    Prefix to append the observation with.

    attribute
    llm_prefix: str

    Prefix to append the LLM call with.

    Methods

    method
    create_prompt

    Return default prompt.

    Inherited fromAgent

    Attributes

    Allm_chain: RunnableAallowed_tools: list[str] | None
    —

    Allowed tools for the agent. If None, all tools are allowed.

    Areturn_values: list[str]
    —

    Return values of the agent.

    Ainput_keys: list[str]

    Methods

    Mdict
    —

    Return dictionary representation of agent.

    Mget_allowed_tools
    —

    Get allowed tools.

    Mplan
    —

    Given input, decided what to do.

    Maplan
    —

    Async given input, decided what to do.

    Mget_full_inputs
    —

    Create the full inputs for the LLMChain from intermediate steps.

    Mvalidate_prompt
    —

    Validate that prompt matches format.

    Mfrom_llm_and_tools
    —

    Construct an agent from an LLM and tools.

    Mreturn_stopped_response
    —

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

    Mtool_run_logging_kwargs
    —

    Return logging kwargs for tool run.

    Inherited fromBaseSingleActionAgent

    Attributes

    Areturn_values: list[str]
    —

    Return values of the agent.

    Ainput_keys: list[str]

    Methods

    Mget_allowed_tools
    —

    Get allowed tools.

    Mplan
    —

    Given input, decided what to do.

    Maplan
    —

    Async given input, decided what to do.

    Mreturn_stopped_response
    —

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

    Mfrom_llm_and_tools
    —

    Construct an agent from an LLM and tools.

    Mdict
    —

    Return dictionary representation of agent.

    Msave
    —

    Save the agent.

    Mtool_run_logging_kwargs
    —

    Return logging kwargs for tool run.

    View source on GitHub