Zhongye1/KnowledgeRAG-GZHU

​​KnowledgeRAG-GZHU​​ 是一个面向智能知识管理的检索增强生成(RAG)系统,集成文档解析、知识库管理、知识图谱生成、向量检索、Ollama模型服务及智能问答核心功能。前端基于 ​​Vue3 + TypeScript​​ 构建交互框架,实现知识组织与问答可视化;后端采用 ​​FastAPI​​ 架构提供高性能服务支持。该系统通过本地知识库与大语言模型协同推理,显著缓解大模型幻觉问题,提升领域知识问答的精确性与可靠性。

32
/ 100
Emerging

**Feature-rich multi-step RAG pipeline with hybrid retrieval (dense + sparse + reranking) and Agent-driven task automation via ReAct framework.** Supports streaming document generation across 5 modes (reports/summaries/outlines/blogs/papers) with SSE, and integrates with office tools (Obsidian, Feishu, DingTalk, WeChat Work, Notion, GitHub) via webhooks and API adapters. Containerized with Docker Compose, includes local Whisper ASR for voice queries, DuckDuckGo web search fallback, and multi-model routing across Ollama, OpenAI, DeepSeek, and Hunyuan with Cross-Encoder reranking to minimize hallucinations.

No License No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 7 / 25
Community 10 / 25

How are scores calculated?

Stars

72

Forks

6

Language

Vue

License

Last pushed

Jan 02, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/Zhongye1/KnowledgeRAG-GZHU"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.