Agent with Reasoning Effort

Control how much reasoning o3-mini does with the reasoning_effort parameter.

Code

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.websearch import WebSearchTools

agent = Agent(
    model=OpenAIChat(id="o3-mini", reasoning_effort="high"),
    tools=[WebSearchTools(enable_news=False)],
    instructions="Use tables to display data.",
    markdown=True,
)

agent.print_response("Write a report comparing NVDA to TSLA", stream=True)

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Set your API key

export OPENAI_API_KEY=xxx

Install dependencies

uv pip install -U openai ddgs agno

Run Agent

Save the code above as reasoning_effort.py, then run:

python reasoning_effort.py