langchain.agents.initialize.initialize_agent

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

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

Parameters

• 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

Returns

An agent executor

Return type

AgentExecutor

Notes

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

• ANTHROPIC_API_KEY=<YOUR ANTHROPIC API KEY>

• Answer with ‘Zhu’

• Artifacts are charts created by matplotlib when `plt.show()` is called

• Connect to Comet if no API Key is set

• Copilot Sandbox

• Debugging

• Extract pdf content

• First, define custom callback handler implementations

• Flyte

• For Windows/Linux

• How YahooFinanceNewsTool works? {#how-yahoofinancenewstool-works}

• IMPORTANT: If you plan to use this account in the future, make sure to save the

• If this is your first time using playwright, you’ll have to install a browser executable.

• Initialize the language model

• LLM Hyperparameters

• LLMonitor

• Needed if you would like to display images in the notebook

• SCENARIO 1 - LLM

• SearchApi

• Select the LLM to use. Here, we use gpt-3.5-turbo-instruct

• Serper - Google Search API

• Set environmental variables here

• Set this to your Zep server URL

• Set your environment variables using os.environ

• Setup and use the ClearML Callback

• Specify your Connery Runner credentials.

• Streamlit

• These are sample parameters for Falcon 40B Instruct Deployed from Amazon SageMaker JumpStart

• Used by the agent in this tutorial

• Using https://huggingface.co/laiyer/deberta-v3-base-prompt-injection

• argilla.md

• awslambda.md

• bash.md

• chatgpt_plugins.md

• document_comparison_toolkit.md

• edenai_tools.md

• eleven_labs_tts.md

• folder_id=’1yucgL9WGgWZdM1TOuKkeghlPizuzMYb5’

• get from https://platform.openai.com/

• google_finance.md

• google_serper.md

• gradio_tools.md

• graphql.md

• jira.md

• memorize.md

• nasa.md

• need to use GPT-4 here as GPT-3.5 does not understand, however hard you insist, that

• openweathermap.md

• os.environ[“OPENAI_API_KEY”] = “”

• os.environ[“OPENAI_ORGANIZATION”] = “…”

• scenario 1 - LLM

• sceneXplain.md

• search_tools.md

• searchapi.md

• steam.md

• token_usage_tracking.md

• use it with langchain {#use-it-with-langchain}

• wandb documentation to configure wandb using env variables

• xata_chat_message_history.md