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-classicagentstypes
    Moduleā—Since v1.0

    types

    Attributes

    Classes

    Type Aliases

    View source on GitHub
    attribute
    AGENT_TO_CLASS: dict[AgentType, AGENT_TYPE]
    class
    BaseSingleActionAgent
    deprecatedclass
    AgentType
    deprecatedclass
    ChatAgent
    deprecatedclass
    ConversationalAgent
    deprecatedclass
    ConversationalChatAgent
    deprecatedclass
    ZeroShotAgent
    deprecatedclass
    OpenAIFunctionsAgent
    deprecatedclass
    OpenAIMultiFunctionsAgent
    deprecatedclass
    ReActDocstoreAgent
    deprecatedclass
    SelfAskWithSearchAgent
    deprecatedclass
    StructuredChatAgent
    typeAlias
    AGENT_TYPE: type[BaseSingleActionAgent] | type[OpenAIMultiFunctionsAgent]

    Base Single Action Agent class.

    An enum for agent types.

    Chat Agent.

    An agent that holds a conversation in addition to using tools.

    An agent designed to hold a conversation in addition to using tools.

    Agent for the MRKL chain.

    An Agent driven by OpenAIs function powered API.

    Agent driven by OpenAIs function powered API.

    Agent for the ReAct chain.

    Agent for the self-ask-with-search paper.

    Structured Chat Agent.