Google CSV Input

Analyze an IMDB movie dataset by attaching a CSV file to a Gemini agent.

csv_input.py

"""
Google Csv Input
================

Cookbook example for `google/gemini/csv_input.py`.
"""

from pathlib import Path

from agno.agent import Agent
from agno.media import File
from agno.models.google import Gemini
from agno.utils.media import download_file

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

csv_path = Path(__file__).parent.joinpath("IMDB-Movie-Data.csv")

download_file(
    "https://agno-public.s3.amazonaws.com/demo_data/IMDB-Movie-Data.csv", str(csv_path)
)

agent = Agent(
    model=Gemini(id="gemini-2.5-flash"),
    markdown=True,
)

agent.print_response(
    "Analyze the top 10 highest-grossing movies in this dataset. Which genres perform best at the box office?",
    files=[
        File(
            filepath=csv_path,
            mime_type="text/csv",
        ),
    ],
)

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

if __name__ == "__main__":
    pass

Run the Example

1. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
2. Install dependencies

   uv pip install -U agno google-genai
   
3. Export your Google API key

   Mac/Linux

   export GOOGLE_API_KEY="your_google_api_key_here"
   
4. Run the example

   Save the code above as csv_input.py, then run:

   python csv_input.py
   

Full source: cookbook/90_models/google/gemini/csv_input.py