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.
This system helps you quickly find answers and insights from your collection of documents, like reports, manuals, or research papers. You upload your files, then ask questions in natural language, and it provides answers with clear citations linking back to the exact source pages and headings. It's designed for anyone who needs to extract precise information from complex documents, such as researchers, legal professionals, or technical writers.
179 stars.
Use this if you need to reliably query large, complex documents (like PDFs with figures, tables, and specific formatting) and get answers with verifiable sources.
Not ideal if your primary need is basic keyword search on simple text files, or if you don't require detailed page-level citations for your answers.
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
Ambuj123-lab/agentic-rag-financial-parser
Enterprise RAG ecosystem managing 15,000+ semantic chunks. Features hybrid parsing...
marcoguad-HR/pay-transparency-tool
RAG-powered assistant and pay gap analysis tool for EU Directive 2023/970 compliance
ChiufungLee/RAG_TestCases_Generator
AI 测试用例生成系统。基于 DeepSeek + 百炼部署的 RAG 知识库，包含需求分析、测试用例生成、智能运维助手、产品指南等内容