Tool Use

Give a local LlamaCpp model web search tools and stream the tool-assisted answer.

tool_use.py

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

from agno.agent import Agent
from agno.models.llama_cpp import LlamaCpp
from agno.tools.websearch import WebSearchTools

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

agent = Agent(
    model=LlamaCpp(id="ggml-org/gpt-oss-20b-GGUF"),
    tools=[WebSearchTools()],
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    agent.print_response("Whats happening in France?")

    # --- Sync + Streaming ---
    agent.print_response("Whats happening in France?", stream=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
   
3. Run the example

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

   python tool_use.py
   

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