Tavily Search

What is the Tavily Search tool?

The Tavily Search tool is a built-in capability in the Agno framework that allows AI agents to ai-powered web search optimized for llms. When added to an agent in Agno Builder, the agent can autonomously decide when to invoke this tool based on the user's request.

This tool requires a TAVILY_API_KEY environment variable. Get your API key at app.tavily.com.

How to use Tavily Search in Agno Builder

1. 1

   Create an agent

   Drag an Agent node onto the canvas in Agno Builder, or use one of the built-in templates.

2. 2

   Enable Tavily Search

   Click the agent, go to the Tools tab, and toggle on "Tavily Search" from the search category.

3. 3

   Add your API key

   Enter your TAVILY_API_KEY in the tool configuration. Your key stays in your browser and is never stored on our servers.

4. 4

   Test in chat

   Open the chat panel and send a message. The agent will automatically use Tavily Search when relevant.

5. 5

   Export Python code

   Click File > Export Python to get clean, runnable code with the correct imports for Tavily Search.

Python code example

This is the code Agno Builder exports when you use Tavily Search:

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.tavily import TavilyTools

agent = Agent(
    name="Tavily Search Agent",
    model=OpenAIChat(id="gpt-4o"),
    tools=[TavilyTools()],
    instructions=["Use the tavily search tool to help the user."],
    markdown=True,
)

agent.print_response("Research the current state of AI agent builders")

Install with: pip install agno # + set TAVILY_API_KEY

Configuration options