The Document Index / Document Parsing / #63
LeDat98/NexusRAG
by LeDat98 · Document Parsing · updated 1mo ago
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.
54
momentum
316
stars
64
forks
#63
rank
chromadbcitationdoclingdocument-parsingfastapigeminiknowledge-baseknowledge-graphlightragollamaragreact
View on GitHub →