GitLab’s AI-assisted Code Suggestions is a tool designed to enhance coding productivity and accelerate software development. It provides generative AI-powered suggestions for code while developers are working, allowing them to complete entire lines of code with a single keystroke, quickly start functions, fill in boilerplate code, and generate tests, among other tasks.
The tool prioritizes data privacy and security, as it keeps proprietary source code protected within GitLab’s enterprise cloud infrastructure and does not use code as training data.
Source code inference against the Code Suggestions model is not retained. Code Suggestions utilizes open-source pre-trained models that are continuously fine-tuned with a customized open-source dataset.
This enables support for multi-language coding and additional use cases. Currently, it supports 13 programming languages including C/C++, C#, Go, Java, JavaScript, Python, PHP, Ruby, Rust, Scala, Kotlin, and TypeScript.GitLab has future plans to expand the tool’s capabilities.
They are working on providing Code Suggestions for self-managed instances through a secure connection to GitLab.com. Additionally, they aim to improve the user experience by offering support for additional IDEs such as JetBrains IntelliJ-based IDEs and Visual Studio.
They also plan to enhance how suggestions are presented and accepted within IDEs, giving developers more control over the feature.Overall, GitLab’s AI-assisted Code Suggestions aims to empower developers by providing intelligent code suggestions, optimizing coding efficiency, and ensuring data privacy and security.