googleapis/python-genai

Google Gen AI Python SDK

What it is – A first‑party Python client library that lets you call Google’s Gemini generative‑AI models (both the public Gemini Developer API and the Gemini Enterprise Agent Platform). It wraps the REST endpoints in a convenient, typed interface and handles authentication, HTTP transport, and response parsing.

Key capabilities

• Create a genai.Client with either an API key (public Gemini) or enterprise credentials (project, location).
• Call client.models.generate_content to get text, images, or video from Gemini models such as gemini-3.5-flash or gemini-2.5-flash.
• Provide inputs as plain strings, dictionaries, or the richer google.genai.types Pydantic models (e.g. Part.from_text, Part.from_uri, Part.from_function_call).
• Configure generation with GenerateContentConfig (temperature, top‑p/k, max tokens, safety settings, system instructions, response modalities, etc.).
• Use automatic function calling: pass Python callables as tools and the model can invoke them, or disable it to receive explicit function‑call objects.
• Support for streaming, async calls (via client.aio), and a fast aiohttp transport option.
• Built‑in handling for proxies, custom base URLs, and API version selection (v1, v1alpha).
• Context‑manager support for automatic resource cleanup, and explicit close()/aclose() methods.
• Helper utilities for listing models, uploading files, and setting safety settings.

Typical usage

from google import genai
from google.genai import types

client = genai.Client(api_key="YOUR_GEMINI_API_KEY")
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents=types.Part.from_text("Why is the sky blue?"),
    config=types.GenerateContentConfig(temperature=0, top_p=0.95),
)
print(response.text)

Why it matters – It abstracts away the low‑level HTTP details of Google’s Gemini APIs, provides type‑safe request building, and integrates advanced features like function calling and safety controls, making it easier for Python developers to embed state‑of‑the‑art generative AI into applications, services, or research notebooks.

Documentation & install

• Docs: https://googleapis.github.io/python-genai/
• Install: pip install google-genai (or uv pip install google-genai)