WatsonX Default COT Fallback

Runs an IBM WatsonX llama-3-3-70b-instruct agent with reasoning=True to stream default chain-of-thought steps in debug mode.

Demonstrates default chain-of-thought behavior with an IBM WatsonX model.

ibm_watsonx_default_COT.py

"""
WatsonX Default COT Fallback
============================

Demonstrates default chain-of-thought behavior with an IBM WatsonX model.
"""

from agno.agent import Agent
from agno.models.ibm import WatsonX

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
reasoning_agent = Agent(
    model=WatsonX(id="meta-llama/llama-3-3-70b-instruct"),
    reasoning=True,
    debug_mode=True,
    markdown=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 ibm-watsonx-ai
   
3. Export environment variables

   Mac/Linux

   export IBM_WATSONX_API_KEY="your_ibm_watsonx_api_key_here"
   export IBM_WATSONX_PROJECT_ID="your_ibm_watsonx_project_id_here"
   

   $Env:IBM_WATSONX_API_KEY="your_ibm_watsonx_api_key_here"
   $Env:IBM_WATSONX_PROJECT_ID="your_ibm_watsonx_project_id_here"
   
4. Run the example

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

   python ibm_watsonx_default_COT.py
   

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