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.

↗ 在 GitHub 打开

星数

519

Fork 数

112

语言

Python

许可

—

最后推送

5个月前

Python knowledge-graph react fastapi ollama rag gemini streaming knowledge-base retrieval-augmented-generation chromadb vector-search citation document-parsing docling reranking lightrag

还没有相关情报

radar 追踪的来源里还没有出现过这个 repo。收集器按计划运行——等它覆盖到这个 repo 再回来看看。