<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Rag on 我思故我在</title><link>https://example.org/tags/rag/</link><description>Recent content in Rag on 我思故我在</description><generator>Hugo -- gohugo.io</generator><language>zh-cn</language><copyright>© 2026 博主</copyright><lastBuildDate>Wed, 19 Aug 2026 09:00:00 +0800</lastBuildDate><atom:link href="https://example.org/tags/rag/index.xml" rel="self" type="application/rss+xml"/><item><title>RAG 检索增强生成入门</title><link>https://example.org/ai/rag-intro/</link><pubDate>Wed, 19 Aug 2026 09:00:00 +0800</pubDate><guid>https://example.org/ai/rag-intro/</guid><description>&lt;h2 class="relative group"&gt;为什么要 RAG&#10; &lt;div id="为什么要-rag" class="anchor"&gt;&lt;/div&gt;&#10; &#10; &lt;span&#10; class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"&gt;&#10; &lt;a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#%e4%b8%ba%e4%bb%80%e4%b9%88%e8%a6%81-rag" aria-label="锚点"&gt;#&lt;/a&gt;&#10; &lt;/span&gt;&#10; &#10;&lt;/h2&gt;&#10;&lt;p&gt;大模型的知识有截止日期，也无法覆盖私有文档。&lt;strong&gt;检索增强生成（RAG）&lt;/strong&gt; 先从知识库检索相关内容，再让模型基于这些内容作答，显著减少幻觉。&lt;/p&gt;</description></item></channel></rss>