> ## 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.

# 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

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

**1. Install dependencies**

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

**2. Export your OpenAI API key**

```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"
```

**3. Run the example**

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

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

Full source: [cookbook/91\_tools/duckdb\_tools.py](https://github.com/agno-agi/agno/blob/v3.0.4/cookbook/91_tools/duckdb_tools.py)


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