Full Line Code Completion: Bringing AI to Desktop

TL;DR

This paper presents a fully local, syntactically correct multi-token code completion system for JetBrains IDEs, enhancing user experience by being fast, secure, and efficient on end-user devices.

Contribution

It introduces a novel offline code completion engine that operates entirely on the user's device, balancing performance, security, and resource constraints.

Findings

Increases Python code production by 1.3 times with the tool

Operates fully locally, ensuring data privacy and security

Achieved efficient time and memory usage in implementation

Abstract

In recent years, several industrial solutions for the problem of multi-token code completion appeared, each making a great advance in the area but mostly focusing on cloud-based runtime and avoiding working on the end user's device. In this work, we describe our approach for building a multi-token code completion feature for the JetBrains' IntelliJ Platform, which we call Full Line Code Completion. The feature suggests only syntactically correct code and works fully locally, i.e., data querying and the generation of suggestions happens on the end user's machine. We share important time and memory-consumption restrictions, as well as design principles that a code completion engine should satisfy. Working entirely on the end user's device, our code completion engine enriches user experience while being not only fast and compact but also secure. We share a number of useful techniques to meet the stated development constraints and also describe offline and online evaluation pipelines that allowed us to make better decisions. Our online evaluation shows that the usage of the tool leads to 1.3 times more Python code in the IDE being produced by code completion. The described solution was initially started with a help of researchers and was then bundled into all JetBrains IDEs where it is now used by millions of users. Thus, we believe that this work is useful for bridging academia and industry, providing researchers with the knowledge of what happens when complex research-based solutions are integrated into real products.