Ollama Reasoning Tools

Local Llama 3.2 via Ollama uses ReasoningTools and web search for an NVDA vs TSLA report.

ollama_reasoning_tools.py

"""
Ollama Reasoning Tools
======================

Demonstrates this reasoning cookbook example.
"""

from agno.agent import Agent
from agno.models.ollama.chat import Ollama
from agno.tools.reasoning import ReasoningTools
from agno.tools.websearch import WebSearchTools


# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------
def run_example() -> None:
    reasoning_agent = Agent(
        model=Ollama(id="llama3.2:latest"),
        tools=[
            ReasoningTools(
                enable_think=True,
                enable_analyze=True,
                add_instructions=True,
                add_few_shot=True,
            ),
            WebSearchTools(),
        ],
        instructions="Use tables where possible",
        markdown=True,
    )
    reasoning_agent.print_response(
        "Write a report comparing NVDA to TSLA",
        stream=True,
        show_full_reasoning=True,
    )


# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    run_example()

Run the Example

1. Set up your virtual environment

   Mac

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

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

   uv pip install -U agno ddgs ollama
   
3. Prepare Ollama

   Install and start Ollama, then pull the model used by this example:

   ollama pull llama3.2:latest
   
4. Run the example

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

   python ollama_reasoning_tools.py
   

Full source: cookbook/10_reasoning/tools/ollama_reasoning_tools.py