Code
cookbook/11_models/vllm/async_tool_use.py
Usage
1
Set up your virtual environment
2
Install Libraries
3
Start vLLM server
4
Run Agent
"""Run `uv pip install` to install dependencies."""
import asyncio
from agno.agent import Agent
from agno.models.vllm import VLLM
from agno.tools.hackernews import HackerNewsTools
agent = Agent(
model=VLLM(id="Qwen/Qwen2.5-7B-Instruct", top_k=20, enable_thinking=False),
tools=[HackerNewsTools()],
markdown=True,
)
asyncio.run(agent.aprint_response("Whats happening in France?", stream=True))
Set up your virtual environment
uv venv --python 3.12
source .venv/bin/activate
Install Libraries
uv pip install -U agno openai vllm
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
Run Agent
python cookbook/11_models/vllm/async_tool_use.py
Was this page helpful?