OpenAI o3-mini with reasoning effort

Code

cookbook/reasoning/models/openai/reasoning_effort.py

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=OpenAIChat(id="o3-mini", reasoning_effort="high"),
    tools=[
        DuckDuckGoTools(
            search=True,
            news=True,
        )
    ],
    instructions="Use tables to display data.",
    show_tool_calls=True,
    markdown=True,
)
agent.print_response("Write a report comparing artificial intelligence trends in different industries", stream=True)

Usage

1. Create a virtual environment

   Open the Terminal and create a python virtual environment.

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   
2. Set your API key

   export OPENAI_API_KEY=xxx
   
3. Install libraries

   pip install -U openai agno
   
4. Run Agent

   Mac

     python cookbook/reasoning/models/openai/reasoning_effort.py