Configure Gemini model parameters

Generates text from an image using the Gemini model and returns the generated text. This example demonstrates how to set model configuration parameters.

Code sample


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 base64
import vertexai

from vertexai.generative_models import GenerationConfig, GenerativeModel, Part

# TODO(developer): Update and un-comment below line
# project_id = "PROJECT_ID"

vertexai.init(project=project_id, location="us-central1")

model = GenerativeModel(model_name="gemini-1.0-pro-vision-001")

# Load example image from local storage
encoded_image = base64.b64encode(open("scones.jpg", "rb").read()).decode("utf-8")
image_content = Part.from_data(
    data=base64.b64decode(encoded_image), mime_type="image/jpeg"

# Generation Config
config = GenerationConfig(
    max_output_tokens=2048, temperature=0.4, top_p=1, top_k=32

# Generate text
response = model.generate_content(
    [image_content, "what is this image?"], generation_config=config

What's next

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