<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0"
     xmlns:atom="http://www.w3.org/2005/Atom"
     xmlns:content="http://purl.org/rss/1.0/modules/content/"
     xmlns:dc="http://purl.org/dc/elements/1.1/"
     xmlns:media="http://search.yahoo.com/mrss/">
  <channel>
    <title>Retrieval on Xinwei Xiong (cubxxw) - AI, Open Source &amp; Nomad Blog</title>
    <link>https://cubxxw.com/tags/retrieval/</link>
    <description>Tech blog by Xinwei Xiong — AI Builder, open source contributor and digital nomad sharing Kubernetes, Go, AI projects and travel.</description>
    <image>
      <title>Xinwei Xiong (cubxxw) - AI, Open Source &amp; Nomad Blog</title>
      <url>https://cubxxw.com/assets/og-image.png</url>
      <link>https://cubxxw.com/</link>
    </image>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 11 Jul 2026 10:00:00 +0800</lastBuildDate>
    <atom:link href="https://cubxxw.com/tags/retrieval/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>GEO Mechanics: How AI Retrieves, Re-ranks, and Cites You</title>
      <link>https://cubxxw.com/ai-agent/posts/geo-how-ai-retrieves-and-cites/</link>
      <pubDate>Sat, 11 Jul 2026 10:00:00 +0800</pubDate>
      <atom:updated>Sat, 11 Jul 2026 18:28:03 +0800</atom:updated>
      <dc:creator>熊鑫伟 (Xinwei Xiong)</dc:creator>
      <guid isPermaLink="true">https://cubxxw.com/ai-agent/posts/geo-how-ai-retrieves-and-cites/</guid>
      <description>To get cited by AI, first understand how it picks. This chapter takes the RAG pipeline apart to the component level: query fan-out, hybrid retrieval, vector semantics, multi-stage reranking, and citations pre-embedded before generation. The one core takeaway — the retrieval unit is the passage, not the page. Optimize the chunk. Chapter 2 of the GEO series.
</description>
      <category domain="tag">GEO</category>
      <category domain="tag">RAG</category>
      <category domain="tag">AI Search</category>
      <category domain="tag">Retrieval</category>
      <category domain="tag">LLM</category>
      <category domain="tag">Embeddings</category>
      <category domain="tag">Content Strategy</category>
      <enclosure url="https://cubxxw.com/images/columns/geo/en-02-retrieval.svg" type="image/jpeg" length="0" />
      <media:content url="https://cubxxw.com/images/columns/geo/en-02-retrieval.svg" medium="image"><media:description>GEO mechanics cover showing the RAG pipeline for AI retrieval, reranking, and citation</media:description></media:content>
    </item>
  </channel>
</rss>
