Describe images and answer questions about them with Gemini vision in Python

What you get

A Python script that sends any local image to Gemini 3.8 Flash and prints a caption or the answer to your question about it.

Prerequisites

Python 3 installed
A Gemini API key from Google AI Studio

Steps

Install the Google Gen AI SDK:

Shell

pip install -U google-genai

Set your key as an environment variable (the client picks up GEMINI_API_KEY automatically):

Shell

export GEMINI_API_KEY="YOUR_API_KEY"

Create describe_image.py. It reads the image, sends it inline as base64 together with your question through the Interactions API, and prints the answer:

Python

import base64
import mimetypes
import sys

from google import genai

image_path = sys.argv[1]
question = sys.argv[2] if len(sys.argv) > 2 else "Caption this image."

with open(image_path, 'rb') as f:
    image_bytes = f.read()

mime_type = mimetypes.guess_type(image_path)[0] or "image/jpeg"

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input=[
        {"type": "text", "text": question},
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": mime_type
        }
    ]
)
print(interaction.output_text)

Describe images and answer questions about them with Gemini vision in Python

What you'll need

What you get

Prerequisites

Steps

Test it