# SpareCodeSearch: Searching for Code Context When You Have No Spare GPU

arXiv: https://arxiv.org/abs/2510.12948 · HTML: https://mlsanity.com/paper/2510.12948/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 3 of its 13 references that are in the map.
- First posted on arXiv 14 Oct 2025.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)

## Builds on (most cited first, 3 of 3)

- [On the Transferability of Pre-trained Language Models for Low-Resource Programming Languages](https://mlsanity.com/paper/2204.09653/) (2022)
- [The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation](https://mlsanity.com/paper/2305.06156/) (2023)
- [Fixing 7,400 Bugs for 1: Cheap Crash-Site Program Repair](https://mlsanity.com/paper/2505.13103/) (2025)

## Abstract (arXiv)

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.