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

# Agent with Tools

> Give a DeepInfra agent web search with WebSearchTools.

## Code

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

from agno.agent import Agent  # noqa
from agno.models.deepinfra import DeepInfra  # noqa
from agno.tools.websearch import WebSearchTools  # noqa

agent = Agent(
    model=DeepInfra(id="meta-llama/Llama-2-70b-chat-hf"),
    tools=[WebSearchTools()],
    markdown=True,
)

if __name__ == "__main__":
    # --- Sync + Streaming ---
    agent.print_response("Whats happening in France?", stream=True)

    # --- Async + Streaming ---
    asyncio.run(agent.aprint_response("What's the latest news about AI?", stream=True))
```

## Usage

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

  <Step title="Set your API key">
    ```bash theme={null}
    export DEEPINFRA_API_KEY=xxx
    ```
  </Step>

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U openai ddgs agno
    ```
  </Step>

  <Step title="Run Agent">
    Save the code above as `tool_use.py`, then run:

    ```bash theme={null}
    python tool_use.py
    ```
  </Step>
</Steps>