Context Composing for Full Line Code Completion

Anton Semenkin, Yaroslav Sokolov, Evgeniia Vu
2/14/2024
cs.SEcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Code Completion is one of the most used Integrated Development Environment (IDE) features, which affects the everyday life of a software developer. Modern code completion approaches moved from the composition of several static analysis-based contributors to pipelines that involve neural networks. This change allows the proposal of longer code suggestions while maintaining the relatively short time spent on generation itself. At JetBrains, we put a lot of effort into perfecting the code completion workflow so it can be both helpful and non-distracting for a programmer. We managed to ship the Full Line Code Completion feature to PyCharm Pro IDE and proved its usefulness in A/B testing on hundreds of real Python users. The paper describes our approach to context composing for the Transformer model that is a core of the feature's implementation. In addition to that, we share our next steps to improve the feature and emphasize the importance of several research aspects in the area.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Full Line Code Completion: Bringing AI to Desktop

83% match2024

Challenge on Optimization of Context Collection for Code Completion

83% match2025

A Transformer-Based Approach for Smart Invocation of Automatic Code Completion

83% match1 repo12024

CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models

81% match2025

Language Models for Code Completion: A Practical Evaluation

80% match1 repo132024

Neural Models for Source Code Synthesis and Completion

79% match2024

Cite this paper

@article{semenkin2024context,
  title  = {Context Composing for Full Line Code Completion},
  author = {Anton Semenkin and Yaroslav Sokolov and Evgeniia Vu},
  year   = {2024},
  eprint = {2402.09230},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.09230v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.09230.svg)](https://codeofpaper.com/paper/2402.09230)

Discussion