GrepRAG: An Empirical Study and Optimization of Grep-Like Retrieval for Code Completion

TL;DR

This paper investigates the effectiveness of simple, index-free lexical retrieval methods like ripgrep for repository-level code completion, demonstrating that lightweight approaches can rival complex retrieval systems and proposing improvements to enhance their performance.

Contribution

It introduces GrepRAG, a novel lightweight retrieval framework that enhances lexical retrieval with re-ranking and deduplication, outperforming state-of-the-art methods in code completion tasks.

Findings

Naive GrepRAG achieves comparable performance to complex graph-based baselines.

GrepRAG improves code exact match by 7.04-15.58% over SOTA methods.

Lexical retrieval effectiveness is linked to spatial proximity and lexical precision.

Abstract

Repository-level code completion remains challenging for large language models (LLMs) due to cross-file dependencies and limited context windows. Prior work addresses this challenge using Retrieval-Augmented Generation (RAG) frameworks based on semantic indexing or structure-aware graph analysis, but these approaches incur substantial computational overhead for index construction and maintenance. Motivated by common developer workflows that rely on lightweight search utilities (e.g., ripgrep), we revisit a fundamental yet underexplored question: how far can simple, index-free lexical retrieval support repository-level code completion before more complex retrieval mechanisms become necessary? To answer this question, we systematically investigate lightweight, index-free, intent-aware lexical retrieval through extensive empirical analysis. We first introduce Naive GrepRAG, a baseline framework in which LLMs autonomously generate ripgrep commands to retrieve relevant context. Despite its simplicity, Naive GrepRAG achieves performance comparable to sophisticated graph-based baselines. Further analysis shows that its effectiveness stems from retrieving lexically precise code fragments that are spatially closer to the completion site. We also identify key limitations of lexical retrieval, including sensitivity to noisy matches from high-frequency ambiguous keywords and context fragmentation caused by rigid truncation boundaries. To address these issues, we propose GrepRAG, which augments lexical retrieval with a lightweight post-processing pipeline featuring identifier-weighted re-ranking and structure-aware deduplication. Extensive evaluation on CrossCodeEval and RepoEval-Updated demonstrates that GrepRAG consistently outperforms state-of-the-art (SOTA) methods, achieving 7.04-15.58 percent relative improvement in code exact match (EM) over the best baseline on CrossCodeEval.