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

# Tool Use

> Use web search tools with Llama 3.3 70B served through the NVIDIA API.

```python tool_use.py theme={null}
"""Run `uv pip install ddgs` to install dependencies."""

import asyncio

from agno.agent import Agent
from agno.models.nvidia import Nvidia
from agno.tools.websearch import WebSearchTools

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

agent = Agent(
    model=Nvidia(id="meta/llama-3.3-70b-instruct"),
    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

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

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

  <Step title="Export your NVIDIA API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export NVIDIA_API_KEY="your_nvidia_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:NVIDIA_API_KEY="your_nvidia_api_key_here"
      ```
    </CodeGroup>
  </Step>

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

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

Full source: [cookbook/90\_models/nvidia/tool\_use.py](https://github.com/agno-agi/agno/blob/main/cookbook/90_models/nvidia/tool_use.py)