> ## 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.

# Tool Use

> Give a GPT-4o agent web search tools through a LiteLLM proxy.

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

from agno.agent import Agent
from agno.models.litellm import LiteLLMOpenAI
from agno.tools.websearch import WebSearchTools

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

agent = Agent(
    model=LiteLLMOpenAI(id="gpt-5.6-luna"),
    tools=[WebSearchTools()],
    markdown=True,
)
agent.print_response("Whats happening in France?")

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

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

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno "litellm[proxy]" ddgs openai
```

**2. Export your API keys**

```bash Mac/Linux theme={null}
export LITELLM_API_KEY="your_litellm_api_key_here"
export OPENAI_API_KEY="your_openai_api_key_here"
```

```bash Windows theme={null}
$Env:LITELLM_API_KEY="your_litellm_api_key_here"
$Env:OPENAI_API_KEY="your_openai_api_key_here"
```

**3. Start LiteLLM**

Start the local OpenAI-compatible proxy on port 4000:

```bash theme={null}
litellm --model gpt-4o --host 127.0.0.1 --port 4000
```

**4. Run the example**

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

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

Full source: [cookbook/90\_models/litellm\_openai/tool\_use.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/litellm_openai/tool_use.py)


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