49 lines
2.6 KiB
Markdown
49 lines
2.6 KiB
Markdown
---
|
||
title: "Personal Knowledge Base (RAG)"
|
||
type: source
|
||
tags: []
|
||
date: 2026-04-22
|
||
---
|
||
|
||
## Source File
|
||
- [[Agent/usecases/knowledge-base-rag]]
|
||
|
||
## Summary(用中文描述)
|
||
- 核心主题:AI Agent 驱动的个人知识库 RAG 系统,实现"零摩擦保存、语义检索"的工作流
|
||
- 问题域:书签堆积却无法找到所需内容——阅读的文章、推文、视频随时间遗忘
|
||
- 方法/机制:
|
||
- 通过 Telegram Topic 或 Slack Channel 一键摄取引擎(URL 自动抓取网页/推文/YouTube 字幕/PDF)
|
||
- Embedding 向量化存储,支持语义搜索("我保存的关于 LLM memory 的内容?")
|
||
- 集成 OpenClaw knowledge-base skill,工作流间自动查询知识库
|
||
- 结论/价值:**捕获像发短信一样简单,检索像搜索一样容易**,无需专用 App
|
||
|
||
## Key Claims(用中文描述)
|
||
- 个人知识积累面临"阅读多、保存多、找到难"的困境
|
||
- 通过 Telegram/Slack 直接投递 URL,自动解析内容并索引至知识库
|
||
- 语义搜索超越关键词匹配,返回排名结果并附带来源引用
|
||
- 知识库可被其他工作流(如视频选题流水线)主动调用
|
||
|
||
## Key Quotes
|
||
> "You read articles, tweets, and watch videos all day but can never find that one thing you saw last week. Bookmarks pile up and become useless." — 痛点描述
|
||
|
||
## Key Concepts
|
||
- [[Knowledge-Base-RAG]]:Retrieval-Augmented Generation,个人知识库的核心架构,详见 [[Knowledge-Base-RAG]] 概念页
|
||
- [[Zero-Friction-Capture]]:零摩擦捕获——任何内容只需发消息即可入库,无需切换 App
|
||
- [[Semantic-Search]]:基于 Embedding 向量相似度的语义检索,而非关键词匹配
|
||
- [[Content-Ingestion]]:URL 内容自动解析与分块(Chunking)入库
|
||
|
||
## Key Entities
|
||
- [[OpenClaw]]:多 Agent 框架,提供 `knowledge-base` skill 实现 RAG 工作流
|
||
- [[ClawHub]]:OpenClaw Skill 市场,knowledge-base skill 的分发来源
|
||
- [[Telegram]]:知识库投递入口(Topic 路由)
|
||
- [[Slack]]:知识库投递入口(Channel)
|
||
|
||
## Connections
|
||
- [[Second Brain]] ← extends ← [[Knowledge-Base-RAG]]:个人知识库 RAG 是 Second Brain 的检索底层
|
||
- [[YouTube-Content-Pipeline]] ← queries ← [[Knowledge-Base-RAG]]:视频选题工作流自动查询知识库避免重复选题
|
||
- [[Pre-Build-Idea-Validator]] ← queries ← [[Knowledge-Base-RAG]]:项目启动前查询知识库确认是否已做过类似项目
|
||
- [[Content-Ingestion]] ← supports ← [[Semantic-Search]]:内容被抓取才能被搜索
|
||
|
||
## Contradictions
|
||
- 暂无发现与其他 Wiki 页面的内容冲突
|