OpenAI Responses Web Search

What is the OpenAI Responses Web Search tool?

The OpenAI Responses Web Search tool is a built-in capability in the Agno framework that allows AI agents to search the web with the responses api native tool. 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 OPENAI_API_KEY environment variable. Get your API key at platform.openai.com.

How to use OpenAI Responses Web 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 OpenAI Responses Web Search

   Click the agent, go to the Tools tab, and toggle on "OpenAI Responses Web Search" from the core category.

3. 3

   Add your API key

   Enter your OPENAI_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 OpenAI Responses Web Search when relevant.

5. 5

   Export Python code

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

Python code example

This is the code Agno Builder exports when you use OpenAI Responses Web Search:

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.models.openai.responses import dict

agent = Agent(
    name="OpenAI Responses Web Search Agent",
    model=OpenAIChat(id="gpt-4o"),
    tools=[dict()],
    instructions=["Use the openai responses web search tool to help the user."],
    markdown=True,
)

agent.print_response("Help me with a openai-responses task")

Install with: pip install agno # + set OPENAI_API_KEY

Configuration options