Skip to main content
Example showing image understanding with the Interactions API. Supports images from URLs, local files, and raw bytes.
image_understanding.py
"""
Gemini Interactions - Image Understanding
==========================================

Example showing image understanding with the Interactions API.
Supports images from URLs, local files, and raw bytes.
"""

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

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

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

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    # --- Image from URL ---
    agent.print_response(
        "What do you see in this image? Describe it in detail.",
        images=[Image(url="https://picsum.photos/id/237/400/300")],
    )

​
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 image_understanding.py, then run:
python image_understanding.py
Full source: cookbook/90_models/google/gemini_interactions/image_understanding.py