Python Client for Generative Language API¶
Generative Language API: The Gemini API allows developers to build generative AI applications using Gemini models. Gemini is our most capable model, built from the ground up to be multimodal. It can generalize and seamlessly understand, operate across, and combine different types of information including language, images, audio, video, and code. You can use the Gemini API for use cases like reasoning across text and images, content generation, dialogue agents, summarization and classification systems, and more.
Quick Start¶
In order to use this library, you first need to go through the following steps:
Installation¶
Install this library in a virtual environment using venv. venv is a tool that creates isolated Python environments. These isolated environments can have separate versions of Python packages, which allows you to isolate one project’s dependencies from the dependencies of other projects.
With venv, it’s possible to install this library without needing system install permissions, and without clashing with the installed system dependencies.
Code samples and snippets¶
Code samples and snippets live in the samples/ folder.
Supported Python Versions¶
Our client libraries are compatible with all current active and maintenance versions of Python.
Python >= 3.7
Unsupported Python Versions¶
Python <= 3.6
If you are using an end-of-life version of Python, we recommend that you update as soon as possible to an actively supported version.
Mac/Linux¶
python3 -m venv <your-env>
source <your-env>/bin/activate
pip install google-ai-generativelanguage
Windows¶
py -m venv <your-env>
.\<your-env>\Scripts\activate
pip install google-ai-generativelanguage
Next Steps¶
Read the Client Library Documentation for Generative Language API to see other available methods on the client.
Read the Generative Language API Product documentation to learn more about the product and see How-to Guides.
View this README to see the full list of Cloud APIs that we cover.
Note
Because this client uses grpc
library, it is safe to
share instances across threads. In multiprocessing scenarios, the best
practice is to create client instances after the invocation of
os.fork()
by multiprocessing.pool.Pool
or
multiprocessing.Process
.
This package includes clients for multiple versions of Generative Language API.
By default, you will get version generativelanguage_v1beta
.
API Reference¶
API Reference¶
API Reference¶
API Reference¶
Changelog¶
For a list of all google-ai-generativelanguage
releases:
- Changelog
- 0.6.12 (2024-10-31)
- 0.6.11 (2024-10-24)
- 0.6.10 (2024-09-23)
- 0.6.9 (2024-08-19)
- 0.6.8 (2024-07-30)
- 0.6.7 (2024-07-08)
- 0.6.6 (2024-06-26)
- 0.6.5 (2024-06-11)
- 0.6.4 (2024-05-16)
- 0.6.3 (2024-05-07)
- 0.6.2 (2024-04-15)
- 0.6.1 (2024-04-03)
- 0.6.0 (2024-03-22)
- 0.5.4 (2024-03-05)
- 0.5.3 (2024-02-22)
- 0.5.2 (2024-02-06)
- 0.5.1 (2024-02-01)
- 0.5.0 (2024-01-24)
- 0.4.1 (2024-01-22)
- 0.4.0 (2023-12-09)
- 0.3.5 (2023-12-07)
- 0.3.4 (2023-09-30)
- 0.3.3 (2023-09-21)
- 0.3.2 (2023-09-20)
- 0.3.1 (2023-07-05)
- 0.3.0 (2023-06-29)
- 0.2.1 (2023-06-03)
- 0.2.0 (2023-05-05)
- 0.1.0 (2023-05-02)
- Changelog