Yandex Code Assistant overview
Note
The service is at the Preview stage.
You can request access to Code Assistant on this page or by contacting your account manager.
Code Assistant is an AI-driven developer assistant based on large language models (LLM)s. With Code Assistant, you can optimize the code writing process and increase your performance. The smart autocompletion mode enables Code Assistant to analyze the code context and come up with the most relevant suggestions for functions, cycles, conditions, and more.
The Code Assistant plugin is now available for Visual Studio Code and JetBrains IDE versions 2024.3, 2024.2, and 2024.1.
Note
To work with Code Assistant, you will need continuous internet access.
The code analysis is running using the Yandex Cloud computing resources, which means Code Assistant does not generate any load against the user workstations.
LLMs that are used in Code Assistant have been fine-tuned based on the open-source code corpus. The quality and number of auto-completion prompts depends on the amount and diversity of open-source code in a particular language.
The smart autocompletion mode explicitly supports code autocompletion for the following programming languages and frameworks:
- C++
- Go
- Java
- JavaScript/TypeScript
- Kotlin
- Python
- Scala
- SQL
- Swift
Autocompletion may also work for other languages. For languages that are less represented in public repositories, the number and quality of autocompletion prompts will be lower.
Code Assistant analyzes your code context and provides the following types of suggestions:
- Automatic.
- User-triggered (Ctrl + Space). In Visual Studio Code, you can also use Ctrl + Enter.
Code Assistant supports the following types of suggestions:
- Inline completion: Provides suggestions as you type. Works for code, texts, and documents.
- Full-function completion: Provides autocompletion for entire functions or methods.