LeDat98/NexusRAG
Hybrid RAG system combining vector search, knowledge graph (LightRAG), and cross-encoder reranking — with Docling document parsing, visual intelligence (image/table captioning), agentic streaming chat, and inline citations. Powered by Gemini or local Ollama models.
The system employs a two-tier embedding architecture—BAAI/bge-m3 (1024-dim) for fast vector retrieval and a configurable second model (Gemini 3072-dim, Ollama, or sentence-transformers) exclusively for knowledge graph entity extraction—optimizing each stage for its computational requirements. Docling or Marker parsers preserve document structure (headings, page boundaries, tables) and auto-caption images/tables for semantic searchability before chunking, while LightRAG extracts entity relationships for multi-hop traversal independent of vector similarity. The frontend (React 19) integrates a document viewer with interactive knowledge graph visualization, allowing users to navigate citations back to source pages and explore entity connections discovered during retrieval.
179 stars.
Stars
179
Forks
43
Language
Python
License
—
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/LeDat98/NexusRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
masterFoad/NanoSage
Local LLM Powered Recursive Search & Smart Knowledge Explorer
Zakk-Yang/nexusync
Intuitive RAG system on top of LllamaIndex
Serhii2009/brix-protocol
Runtime Reliability Infrastructure for LLM Pipelines — enforce deterministic rules, measure the...
Ambuj123-lab/agentic-rag-financial-parser
Enterprise RAG ecosystem managing 15,000+ semantic chunks. Features hybrid parsing...
huangjia2019/rag-project03-audit
[RAG训练营] u.geekbang.org/subject/airag/1009927 ESG合规审计系统 - 可持续发展报告检查工具