<?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 Subhash Dasyam</title><link>https://subhash.net/tags/rag/</link><description>Recent content in RAG on Subhash Dasyam</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 08 Jul 2025 01:09:16 +0400</lastBuildDate><atom:link href="https://subhash.net/tags/rag/index.xml" rel="self" type="application/rss+xml"/><item><title>How Transformers Actually Work: The Complete Simple Guide 🤖</title><link>https://subhash.net/posts/how-transformers-actually-work-complete/</link><pubDate>Tue, 08 Jul 2025 00:45:00 +0400</pubDate><guid>https://subhash.net/posts/how-transformers-actually-work-complete/</guid><description>&lt;p>Ever wondered how ChatGPT, Claude, or GPT-4 actually understand and generate text? Let me break down the magic behind transformers like you&amp;rsquo;re 12 years old! 👇&lt;/p>
&lt;p>Note: When I mention &amp;ldquo;117 million parameters&amp;rdquo; in examples, I&amp;rsquo;m talking about GPT-1 and BERT-base models. Modern models like GPT-4 are much, much bigger!&lt;/p></description></item><item><title>RAG+ Revolution: How Application-Aware Reasoning Transforms AI Knowledge Systems</title><link>https://subhash.net/posts/rag-revolution-how-application-aware/</link><pubDate>Tue, 17 Jun 2025 14:48:00 +0400</pubDate><guid>https://subhash.net/posts/rag-revolution-how-application-aware/</guid><description>&lt;h2 id="paper-review-and-attribution">Paper Review and Attribution&lt;/h2>
&lt;p>This article is based on the fascinating research paper &amp;ldquo;RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoning&amp;rdquo; by Yu Wang, Shiwan Zhao, Ming Fan, and colleagues from Huawei Technologies, Xi&amp;rsquo;an Jiaotong University, and Nankai University.&lt;/p></description></item></channel></rss>