<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Week 7 - Retrieval Augmented Generation (RAG) on AI Platform Engineering Handbook</title><link>/docs/week-07/</link><description>Recent content in Week 7 - Retrieval Augmented Generation (RAG) on AI Platform Engineering Handbook</description><generator>Hugo</generator><language>en</language><copyright>Copyright (c) 2026 Harshhaa</copyright><atom:link href="/docs/week-07/index.xml" rel="self" type="application/rss+xml"/><item><title>RAG Foundations</title><link>/docs/week-07/rag-foundations/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>/docs/week-07/rag-foundations/</guid><description>&lt;hr&gt;
&lt;h2 id="1-what-is-rag"&gt;1. What is RAG&lt;/h2&gt;
&lt;p&gt;RAG stands for Retrieval-Augmented Generation. That&amp;rsquo;s a mouthful, so let&amp;rsquo;s break the phrase into its three pieces because each word actually tells you exactly what&amp;rsquo;s happening.&lt;/p&gt;</description></item><item><title>Advanced RAG</title><link>/docs/week-07/advanced-rag/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>/docs/week-07/advanced-rag/</guid><description>&lt;hr&gt;
&lt;h2 id="1-multi-document-rag"&gt;1. Multi-Document RAG&lt;/h2&gt;
&lt;p&gt;Basic RAG, in its simplest form, is often explained as if you&amp;rsquo;re searching through one big pile of text and pulling out a few relevant chunks. But in reality, most useful RAG systems need to work across many separate documents — sometimes hundreds, thousands, or more — and the answer to a question might require pulling together pieces from several completely different documents at once.&lt;/p&gt;</description></item><item><title>Vector Databases</title><link>/docs/week-07/vector-databases/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>/docs/week-07/vector-databases/</guid><description>&lt;hr&gt;
&lt;h2 id="1-vector-database-architecture"&gt;1. Vector Database Architecture&lt;/h2&gt;
&lt;p&gt;Let&amp;rsquo;s start by understanding, at a high level, what&amp;rsquo;s actually happening inside a vector database, because this foundation will make everything else in this guide much easier to follow.&lt;/p&gt;</description></item></channel></rss>