Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Nguyen, Minh
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.12948
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909846988652544
author Nguyen, Minh
author_facet Nguyen, Minh
contents Retrieval-Augmented Generation (RAG) frameworks aim to enhance Code Language Models (CLMs) by including another module for retrieving relevant context to construct the input prompt. However, these retrieval modules commonly use semantic search, requiring substantial computational resources for training and hosting these embedded models, making them infeasible to integrate into lightweight applications such as in-IDE AI-based code completion. In this solution paper, we prove that using keyword-search is sufficient to retrieve relevant and useful code context inside large codebases, without the need for extensive GPU resources. The usefulness of code contexts found by our solution is demonstrated through their completion results on the Code Context Competition's benchmark, reaching 0.748 and 0.725 chRF scores on Kotlin and Python tracks, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SpareCodeSearch: Searching for Code Context When You Have No Spare GPU
Nguyen, Minh
Software Engineering
Artificial Intelligence
Retrieval-Augmented Generation (RAG) frameworks aim to enhance Code Language Models (CLMs) by including another module for retrieving relevant context to construct the input prompt. However, these retrieval modules commonly use semantic search, requiring substantial computational resources for training and hosting these embedded models, making them infeasible to integrate into lightweight applications such as in-IDE AI-based code completion. In this solution paper, we prove that using keyword-search is sufficient to retrieve relevant and useful code context inside large codebases, without the need for extensive GPU resources. The usefulness of code contexts found by our solution is demonstrated through their completion results on the Code Context Competition's benchmark, reaching 0.748 and 0.725 chRF scores on Kotlin and Python tracks, respectively.
title SpareCodeSearch: Searching for Code Context When You Have No Spare GPU
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2510.12948