<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Posts on Satvik Gaikwad</title><link>https://satvikg7.github.io/posts/</link><description>Recent content in Posts on Satvik Gaikwad</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sat, 11 Jan 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://satvikg7.github.io/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Building a Semantic Code Search Engine with LLMs</title><link>https://satvikg7.github.io/posts/building-a-semantic-code-search-engine-with-llms/</link><pubDate>Sat, 11 Jan 2025 00:00:00 +0000</pubDate><guid>https://satvikg7.github.io/posts/building-a-semantic-code-search-engine-with-llms/</guid><description>&lt;p&gt;As developers, we spend a significant amount of time navigating large codebases. &amp;ldquo;Where is the authentication logic?&amp;rdquo; or &amp;ldquo;How does the payment flow work?&amp;rdquo; - these are questions we ask daily. Traditional text search falls short because it can&amp;rsquo;t understand &lt;em&gt;intent&lt;/em&gt;. That&amp;rsquo;s why I built &lt;strong&gt;Code Scout&lt;/strong&gt;.&lt;/p&gt;
&lt;h2 id="the-problem"&gt;The Problem&lt;/h2&gt;
&lt;p&gt;When joining a new project or revisiting an old one, understanding the codebase is often the biggest hurdle. You know what you&amp;rsquo;re looking for conceptually, but translating that into grep patterns or file names is tedious.&lt;/p&gt;</description></item></channel></rss>