Describe an image

This code sample shows how to use Gemini to generate text descriptions for an image.

Code sample

Python

Before trying this sample, follow the Python setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Python API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import vertexai
from vertexai.generative_models import GenerativeModel, Part

# TODO (developer): update project id
vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

contents = [
    # Text prompt
    "Describe this image.",
    # Example image of a Jack Russell Terrier puppy from Wikipedia.
    Part.from_uri(
        "https://upload.wikimedia.org/wikipedia/commons/1/1d/Szczenie_Jack_Russell_Terrier.jpg",
        "image/jpeg",
    ),
]

response = model.generate_content(contents)
print(response.text)
# Example response:
#     'Here is a description of the image:'
#     'Close-up view of a young Jack Russell Terrier puppy sitting in short grass ...'

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.