LiteLLM Tool Use

Call YFinance tools from a LiteLLM agent with sync, streaming, and async runs.

tool_use.py

"""
Litellm Tool Use
================

Cookbook example for `litellm/tool_use.py`.
"""

import asyncio

from agno.agent import Agent
from agno.models.litellm import LiteLLM
from agno.tools.yfinance import YFinanceTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

openai_agent = Agent(
    model=LiteLLM(
        id="gpt-4o",
        name="LiteLLM",
    ),
    markdown=True,
    tools=[YFinanceTools()],
)

# Ask a question that would likely trigger tool use

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    openai_agent.print_response("How is TSLA stock doing right now?")

    # --- Sync + Streaming ---
    openai_agent.print_response("Whats happening in France?", stream=True)

    # --- Async ---
    asyncio.run(openai_agent.aprint_response("What is happening in France?"))

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
2. Install dependencies

   uv pip install -U agno litellm yfinance
   
3. Export your LiteLLM API key

   Mac/Linux

   export LITELLM_API_KEY="your_litellm_api_key_here"
   
4. Run the example

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

   python tool_use.py
   

Full source: cookbook/90_models/litellm/tool_use.py