CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale

TL;DR

CSR-RAG is a hybrid retrieval system designed for enterprise-scale Text-to-SQL tasks, achieving high accuracy and low latency, suitable for large databases and LLM integration.

Contribution

The paper introduces CSR-RAG, a novel hybrid retrieval approach that enhances efficiency and accuracy for enterprise-scale Text-to-SQL translation.

Findings

Achieves up to 40% precision and 80% recall on enterprise benchmarks.

Maintains a low average query latency of 30ms on commodity hardware.

Suitable for integration with modern LLM-based enterprise systems.

Abstract

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.