Llama Reasoning Tools

Llama 4 Maverick pairs ReasoningTools with YFinanceTools to report on the NVDA stock price.

llama_reasoning_tools.py

"""
Llama Reasoning Tools
=====================

Demonstrates this reasoning cookbook example.
"""

from agno.agent import Agent
from agno.models.meta import Llama
from agno.tools.reasoning import ReasoningTools
from agno.tools.yfinance import YFinanceTools


# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------
def run_example() -> None:
    reasoning_agent = Agent(
        model=Llama(id="Llama-4-Maverick-17B-128E-Instruct-FP8"),
        tools=[
            ReasoningTools(
                enable_think=True,
                enable_analyze=True,
                add_instructions=True,
            ),
            YFinanceTools(),
        ],
        instructions="Use tables where possible",
        markdown=True,
    )
    reasoning_agent.print_response(
        "What is the NVDA stock price? Write me a report",
        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 llama-api-client yfinance
   
3. Export your Meta Llama API key

   Mac/Linux

   export LLAMA_API_KEY="your_llama_api_key_here"
   

   $Env:LLAMA_API_KEY="your_llama_api_key_here"
   
4. Run the example

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

   python llama_reasoning_tools.py
   

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