Video Input (Bytes Content)

Pass raw video bytes to a Gemini agent with Video(content=...).

Code

import requests
from agno.agent import Agent
from agno.media import Video
from agno.models.google import Gemini

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

url = "https://videos.pexels.com/video-files/5752729/5752729-uhd_2560_1440_30fps.mp4"

# Download the video file from the URL as bytes
response = requests.get(url)
video_content = response.content

agent.print_response(
    "Tell me about this video",
    videos=[Video(content=video_content)],
)

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Set your API key

export GOOGLE_API_KEY=xxx

Install dependencies

uv pip install -U google-genai requests agno

Run Agent

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

python video_input_bytes_content.py