Image Agent

Code

1from kern.agent import Agent
2from kern.media import Image
3from kern.models.google import Gemini
4from kern.tools.hackernews import HackerNewsTools
5
6agent = Agent(
7    model=Gemini(id="gemini-2.0-flash-exp"),
8    tools=[HackerNewsTools()],
9    markdown=True,
10)
11
12agent.print_response(
13    "Tell me about this image and give me the latest news about it.",
14    images=[
15        Image(
16            url="https://upload.wikimedia.org/wikipedia/commons/b/bf/Krakow_-_Kosciol_Mariacki.jpg"
17        ),
18    ],
19    stream=True,
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/image_input.py