Skip to main content
1

Create a Python file

touch gemini_reasoning_tools.py
2

Add the following code to your Python file

gemini_reasoning_tools.py
from agno.agent import Agent
from agno.models.google import Gemini
from agno.tools.reasoning import ReasoningTools
from agno.tools.duckduckgo import DuckDuckGoTools

reasoning_agent = Agent(
    model=Gemini(id="gemini-2.5-pro-preview-03-25"),
    tools=[
        ReasoningTools(
            think=True,
            analyze=True,
            add_instructions=True,
        ),
        DuckDuckGoTools(),
    ],
    instructions="Use tables where possible",
    stream_events=True,
        markdown=True,
    debug_mode=True,
)
reasoning_agent.print_response(
    "Write a report comparing NVDA to TSLA.", show_full_reasoning=True
)
3

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
4

Install libraries

pip install -U agno google-genai ddgs
5

Export your Google API key

  export GOOGLE_API_KEY="your_google_api_key_here"
6

Run Agent

python gemini_reasoning_tools.py