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-classicagentsagentLLMSingleActionAgent
    Class●Since v1.0Deprecated

    LLMSingleActionAgent

    Copy
    LLMSingleActionAgent()

    Bases

    BaseSingleActionAgent

    Attributes

    Methods

    Inherited fromBaseSingleActionAgent

    Attributes

    Areturn_values: list[str]
    —

    Return values of the agent.

    Methods

    Mget_allowed_tools
    —

    Get allowed tools.

    Mreturn_stopped_response
    —

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

    View source on GitHub
    Mfrom_llm_and_tools
    —

    Construct an agent from an LLM and tools.

    Msave
    —

    Save the agent.

    attribute
    llm_chain: LLMChain
    attribute
    output_parser: AgentOutputParser
    attribute
    stop: list[str]
    attribute
    input_keys: list[str]
    method
    dict
    method
    plan
    method
    aplan
    method
    tool_run_logging_kwargs

    Base class for single action agents.

    LLMChain to use for agent.

    Output parser to use for agent.

    List of strings to stop on.

    Return the input keys.

    Return dictionary representation of agent.

    Given input, decided what to do.

    Async given input, decided what to do.

    Return logging kwargs for tool run.