Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

Interact with your SQL database, Natural Language to SQL using LLMs

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.

Agentar-Scale-SQL is a novel framework that leverages scalable computation to significantly improve Text-to-SQL performance.

sqlgpt-parser is a Python implementation of an SQL parser that effectively converts SQL statements into Abstract Syntax Trees (AST). By leveraging AST tree comparisons between two SQL queries, it becomes possible to achieve robust evaluation of text-to-SQL models.

a highly customized UI for NaturalLanguage-to-SQL human evaluation

An interactive DataOps assistant using an LLM-powered agent architecture to automate data profiling, cleaning, feature engineering, and natural language-based querying & visualization.

Turn plain-English questions into executable SQL. LangChain agents over a schema-aware FastAPI service, with example-SQL retrieval (RAG), per-DB instructions, OpenAI fine-tuning, and streaming generation.

Multilingual internship search assistant that converts natural language queries into SQL using LangChain + Groq Llama 3 and retrieves results from a local SQLite database via a Flask web UI.

NL-to-SQL PEFT Lab: interactive benchmark and playground for small generative models

CenQuery is a high-accuracy Natural Language to SQL (NL-to-SQL) system specifically architected for Indian Census datasets. By moving away from generic LLMs, this project utilizes a fine-tuned Llama-3-SQLCoder-8b model with LoRA adapters to ensure schema-safe query generation and 100% execution accuracy on domain-specific queries.

A natural language analytics engine that converts plain English business questions into SQL and delivers instant insights from 1.6 million rows of real e-commerce data — powered by Google Gemini.

Production-grade AI Voice Assistant that converts natural language (voice/text) into accurate SQL queries for ERP or databases. Handles ambiguity, validates queries, and returns trusted answers. Built for real business systems, not demo chatbots.

Portfolio NL→SQL assistant: 94.0% execution accuracy on BIRD Mini-Dev (above the 92.96% human-expert baseline), schema-RAG + sqlglot AST guards + deterministic chart picker, $0 free-tier LLM stack. Streamlit chat UI, live demo. · Портфолио NL→SQL: 94% EA на BIRD Mini-Dev, schema-RAG + sqlglot-гарды + chart picker, бесплатный стек, живое демо.

Generating Dashboard Level Analytics from DB Data directly from Natural Language User Query Using LLMs

AI-powered natural language to SQL analytics app using Streamlit, SQLite, LangChain, and Groq

Data-quality-aware NL-to-SQL system using RAG, QLoRA fine-tuning, and execution validation to generate robust SQL on messy real-world data.

End-to-end analytics: dbt on Databricks + Power BI dashboard + AI chatbot on Olist Brazilian e-commerce.

Generate Natural Language to SQL with RAG

Bilingual AR/EN agentic CRM + comms drafter for MENA freelancers — cross-lingual memory, hybrid RAG, HITL drafts, NL→SQL. Next.js 16 · LangGraph v1 · Supabase + pgvector · AI SDK 6.