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-classicagentsconversationalbaseConversationalAgentfrom_llm_and_tools
    Method●Since v1.0

    from_llm_and_tools

    Construct an agent from an LLM and tools.

    Copy
    from_llm_and_tools(
      cls,
      llm: BaseLanguageModel,
      tools: Sequence[BaseTool],
      callback_manager: BaseCallbackManager | None = None,
      output_parser: AgentOutputParser | None = None,
      prefix: str = PREFIX,
      suffix: str = SUFFIX,
      format_instructions: str = FORMAT_INSTRUCTIONS,
      ai_prefix: str = 'AI',
      human_prefix: str = 'Human',
      input_variables: list[str] | None = None,
      **kwargs: Any = {}
    ) -> Agent

    Parameters

    NameTypeDescription
    llm*BaseLanguageModel

    The language model to use.

    tools*Sequence[BaseTool]

    A list of tools to use.

    callback_managerBaseCallbackManager | None
    Default:None

    The callback manager to use.

    output_parserAgentOutputParser | None
    Default:None

    The output parser to use.

    prefixstr
    Default:PREFIX

    The prefix to use in the prompt.

    suffixstr
    Default:SUFFIX

    The suffix to use in the prompt.

    format_instructionsstr
    Default:FORMAT_INSTRUCTIONS

    The format instructions to use.

    ai_prefixstr
    Default:'AI'

    The prefix to use before AI output.

    human_prefixstr
    Default:'Human'

    The prefix to use before human output.

    input_variableslist[str] | None
    Default:None

    The input variables to use.

    **kwargsAny
    Default:{}

    Any additional keyword arguments to pass to the agent.

    View source on GitHub