Mistral Reasoning COT

Run mistral-large-latest with reasoning=True and use_json_mode=True, streaming the full chain-of-thought for a Fibonacci script walkthrough.

Demonstrates built-in chain-of-thought reasoning with Mistral.

mistral_reasoning_cot.py

"""
Mistral Reasoning COT
=====================

Demonstrates built-in chain-of-thought reasoning with Mistral.
"""

from agno.agent import Agent
from agno.models.mistral import MistralChat

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
reasoning_agent = Agent(
    model=MistralChat(id="mistral-large-latest"),
    reasoning=True,
    markdown=True,
    use_json_mode=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    reasoning_agent.print_response(
        "Give me steps to write a python script for fibonacci series",
        stream=True,
        show_full_reasoning=True,
    )

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 mistralai
   
3. Export your Mistral API key

   Mac/Linux

   export MISTRAL_API_KEY="your_mistral_api_key_here"
   

   $Env:MISTRAL_API_KEY="your_mistral_api_key_here"
   
4. Run the example

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

   python mistral_reasoning_cot.py
   

Full source: cookbook/10_reasoning/agents/mistral_reasoning_cot.py