Cache Tool Calls

Cache YFinance tool results with cache_results=True to skip repeat API calls.

cache_tool_calls.py

"""
Cache Tool Calls
=============================

Demonstrates cache tool calls.
"""

import asyncio

from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.tools.websearch import WebSearchTools
from agno.tools.yfinance import YFinanceTools

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


agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[WebSearchTools(), YFinanceTools(cache_results=True)],
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    asyncio.run(
        agent.aprint_response(
            "What is the current stock price of AAPL and latest news on 'Apple'?",
            markdown=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 ddgs openai yfinance
   
3. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Run the example

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

   python cache_tool_calls.py
   

Full source: cookbook/91_tools/other/cache_tool_calls.py