langchain.agents.agent_types.AgentType

class langchain.agents.agent_types.AgentType(value)

[Deprecated] An enum for agent types.

See documentation: https://python.langchain.com/docs/modules/agents/agent_types/

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.

ZERO_SHOT_REACT_DESCRIPTION = 'zero-shot-react-description'

A zero shot agent that does a reasoning step before acting.

REACT_DOCSTORE = 'react-docstore'

A zero shot agent that does a reasoning step before acting.

This agent has access to a document store that allows it to look up relevant information to answering the question.

SELF_ASK_WITH_SEARCH = 'self-ask-with-search'

An agent that breaks down a complex question into a series of simpler questions.

This agent uses a search tool to look up answers to the simpler questions in order to answer the original complex question.

CONVERSATIONAL_REACT_DESCRIPTION = 'conversational-react-description'

CHAT_ZERO_SHOT_REACT_DESCRIPTION = 'chat-zero-shot-react-description'

A zero shot agent that does a reasoning step before acting.

This agent is designed to be used in conjunction

CHAT_CONVERSATIONAL_REACT_DESCRIPTION = 'chat-conversational-react-description'

STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION = 'structured-chat-zero-shot-react-description'

An zero-shot react agent optimized for chat models.

This agent is capable of invoking tools that have multiple inputs.

OPENAI_FUNCTIONS = 'openai-functions'

An agent optimized for using open AI functions.

OPENAI_MULTI_FUNCTIONS = 'openai-multi-functions'

Examples using AgentType

• 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

• Create a dataframe

• 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

• LLMonitor

• 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/protectai/deberta-v3-base-prompt-injection-v2

• airbyte_structured_qa.md

• 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

• 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”] = “”

• pandas.md

• scenario 1 - LLM

• 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