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-classicagentsagent
    Module●Since v1.0

    agent

    Chain that takes in an input and produces an action and action input.

    Attributes

    attribute
    AGENT_DEPRECATION_WARNING: str
    attribute
    logger
    attribute
    NextStepOutput: list[AgentFinish | AgentAction | AgentStep]

    Classes

    class
    AgentExecutorIterator

    Iterator for AgentExecutor.

    class
    InvalidTool

    Tool that is run when invalid tool name is encountered by agent.

    class
    Chain

    Abstract base class for creating structured sequences of calls to components.

    Chains should be used to encode a sequence of calls to components like models, document retrievers, other chains, etc., and provide a simple interface to this sequence.

    class
    BaseSingleActionAgent

    Base Single Action Agent class.

    class
    BaseMultiActionAgent

    Base Multi Action Agent class.

    class
    AgentOutputParser

    Base class for parsing agent output into agent action/finish.

    class
    MultiActionAgentOutputParser

    Base class for parsing agent output into agent actions/finish.

    This is used for agents that can return multiple actions.

    class
    RunnableAgent

    Agent powered by Runnables.

    class
    RunnableMultiActionAgent

    Agent powered by Runnables.

    class
    ExceptionTool

    Tool that just returns the query.

    class
    AgentExecutor

    Agent that is using tools.

    deprecatedclass
    AgentType

    An enum for agent types.

    deprecatedclass
    LLMChain

    Chain to run queries against LLMs.

    This class is deprecated. See below for an example implementation using LangChain runnables:

    from langchain_core.output_parsers import StrOutputParser
    from langchain_core.prompts import PromptTemplate
    from langchain_openai import OpenAI
    
    prompt_template = "Tell me a {adjective} joke"
    prompt = PromptTemplate(input_variables=["adjective"], template=prompt_template)
    model = OpenAI()
    chain = prompt | model | StrOutputParser()
    
    chain.invoke("your adjective here")
    deprecatedclass
    LLMSingleActionAgent

    Base class for single action agents.

    deprecatedclass
    Agent

    Agent that calls the language model and deciding the action.

    This is driven by a LLMChain. The prompt in the LLMChain MUST include a variable called "agent_scratchpad" where the agent can put its intermediary work.

    Type Aliases

    typeAlias
    RunnableAgentType
    View source on GitHub