<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Semantic-Search on Yushi's Blog</title><link>https://blog.yushi91.com/blog/semantic-search/</link><description>Recent content in Semantic-Search on Yushi's Blog</description><generator>Hugo</generator><language>en-US</language><copyright>Copyright © 2025, Yushi Cui.</copyright><lastBuildDate>Wed, 15 Apr 2026 10:00:00 +1200</lastBuildDate><atom:link href="https://blog.yushi91.com/blog/semantic-search/index.xml" rel="self" type="application/rss+xml"/><item><title>My First RAG Solution: Semantic Search Blew My Mind</title><link>https://blog.yushi91.com/blog/first-rag-solution-semantic-search/</link><pubDate>Wed, 15 Apr 2026 10:00:00 +1200</pubDate><guid>https://blog.yushi91.com/blog/first-rag-solution-semantic-search/</guid><description>&lt;p>&lt;img src="https://blog.yushi91.com/rag-solution.webp" alt="My First RAG Solution" loading="lazy">
&lt;/p>
&lt;h2 id="what-i-just-built">What I just built&lt;/h2>
&lt;p>I just finished my first RAG solution. RAG, as in Retrieval-Augmented Generation. I know the rabbit hole goes deep with this stuff, but getting the first version working? Way smoother than I expected. Some of the ideas behind it genuinely caught me off guard.&lt;/p>
&lt;h2 id="the-problem-with-keyword-search">The problem with keyword search&lt;/h2>
&lt;p>Regular search is keyword-based. You type &amp;ldquo;ruby&amp;rdquo; and it scans for the exact word &amp;ldquo;ruby.&amp;rdquo; If that string isn&amp;rsquo;t in the document, you get nothing.&lt;/p></description></item></channel></rss>