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
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
pip install perpetual-rag
perpetual-rag init --vault ~/my_KnowledgeBase --project "我的研究專案"
核心功能
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 |
1 maintainer
Metadata
1 maintainer
Release files for perpetual-rag 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| perpetual_rag-1.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Release files / perpetual_rag-1.0.0-py3-none-any.whl
| Download URL | perpetual_rag-1.0.0-py3-none-any.whl |
|---|---|
| Size | 34.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f2389bebe63758eb17590c54e5af750db50e3104f36a789d46749aef9d980d2e
|
|
BLAKE2b-256 checksum How to use checksums |
949f7686fbef2fa4709a7a630f65a656ce29545d89de03829838139f5a069c7c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.4
|
Security for perpetual-rag 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
