beingstrong的博客

论文《Text2SQL is Not Enough: Unifying AI and Databases with TAG》笔记

MAC-SQL出自2023年12月的论文《MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL》它是用基于LLM的multi-agent]来实现text2sql，其由Decomposer、Selector、Refiner三个agent组成。

text2sql论文《[C3: Zero-shot Text-to-SQL with ChatGPT](https://arxiv.org/abs/2307.07306)》和《[A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capability](https://arxiv.org/abs/2303.13547)》思路

PET-SQL出自论文《[PET-SQL: A Prompt-enhanced Two-stage Text-to-SQL Framework with Cross-consistency](https://arxiv.org/abs/2403.09732)》，将基于大模型的Text2SQL分为两个阶段进行。

text2sql(NL2Sql)综述《The Dawn of Natural Language to SQL: Are We Fully Ready?》详细笔记

text2sql方法：RESDSQL和DAIL-SQL思路的详细介绍

基于RAG的SQL生成(text2sql)开源python框架vanna使用简介和原理探索

text2sql方法：NatSQL和DIN-SQL思路介绍