CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 13395 > Article
Open Access Paper
12 November 2024 FATO-SQL: a comprehensive framework for high-performance Text-to-SQL task
Yongnan Chen, Shijia Gu, Zixiang He
Author Affiliations +
Proceedings Volume 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) ; 133953A (2024) https://doi.org/10.1117/12.3049621
Event: International Conference on Optics, Electronics, and Communication Engineering, 2024, Wuhan, China
Abstract
Text-to-SQL tasks aim to bridge the gap between natural language questions and SQL queries, enabling efficient interaction with databases without the need for expertise in SQL coding. In this paper, we introduce FATO-SQL, a novel Large Language Model (LLM)-based framework designed for medium-scale LLMs to generate complex SQL queries. FATO-SQL leverages the Retrieval-Augmented Generation (RAG), prompting engineering, and two rounds of LLM calls for SQL generation and diverse response generation. We implemented FATO-SQL using production data from the petrochemical industry, testing it with multiple tables joins and multi-level nested SQL queries. Results show that FATO-SQL achieves an overall accuracy of 94% on 40 testing questions. The FATO-SQL framework demonstrates promising potential for practical industrial applications, highlighting its efficacy and adaptability in real-world scenarios.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Yongnan Chen, Shijia Gu, and Zixiang He "FATO-SQL: a comprehensive framework for high-performance Text-to-SQL task", Proc. SPIE 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) , 133953A (12 November 2024); https://doi.org/10.1117/12.3049621
PROCEEDINGS
 8 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Databases
Aliasing
Industry
Vacuum
Data modeling
Industrial applications
Neodymium
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top