Phase 0-2: Schema cleanup, typed relations, event-driven automation
- Phase 0: AGENTS.md cleanup (dedup quotes, renumber sections, merge qmd) - Phase 1: typed relations (manage-relations.py, graph-search.py, check-staleness.py, detect-conflicts.py) - Phase 2: frontmatter validator, weekly lint, knowledge promotion, git hooks - Fix .gitignore to track tools/ and .githooks/ - Fix git remote URL (remove plaintext token) - New wiki pages: 504 pages, 34 raw sources
This commit is contained in:
@@ -19,6 +19,8 @@ aliases:
|
||||
> **核心差异**:RAG 每次查询都从原始文档重新发现知识;LLM Wiki 将知识编译一次并持续维护。
|
||||
|
||||
## 对比表
|
||||
- [[Memex]]
|
||||
- [[知识库维护自动化]]
|
||||
|
||||
| 维度 | RAG | LLM Wiki |
|
||||
|------|-----|----------|
|
||||
@@ -76,4 +78,11 @@ LLM Wiki: Ingest → Compile → Maintain → Query → 复用
|
||||
|
||||
## 实践佐证
|
||||
|
||||
---
|
||||
## 核心概念
|
||||
|
||||
| 页面 | 简介 |
|
||||
|------|------|
|
||||
| [[RAG vs 持久化知识库]] | RAG检索模式与Wiki持久化模式的对比分析 |
|
||||
|
||||
[[Farzapedia|Farza]] 在构建个人 Wiki 前曾用 RAG 做过类似系统,但效果"一言难尽"。转为基于文件系统的知识库后,Agent 天然就能理解文件结构和反向链接,反而好用得多。
|
||||
|
||||
Reference in New Issue
Block a user