<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>知识库 on Plbear | Cuz Penguin QQ</title><link>https://www.plbear.com/tags/%E7%9F%A5%E8%AF%86%E5%BA%93/</link><description>Recent content in 知识库 on Plbear | Cuz Penguin QQ</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Wed, 15 Apr 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://www.plbear.com/tags/%E7%9F%A5%E8%AF%86%E5%BA%93/index.xml" rel="self" type="application/rss+xml"/><item><title>RAG 个人知识库实战：weknora + MCP 构建私有技术问答助手</title><link>https://www.plbear.com/posts/2026-04-15-rag-personal-knowledge-base/</link><pubDate>Wed, 15 Apr 2026 10:00:00 +0800</pubDate><guid>https://www.plbear.com/posts/2026-04-15-rag-personal-knowledge-base/</guid><description>基于 weknora + MCP 构建个人私有技术知识库 RAG 问答系统的完整实战，涵盖知识库搭建、文档处理、向量化、检索优化、MCP 接入、效果评估，以及在个人技术知识管理中的应用和踩坑经验。</description></item><item><title>技术人知识体系搭建：博客+知识库+AI 问答的三位一体方案</title><link>https://www.plbear.com/posts/2026-01-14-knowledge-system-trinity/</link><pubDate>Wed, 14 Jan 2026 10:00:00 +0800</pubDate><guid>https://www.plbear.com/posts/2026-01-14-knowledge-system-trinity/</guid><description>技术人个人知识体系的完整搭建方案，博客（输出）+ 知识库（沉淀）+ AI 问答（检索）三位一体，涵盖工具选型、工作流设计、内容运营、AI 增强，以及从0到1搭建个人技术品牌的实战经验。</description></item><item><title>个人知识库搭建实践：Obsidian vs weknora vs Notion 选型与迁移</title><link>https://www.plbear.com/posts/2025-09-22-personal-knowledge-base/</link><pubDate>Mon, 22 Sep 2025 10:00:00 +0800</pubDate><guid>https://www.plbear.com/posts/2025-09-22-personal-knowledge-base/</guid><description>个人知识库的搭建实践，从工具选型（Obsidian vs weknora vs Notion）到知识体系构建、笔记方法论、AI 增强，以及从 Notion 迁移到 weknora 的完整经验，打造技术人的第二大脑。</description></item><item><title>RAG 检索增强生成实战：从文档切分到向量检索完整方案</title><link>https://www.plbear.com/posts/2025-01-15-rag-practice/</link><pubDate>Wed, 15 Jan 2025 10:00:00 +0800</pubDate><guid>https://www.plbear.com/posts/2025-01-15-rag-practice/</guid><description>RAG（检索增强生成）的完整落地方案，涵盖文档切分策略、向量化、向量检索、重排序、Prompt 工程，以及在招聘场景下的实际应用和踩坑经验。</description></item></channel></rss>