GenRewrite: Query Rewriting via Large Language Models

TL;DR

GenRewrite leverages large language models and novel techniques to improve query rewriting, outperforming traditional and baseline methods on standard benchmarks by reducing errors and manual effort.

Contribution

It introduces a holistic LLM-based query rewriting system with Natural Language Rewrite Rules and a counterexample-guided correction method, advancing beyond traditional rule-based and synthesis approaches.

Findings

GenRewrite outperforms all baselines on TPC-DS and JOB benchmarks.

It improves 25 queries at >=2x speedup on TPC-DS, 1.35x more than LLM baselines.

The system reduces errors and manual effort in query rewriting.

Abstract

Query rewriting is an effective technique for refining poorly written queries before they reach the query optimizer. However, manual rewriting is not scalable, as it is prone to errors and requires deep expertise. Traditional query rewriting algorithms fall short too: rule-based approaches fail to generalize to new query patterns, while synthesis-based methods struggle with complex queries. Fortunately, Large Language Models (LLMs) already possess broad knowledge and advanced reasoning capabilities, making them a promising solution for tackling these longstanding challenges. In this paper, we present GenRewrite, the first holistic system that leverages LLMs for query rewriting beyond traditional rules. We introduce the notion of Natural Language Rewrite Rules (NLR2s), which serve as hints for the LLM while also a means of knowledge transfer from rewriting one query to another, allowing GenRewrite to become smarter and more effective over time. We present a novel counterexample-guided technique that iteratively corrects the syntactic and semantic errors in the rewritten query, significantly reducing the LLM costs and the manual effort required for verification. Across the standard TPC-DS and JOB benchmarks and their SQLStorm-generated variants, GenRewrite consistently optimizes more queries at every speedup threshold than all baselines. At the >=2x threshold on TPC-DS, GenRewrite improves 25 queries-1.35x more than LLM-driven baselines and 2.6x more than LLM-enhanced rule-based baselines-and the gap widens further on TPC-DS (SQLStorm); on JOB and its SQLStorm variant, where queries are simpler, absolute gains are smaller but GenRewrite still leads by a notable margin.