> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Async Agent with Tools

> Run a vLLM agent with WebSearchTools asynchronously.

## Code

```python tool_use.py theme={null}
import asyncio

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

agent = Agent(
    model=VLLM(
        id="NousResearch/Nous-Hermes-2-Mistral-7B-DPO", top_k=20, enable_thinking=False
    ),
    tools=[WebSearchTools()],
    markdown=True,
)
asyncio.run(agent.aprint_response("Whats happening in France?", stream=True))
```

## Usage

<Snippet file="create-venv-step.mdx" />

**1. Install Libraries**

```bash theme={null}
uv pip install -U agno ddgs openai vllm
```

**2. Start vLLM server**

```bash theme={null}
vllm serve NousResearch/Nous-Hermes-2-Mistral-7B-DPO \
    --enable-auto-tool-choice \
    --tool-call-parser hermes \
    --dtype float16 \
    --max-model-len 8192 \
    --gpu-memory-utilization 0.9
```

**3. Set your API key**

```bash theme={null}
export VLLM_API_KEY=xxx
```

**4. Run Agent**

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

```bash theme={null}
python tool_use.py
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.