Tavily Search Tool#

The Tavily AI search integration allows users to perform real-time web searches within the AG2 framework. Follow these steps to integrate TavilySearchTool with AG2 Agents.

Configuring Your Tavily API Key#

1. Create a Tavily Account:

   • Visit Tavily AI
   • Click Sign Up and create an account

2. Get API Key:

   • Navigate to Tavily API
   • Generate API key under API Keys

3. Set Environment Variable:

   export TAVILY_API_KEY="your_api_key_here"
   

Package Installation#

To get started with the Tavily Search integration in AG2, follow these steps:

Install AG2 with openai extra since we use openai in our examples:

pip install -U "ag2[openai]"

Note: If you have been using autogen or pyautogen, all you need to do is upgrade it using:

pip install -U "autogen[openai]"

or

pip install -U "pyautogen[openai]"

as pyautogen, autogen, and ag2 are aliases for the same PyPI package.

You’re all set! Now you can start using Tavily AI Search with AG2.

Implementation#

The TavilySearchTool enables agents to perform real time AI Powered web search.

Imports#

import os

from autogen import AssistantAgent, UserProxyAgent
from autogen.tools.experimental import TavilySearchTool

Agent Configuration#

Configure an assistant agent and user proxy to be used for LLM recommendation and execution respectively.

os.environ["AUTOGEN_USE_DOCKER"] = "False"

from autogen import LLMConfig

config_list = LLMConfig(api_type="openai", model="gpt-4o-mini")

assistant = AssistantAgent(
    name="assistant",
    llm_config=config_list,
)

user_proxy = UserProxyAgent(name="user_proxy", human_input_mode="NEVER")

Tool Setup#

tavily_search_tool = TavilySearchTool(tavily_api_key=os.getenv("TAVILY_API_KEY"))

# Register the tool for LLM recommendation and execution.
tavily_search_tool.register_for_llm(assistant)
tavily_search_tool.register_for_execution(user_proxy)

Start the Conversation#

With the setup complete, you can now use the assistant to fetch live web search results.

response = user_proxy.initiate_chat(
    recipient=assistant,
    message="What happened with stock prices after deepseek was launched? Please search the web.",
    max_turns=2,
)
print(f"Final Answer: {response.summary}")