Home >Technology peripherals >AI >Google releases Gemini Pro, an AI SDK that helps Android applications integrate high-performance models

Google releases Gemini Pro, an AI SDK that helps Android applications integrate high-performance models

PHPz
PHPzforward
2023-12-30 20:27:58780browse

谷歌推出 Google AI SDK,简化在安卓应用中集成高性能模型 Gemini Pro

Google recently launched a new Google AI SDK designed to simplify the integration of its high-performance Gemini Pro model into Android apps. With this SDK, developers no longer need to build and manage their own backend infrastructure

According to Google, Gemini Pro is one of the most powerful models that can be used to process a variety of text and images reasoning tasks. Gemini Pro runs in Google data centers and is accessible through the Gemini API. Google says the easiest way to use Gemini is through Google AI Studio, a web-based tool that enables prototyping and running prompts in the browser. If the results are satisfactory, developers can export the model as code and run it on the backend using a programming language of their choice, such as Python

谷歌推出 Google AI SDK,简化在安卓应用中集成高性能模型 Gemini Pro

Google provides for Android apps Google AI client SDK for Android is installed, which encapsulates the Gemini REST API into a Kotlin native API. By using this SDK, developers can avoid interacting directly with the REST API and implement server-side services in Android applications to access Gemini models

Gemini provides a multi-modal model (gemini-pro -vision), in addition to plain text models, it can accept text and images as input and generate corresponding text output. In addition, Gemini also supports streaming, making interactions faster

In order to further simplify the developer's workflow, the latest Android Studio preview version launches a new project template, which will guide developers to follow Gemini Steps required for Pro development

According to this site’s understanding, in addition to providing Gemini Pro, Google has also launched a smaller model, Gemini Nano. This model can run on the device, the data does not need to leave the device, and can be used even when there is no network. Gemini Nano is available on select devices through AICore, a new system service in Android 14 designed to simplify integrating artificial intelligence into Android apps. It is responsible for model management, runtime, security and other aspects

The above is the detailed content of Google releases Gemini Pro, an AI SDK that helps Android applications integrate high-performance models. For more information, please follow other related articles on the PHP Chinese website!

Statement:
This article is reproduced at:51cto.com. If there is any infringement, please contact admin@php.cn delete