dat
Active·★ 259·Apache-2.0·Updated 2025-12-26
★ Trending
DAT (Data Ask Tool) is an enterprise-grade AI framework that enables business users to interact with databases using natural language, eliminating the need for complex SQL queries. It ensures high-quality and deterministic results through a pre-modeled semantic layer and an Askdata Agent workflow.
#NL2SQL#Enterprise AI#Data Query#Semantic Layer#Extensible Framework#Data Analysis
01
Features
01Pluggable SPI architecture for flexible extension of databases, LLMs, and embedding models.
02Comprehensive support for multiple databases including MySQL, PostgreSQL, Oracle, and easy expansion.
03Intelligent semantic SQL generation leveraging LLMs for natural language understanding and dialect conversion.
04Rich semantic modeling capabilities including entities, dimensions, and measures with intuitive YAML configuration.
05Vectorized retrieval augmentation using embedding models for semantic search of SQL Q&A pairs and business knowledge.
02
Compatibility
MySQL
Supported
Verified via docs
PostgreSQL
Supported
Verified via docs
Oracle
Supported
Verified via docs
DuckDB
Native
Verified via docs
OpenAI
Supported
Verified via docs
Anthropic
Supported
Verified via docs
03
Quick start
1
$ wget https://github.com/hexinfo/dat/releases/latest/download/dat-cli-0.7.2-full.tar.gz
04
Use cases
↳Integrate with the Dify platform for web-based intelligent Q&A applications without developing a custom frontend.
↳Integrate into custom web projects via streaming Q&A API for self-developed interfaces.
↳Integrate into MCP (Model Context Protocol)-supported agents like Claude Desktop or Cline for enhanced smart data querying capabilities.
05
Alternatives
Comments
Log in to leave a comment
No comments yet. Be the first!