SAG

Active
GitHub TypeScript MIT

Description

SQL-Driven RAG Engine that automatically builds knowledge graphs during querying, combining SQL query capabilities with Retrieval-Augmented Generation for efficient knowledge retrieval.

Key Features

  • SQL-driven RAG engine that automatically builds knowledge graphs at query time instead of pre-maintaining them
  • Three-stage smart search: entity recall → multi-hop expansion → intelligent ranking (PageRank)
  • Semantic atomic event extraction — automatically decomposes documents into structured events and multi-dimensional entities
  • 5W1H dimension system (time, location, person, topic, action, tags) with custom entity type support
  • Complete provenance — every search result includes a clue chain and confidence scores
  • Docker Compose one-click deployment and Python SDK integration

Use Cases

💡 Build enterprise-grade private knowledge platforms with intelligent search across documents, conversations, and business data
💡 Provide RAG-enhanced retrieval services with provenance for AI agents
💡 Personal knowledge management: auto-split notes, smart entity annotation, multi-dimensional search
💡 Team collaboration docs: auto-extract decision points, track information evolution, generate reports
💡 Research analysis assistant: auto-extract arguments, build topic networks, discover hidden connections

Tags

python rag tools database data-processing

Categories

📚 RAG Tools

Quick Start

git clone https://github.com/Zleap-AI/SAG.git && cd SAG && cp .env.example .env && docker compose up -d, visit http://localhost
Visit GitHub

Related Projects