BukeLy/rag-api
Multi-tenant RAG API powered by LightRAG/RAG-Anything. Auto-selects best parser (DeepSeek-OCR/MinerU/Docling) via complexity scoring
Builds knowledge graphs automatically via LightRAG with pluggable entity extraction and relationship reasoning, then offers five retrieval modes (naive/local/global/hybrid/mix) to balance speed versus context depth. Provides complete multi-tenant isolation with per-tenant LightRAG instance pools, configuration overrides, and data compartmentalization across DragonflyDB (KV/task storage), Qdrant (vectors), and Memgraph (graphs). FastAPI-based service with async task queuing, batch document processing (up to 100 files), and VLM-enhanced chart understanding modes for RAG-Anything integration.
Stars
48
Forks
6
Language
Python
License
—
Category
Last pushed
Dec 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/BukeLy/rag-api"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
brevia-ai/brevia
Extensible API and framework to build your Retrieval Augmented Generation (RAG) and Information...
swirlai/swirl-search
AI Search & RAG Without Moving Your Data. Get instant answers from your company's knowledge...
wzdavid/ThinkRAG
A LLM RAG system runs on your laptop. 大模型检索增强生成系统，可以轻松部署在笔记本电脑上，实现本地知识库智能问答。企业级SaaS版本请访问：
thinkany-ai/rag-search
RAG Search API
sankalp1999/code_qa
RAG on codebases using treesitter and LanceDB