Skip to main content
1

Create a Python file

touch ollama_reasoning_tools.py
2

Add the following code to your Python file

ollama_reasoning_tools.py
from agno.agent import Agent
from agno.models.ollama.chat import Ollama
from agno.tools.duckduckgo import DuckDuckGoTools
from agno.tools.reasoning import ReasoningTools

reasoning_agent = Agent(
    model=Ollama(id="llama3.2:latest"),
    tools=[
        ReasoningTools(
            think=True,
            analyze=True,
            add_instructions=True,
            add_few_shot=True,
        ),
        DuckDuckGoTools(),
    ],
    instructions="Use tables where possible",
    markdown=True,
)
reasoning_agent.print_response(
    "Write a report comparing NVDA to TSLA",
    stream=True,
    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 ollama ddgs
5

Run Agent

python ollama_reasoning_tools.py