Contextual Augmented Multi-Model Programming (CAMP): A Hybrid Local-Cloud Copilot Framework

TL;DR

CAMP is a hybrid framework that enhances cloud-based LLMs with local retrieval capabilities to improve AI-assisted programming in sandboxed environments like Xcode.

Contribution

The paper introduces CAMP, a novel multi-model framework integrating local retrieval-augmented generation with cloud LLMs for improved local IDE support.

Findings

Enhanced code quality in generated outputs

Increased user adoption in local development environments

Successful integration of RAG in Xcode Copilot

Abstract

The advancements in cloud-based Large Languages Models (LLMs) have revolutionized AI-assisted programming. However, their integration into certain local development environments like ones within the Apple software ecosystem (e.g., iOS apps, macOS) remains challenging due to computational demands and sandboxed constraints. This paper presents CAMP, a multi-model AI-assisted programming framework that consists of a local model that employs Retrieval-Augmented Generation (RAG) to retrieve contextual information from the codebase to facilitate context-aware prompt construction thus optimizing the performance of the cloud model, empowering LLMs' capabilities in local Integrated Development Environments (IDEs). The methodology is actualized in Copilot for Xcode, an AI-assisted programming tool crafted for Xcode that employs the RAG module to address software constraints and enables diverse generative programming tasks, including automatic code completion, documentation, error detection, and intelligent user-agent interaction. The results from objective experiments on generated code quality and subjective experiments on user adoption collectively demonstrate the pilot success of the proposed system and mark its significant contributions to the realm of AI-assisted programming.