Tool Use

Give a GPT-4o agent web search tools through a LiteLLM proxy.

tool_use.py

"""Run `uv pip install ddgs` to install dependencies."""

from agno.agent import Agent
from agno.models.litellm import LiteLLMOpenAI
from agno.tools.websearch import WebSearchTools

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

agent = Agent(
    model=LiteLLMOpenAI(id="gpt-4o"),
    tools=[WebSearchTools()],
    markdown=True,
)
agent.print_response("Whats happening in France?")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass

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 "litellm[proxy]" ddgs openai
   
3. Export your API keys

   Mac/Linux

   export LITELLM_API_KEY="your_litellm_api_key_here"
   export OPENAI_API_KEY="your_openai_api_key_here"
   

   $Env:LITELLM_API_KEY="your_litellm_api_key_here"
   $Env:OPENAI_API_KEY="your_openai_api_key_here"
   
4. Start LiteLLM

   Start the local OpenAI-compatible proxy on port 4000:

   litellm --model gpt-4o --host 127.0.0.1 --port 4000
   
5. Run the example

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

   python tool_use.py
   

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