Skip to main content
Example showing video understanding with the Interactions API. Supports video from URLs and local files.
video_understanding.py
"""
Gemini Interactions - Video Understanding
==========================================

Example showing video understanding with the Interactions API.
Supports video from URLs and local files.

Note: For larger videos, consider uploading via the Files API first.
"""

from agno.agent import Agent
from agno.media import Video
from agno.models.google import GeminiInteractions

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

agent = Agent(
    model=GeminiInteractions(id="gemini-3.5-flash"),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Video from URL ---
    agent.print_response(
        "Describe what happens in this video.",
        videos=[
            Video(
                url="https://download.samplelib.com/mp4/sample-5s.mp4",
                mime_type="video/mp4",
            )
        ],
    )

Run the Example

1

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate
uv venv --python 3.12
.venv\Scripts\activate
2

Install dependencies

uv pip install -U agno google-genai
3

Export your Google API key

export GOOGLE_API_KEY="your_google_api_key_here"
$Env:GOOGLE_API_KEY="your_google_api_key_here"
4

Run the example

Save the code above as video_understanding.py, then run:
python video_understanding.py
Full source: cookbook/90_models/google/gemini_interactions/video_understanding.py