提出高效文本转SQL的检索系统，适配企业级数据库场景。
CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale
- 融合上下文、结构、关系三类检索，提升准确率。
- 精度达40%，召回超80%，查询延迟仅30ms。
- 适合需要快速响应的企业级大模型应用。
自然语言转SQL是长期存在的难题，近年受大语言模型（LLMs）推动取得进展。虽然多数学术基准将模式描述作为自然语言输入的一部分，但企业级应用通常需在生成SQL前先进行表检索。为此，我们提出一种新型混合检索增强生成（RAG）系统——上下文、结构、关系检索（CSR-RAG），以实现企业级数据库中计算高效且足够精确的检索。通过大量企业级基准测试，我们证明了CSR-RAG在商用数据中心硬件上平均查询生成延迟仅为30ms，精度最高达40%，召回率超过80%，适用于现代基于LLM的企业级系统。
原文摘要 · Abstract (English)
Natural language to SQL translation (Text-to-SQL) is one of the long-standing problems that has recently benefited from advances in Large Language Models (LLMs). While most academic Text-to-SQL benchmarks request schema description as a part of natural language input, enterprise-scale applications often require table retrieval before SQL query generation. To address this need, we propose a novel hybrid Retrieval Augmented Generation (RAG) system consisting of contextual, structural, and relational retrieval (CSR-RAG) to achieve computationally efficient yet sufficiently accurate retrieval for enterprise-scale databases. Through extensive enterprise benchmarks, we demonstrate that CSR-RAG achieves up to 40% precision and over 80% recall while incurring a negligible average query generation latency of only 30ms on commodity data center hardware, which makes it appropriate for modern LLM-based enterprise-scale systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。