<?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 Strathweb. A free flowing tech monologue.</title>
    <link>https://www.strathweb.com/categories/rag/</link>
    <description>Recent content in Rag on Strathweb. A free flowing tech monologue.</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 14 Jul 2025 07:06:14 +0000</lastBuildDate><atom:link href="https://www.strathweb.com/categories/rag/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>RAG Agent with HyPE Pattern using Semantic Kernel</title>
      <link>https://www.strathweb.com/2025/07/rag-agent-with-hype-pattern-using-semantic-kernel/</link>
      <pubDate>Mon, 14 Jul 2025 07:06:14 +0000</pubDate>
      
      <guid>https://www.strathweb.com/2025/07/rag-agent-with-hype-pattern-using-semantic-kernel/</guid>
      <description>&lt;p&gt;In this post we will explore a novel approach to Retrieval-Augmented Generation (RAG) called &lt;a href=&#34;https://ssrn.com/abstract=5139335&#34;&gt;HyPE (Hypothetical Prompt Embeddings)&lt;/a&gt;, which I came across in a preprint paper recently. This technique tries to address one of the fundamental challenges in RAG systems: the semantic mismatch between user queries and document content. If you&amp;rsquo;ve ever built a RAG system, you&amp;rsquo;ve probably felt the frustration when your carefully crafted vector search returns seemingly irrelevant results. At least for me, it was always tremendously annoying when a simple question like &amp;ldquo;What is quantum entanglement?&amp;rdquo; wouldn&amp;rsquo;t reliably match a document section that clearly explains quantum entanglement.&lt;/p&gt;</description>
    </item>
    
  </channel>
</rss>
