Google Image Input

Pass an image URL to a Gemini agent and fetch related news with web search.

Google has shut down gemini-2.0-flash-exp. Replace it with gemini-3.5-flash before running. See Gemini 2.0 Flash model status.

image_input.py

"""
Google Image Input
==================

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

from agno.agent import Agent
from agno.media import Image
from agno.models.google import Gemini
from agno.tools.websearch import WebSearchTools

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

agent = Agent(
    model=Gemini(id="gemini-2.0-flash-exp"),
    tools=[WebSearchTools()],
    markdown=True,
)

agent.print_response(
    "Tell me about this image and give me the latest news about it.",
    images=[
        Image(
            url="https://upload.wikimedia.org/wikipedia/commons/b/bf/Krakow_-_Kosciol_Mariacki.jpg"
        ),
    ],
)

# ---------------------------------------------------------------------------
# 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
   

   uv venv --python 3.12
   .venv\Scripts\activate
   
2. Install dependencies

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

   Mac/Linux

   export GOOGLE_API_KEY="your_google_api_key_here"
   

   $Env:GOOGLE_API_KEY="your_google_api_key_here"
   
4. Update the Gemini model

   Replace gemini-2.0-flash-exp with gemini-3.5-flash in the saved file.

5. Run the example

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

   python image_input.py
   

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