weAIDB/CrackSQL
LLM-based Dialect Translation System
Combines rule-based translation (leveraging SQLGlot parsing) with fine-tuned LLMs and embedding models through a hybrid three-mode approach: rule-only for broad compatibility across 24+ dialects, LLM-direct for flexibility, and Rule+LLM for precision via adaptive local-to-global iteration. Supports PostgreSQL, MySQL, and Oracle with both cloud-based models (GPT, DeepSeek) and locally-deployed Hugging Face models, accessible through Python API, CLI, and web interface.
Available on PyPI.
Stars
78
Forks
24
Language
Python
License
MIT
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Dependencies
29
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/weAIDB/CrackSQL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
mindsdb/mindsdb
Query Engine for AI Analytics: Build self-reasoning agents across all your live data
vanna-ai/vanna
🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.
dataease/SQLBot
🔥 基于大模型和 RAG 的智能问数系统，对话式数据分析神器。Text-to-SQL Generation via LLMs using RAG.
Canner/WrenAI
⚡️ GenBI (Generative BI) queries any database in natural language, generates accurate SQL...
Dataherald/dataherald
Interact with your SQL database, Natural Language to SQL using LLMs