Video Input (Bytes Content)

Code

1import requests
2from kern.agent import Agent
3from kern.media import Video
4from kern.models.google import Gemini
5
6agent = Agent(
7    model=Gemini(id="gemini-2.0-flash-exp"),
8    markdown=True,
9)
10
11url = "https://videos.pexels.com/video-files/5752729/5752729-uhd_2560_1440_30fps.mp4"
12
13# Download the video file from the URL as bytes
14response = requests.get(url)
15video_content = response.content
16
17agent.print_response(
18    "Tell me about this video",
19    videos=[Video(content=video_content)],
20)

Usage

Set up your virtual environment

1uv venv --python 3.12
2source .venv/bin/activate

1uv venv --python 3.12
2.venv\Scripts\activate

Set your API key

1export GOOGLE_API_KEY=xxx

Install dependencies

1uv pip install -U google-genai kern-ai

Run Agent

1python cookbook/11_models/google/gemini/video_input_bytes_content.py