vLLM Tool Use

tool_use.py

"""Build a Web Search Agent using xAI."""

import asyncio

from agno.agent import Agent
from agno.models.vllm import VLLM
from agno.tools.websearch import WebSearchTools

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

agent = Agent(
    model=VLLM(
        id="NousResearch/Nous-Hermes-2-Mistral-7B-DPO", top_k=20, enable_thinking=False
    ),
    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)

    # --- Async + Streaming ---
    asyncio.run(agent.aprint_response("Whats happening in France?", stream=True))

Run the Example

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

uv venv --python 3.12
.venv\Scripts\activate

Install dependencies

uv pip install -U agno ddgs openai

Export your vLLM API key

export VLLM_API_KEY="your_vllm_api_key_here"

$Env:VLLM_API_KEY="your_vllm_api_key_here"

Install vLLM

Install vLLM in the environment that will serve the model:

uv pip install -U vllm

Start vLLM

Serve the model used by this example with automatic tool calling enabled:

vllm serve NousResearch/Nous-Hermes-2-Mistral-7B-DPO --enable-auto-tool-choice --tool-call-parser hermes

Run the example

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

python tool_use.py

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

Examples

Primitives

Context

Models

Tools

More

vLLM Tool Use

Run the Example

​Run the Example

Run the Example