> ## 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

> Tool use example using Ollama with the OpenAI Responses API.

```python tool_use.py theme={null}
"""Tool use example using Ollama with the OpenAI Responses API.

This demonstrates using tools with Ollama's Responses API endpoint.

Requirements:
- Ollama v0.13.3 or later running locally
- Run: ollama pull llama3.1:8b
"""

from agno.agent import Agent
from agno.models.ollama import OllamaResponses
from agno.tools.duckduckgo import DuckDuckGoTools

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

agent = Agent(
    model=OllamaResponses(id="gpt-oss:20b"),
    tools=[DuckDuckGoTools()],
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Sync ---
    agent.print_response("What is the latest news about AI?")

    # --- Sync + Streaming ---
    agent.print_response("What is the latest news about AI?", stream=True)
```

## Run the Example

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

**1. Install dependencies**

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

**2. Prepare Ollama**

Install and start Ollama, then pull the model used by this example:

```bash theme={null}
ollama pull gpt-oss:20b
```

**3. 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/ollama/responses/tool\_use.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/90_models/ollama/responses/tool_use.py)


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