Google AI Python SDK for the Gemini API

The Google AI Python SDK is the easiest way for Python developers to build with the Gemini API. The Gemini API gives you access to Gemini models created by Google DeepMind. Gemini models are built from the ground up to be multimodal, so you can reason seamlessly across text, images, and code.

Get started with the Gemini API

Go to Google AI Studio.
Login with your Google account.
Create an API key.
Try a Python SDK quickstart in the Gemini API Cookbook.
For detailed instructions, try the Python SDK tutorial on ai.google.dev.

Usage example

See the Gemini API Cookbook or ai.google.dev for complete code.

Install from PyPI.

pip install -U google-generativeai

Import the SDK and configure your API key.

import google.generativeai as genai
import os

genai.configure(api_key=os.environ["GOOGLE_API_KEY"])

Create a model and run a prompt.

model = genai.GenerativeModel('gemini-1.0-pro-latest')
response = model.generate_content("The opposite of hot is")
print(response.text)

Documentation

See the Gemini API Cookbook or ai.google.dev for complete documentation.

Contributing

See Contributing for more information on contributing to the Google AI Python SDK.

License