text2sql

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

This is a continuously updated handbook for readers to easily track the latest Text-to-SQL techniques in the literature and provide practical guidance for researchers and practitioners. If we missed any interesting work, feel free to contact us.

Chat2Graph: Graph Native Agentic System.

基于python和llm大模型开发的数据处理和任务调度系统。 支持数据源管理，数据模型管理，数据集成，数据查询API接口，低代码自定义数据处理任务模版，单任务及dag任务工作流调度等功能。集成了llm模块实现rag知识库问答，链接各数据源数据进行数据对话问答，交互式数据分析功能。

Content Enhanced BERT-based Text-to-SQL Generation https://arxiv.org/abs/1910.07179

A solution guidance for Generative BI using Amazon Bedrock, Amazon OpenSearch with RAG

🔥[VLDB'24] Official repository for the paper “The Dawn of Natural Language to SQL: Are We Fully Ready?”

RSL-SQL: Robust Schema Linking in Text-to-SQL Generation

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

This repo accelerates development of RAG applications with rich data sources including SQL Warehouses and documents analysed with Azure Document Intelligence

Convert natural language query to appropriate SQL, make ERPs cool again.

🌶️ R²SQL: "Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing." (AAAI 2021)

Fine-Tuning Dataset Auto-Generation for Graph Query Languages.

Data Neuron is a powerful framework that enables you to build text-to-SQL applications with an easily maintainable semantic layer. Whether you're creating customer-facing chatbots, internal Slack bots for analytics, or other data-driven applications, Data Neuron provides the tools to make your data accessible through natural language

The easiest and most comprehensive framework for building enterprise-grade NL2SQL solutions at scale.

Text2SQL Engine with advanced RAG

The dataset and source code for our paper: "Did You Ask a Good Question? A Cross-Domain Question IntentionClassification Benchmark for Text-to-SQL"

EvalBench is a flexible framework designed to measure the quality of generative AI (GenAI) workflows around database specific tasks.

Table2answer: Read the database and answer without SQL https://arxiv.org/abs/1902.04260