Google is integrating its Gemini Pro large language model into Android Studio

Google LLC today rolled out an update to the coding assistant in Android Studio, its tool for building Android apps.

Android Studio is a so-called IDE, or integrated development environment. It’s a kind of word processor where developers can write code for new applications. Android Studio offers other features, including an emulator that lets you run virtual Android devices on a Windows PC and use them to test new code.

Last May, Google added an artificial intelligence coding assistant called Studio Bot to the IDE. It was based on a major language model called PaLM 2 that the search giant announced the same month. Today’s update replaces Studio Bot with Gemini in Android Studio, an improved coding assistant based on a newer AI model.

Six months after the debut of PaLM 2 last year, Google introduced a new flagship line of LLMs. The Gemini series, as it’s called, includes three models with different feature sets and hardware requirements. Android Studio’s upgraded chatbot is based on Gemini Pro, the mid-range model in the series, which is designed to balance response quality and hardware efficiency.

“If you’ve already used Studio Bot in the Canary channel, you’ll still have the same useful and powerful features, but you’ll notice improved response quality compared to earlier versions,” Android Studio Product Manager Sandhya Mohan described in blog post today.

Gemini in Android Studio can answer general Android questions, such as how to integrate an app with the operating system’s location tracking feature. The chatbot can also answer project-specific questions. A developer might, for example, ask for advice on how to remove duplicate records from a dataset that an application uses to run some of its features.

Gemini in Android Studio can also take on more complex tasks. According to Google, the chatbot is capable of rewriting code files in a new programming language and generating entire parts of the app’s interface. Gemini in Android Studio can also write documentation that explains how the newly generated code works.

“Gemini is only available after you log in and enable it,” Mohan explained. “You don’t need to send code context to take advantage of most features. By default, chat replies in Android Studio Gemini are based solely on chat history, and you control whether you want to share additional context for custom replies.”

The chatbot is based on Gemini 1.0 Pro, the LLM that Google introduced last December. Since then, the search giant has detailed a newer iteration of the model called the Gemini 1.5 Pro. It is possible that the latter model will be introduced to Android Studio in a future update given the fact that it has improved coding capabilities.

According to Google, Gemini 1.5 Pro surpassed version 1.0 used by Android Studio in 87% of benchmarks evaluated by its engineers. In one internal test, the search giant gave Gemini 1.5 Pro a query containing more than 100,000 lines of code. He proved more adept at generating explanations and suggesting improvements.

Picture: Google