langchain.agents.initialize.initialize_agent(tools: Sequence[BaseTool], llm: BaseLanguageModel, agent: Optional[AgentType] = None, callback_manager: Optional[BaseCallbackManager] = None, agent_path: Optional[str] = None, agent_kwargs: Optional[dict] = None, *, tags: Optional[Sequence[str]] = None, **kwargs: Any) AgentExecutor[source]

[Deprecated] Load an agent executor given tools and LLM.

  • tools (Sequence[BaseTool]) – List of tools this agent has access to.

  • llm (BaseLanguageModel) – Language model to use as the agent.

  • agent (Optional[AgentType]) – Agent type to use. If None and agent_path is also None, will default to AgentType.ZERO_SHOT_REACT_DESCRIPTION.

  • callback_manager (Optional[BaseCallbackManager]) – CallbackManager to use. Global callback manager is used if not provided. Defaults to None.

  • agent_path (Optional[str]) – Path to serialized agent to use.

  • agent_kwargs (Optional[dict]) – Additional keyword arguments to pass to the underlying agent

  • tags (Optional[Sequence[str]]) – Tags to apply to the traced runs.

  • **kwargs (Any) – Additional keyword arguments passed to the agent executor


An agent executor

Return type



Deprecated since version 0.1.0: Use Use new agent constructor methods like create_react_agent, create_json_agent, create_structured_chat_agent, etc. instead.

Examples using initialize_agent