> ## 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.

# DuckDB Tools

> Query a remote IMDB movie CSV with SQL using DuckDbTools to compute average ratings.

```python duckdb_tools.py theme={null}
"""
Duckdb Tools
=============================

Demonstrates duckdb tools.
"""

from agno.agent import Agent
from agno.tools.duckdb import DuckDbTools

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


agent = Agent(
    tools=[DuckDbTools()],
    instructions="Use this file for Movies data: https://agno-public.s3.amazonaws.com/demo_data/IMDB-Movie-Data.csv",
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        "What is the average rating of movies?", markdown=True, stream=False
    )
```

## Run the Example

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

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

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

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

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

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

Full source: [cookbook/91\_tools/duckdb\_tools.py](https://github.com/agno-agi/agno/blob/main/cookbook/91_tools/duckdb_tools.py)