Python
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.
★ 530
Stars
113 forks · 4 open issues
+2.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
10.0
Momentum / 100
see the breakdown below
7mo ago
Created
last push 6mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 2.1 | +2.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 0.0 | last push 6mo ago; decays to zero at 180 days |
| Scale | 15 | 7.9 | 530 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 10.0 | sum of the above |
Detail
| Topics | chromadbcitationdoclingdocument-parsingfastapigeminiknowledge-baseknowledge-graphlightragollamaragreactrerankingretrieval-augmented-generationstreamingvector-search |
| Matched on | RAG (retrieval-augmented-generation) |
| Short window | +2 stars over 7 days = 0.3/day |
| Long window | +-1 stars over 26 days = 0.0/day |
| Lifetime average | 2.25 stars/day over 235 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |