Skip to main content

​
Code

cookbook/models/vllm/async_tool_use.py
"""Run `pip install duckduckgo-search` to install dependencies."""

import asyncio

from agno.agent import Agent
from agno.models.vllm import vLLM
from agno.tools.duckduckgo import DuckDuckGoTools

agent = Agent(
    model=vLLM(id="Qwen/Qwen2.5-7B-Instruct", top_k=20, enable_thinking=False),
    tools=[DuckDuckGoTools()],
    show_tool_calls=True,
    markdown=True,
)
asyncio.run(agent.aprint_response("Whats happening in France?", stream=True))

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
2

Install Libraries

pip install -U agno openai vllm duckduckgo-search
3

Start vLLM server

vllm serve Qwen/Qwen2.5-7B-Instruct \
    --enable-auto-tool-choice \
    --tool-call-parser hermes \
    --dtype float16 \
    --max-model-len 8192 \
    --gpu-memory-utilization 0.9
4

Run Agent

python cookbook/models/vllm/async_tool_use.py