Metadata-Version: 2.4
Name: perpetual-rag
Version: 1.0.0
Summary: 永續性知識管理系統：基於 Obsidian-NotebookLM-Claude Code 三層防幻覺 RAG 框架
Author-email: chenquanfu <s112000805@g.ksu.edu.tw>
License: MIT
Project-URL: Homepage, https://github.com/quanfu2026/perpetual-rag
Project-URL: Documentation, https://github.com/quanfu2026/perpetual-rag/blob/main/starter_kit/SETUP.md
Project-URL: Issues, https://github.com/quanfu2026/perpetual-rag/issues
Keywords: RAG,knowledge-management,hallucination,obsidian,claude
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: rank-bm25>=0.2.2
Requires-Dist: jieba>=0.42.1
Requires-Dist: scikit-learn>=1.0.0
Requires-Dist: pyyaml>=6.0

# perpetual-rag

**永續性知識管理系統** — 基於 Obsidian-NotebookLM-Claude Code 三層架構的防幻覺 RAG 框架

[![Version](https://img.shields.io/badge/version-1.0.0-blue)](https://github.com/quanfu2026/perpetual-rag)
[![Python](https://img.shields.io/badge/python-3.8+-green)](https://python.org)
[![License](https://img.shields.io/badge/license-MIT-orange)](LICENSE)

> 論文：「永續性知識管理：基於 Obsidian-NotebookLM-Claude Code 三層防幻覺 RAG 框架」
> ILT2026 國際學習科技研討會

---

## 一鍵安裝

```bash
pip install perpetual-rag
perpetual-rag init --vault ~/my_KnowledgeBase --project "我的研究專案"
```

## 核心功能

```bash
perpetual-rag init    # 建立知識庫
perpetual-rag search "關鍵字"  # BM25 搜尋
perpetual-rag audit   # 防幻覺掃描
perpetual-rag graph   # 生成知識圖譜
perpetual-rag bump    # 版本升級
```

## 系統架構

```
Obsidian（儲存層）→ NotebookLM（理解層）→ Claude Code（執行層）
       ↑ 知識解耦（SoC 原則）↑
```

## 驗證結果

| 指標 | 數值 |
|------|------|
| 幻覺率 | **3%**（基準 59%，降幅 -95%）|
| Token 消耗 | **↓65–76%** |
| RAM 峰值 | **120MB**（Mac Mini 2014，無 GPU）|
| 跨 Session 恢復 | **6 秒，零錯誤** |
