<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Hybrid Retrieval on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/tags/hybrid-retrieval/</link>
    <description>Recent content in Hybrid Retrieval on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 14 Sep 2026 05:00:03 +0100</lastBuildDate>
    <atom:link href="http://programmer.ie/tags/hybrid-retrieval/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>The RAG Baseline</title>
      <link>http://programmer.ie/books/memory/03-chapter/</link>
      <pubDate>Mon, 14 Sep 2026 05:00:03 +0100</pubDate>
      <guid>http://programmer.ie/books/memory/03-chapter/</guid>
      <description>&lt;p&gt;The October contributor from Chapter 1 asks for a second service with its own event log. The July decision is still in the repository. So are the contention report, the benchmark, the earlier SQLite setup, and a great deal of discussion that no longer matters to this task. Before inventing a new kind of memory, there is an obvious possibility to test: find the useful parts of that history and let a capable model read them.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
