<?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/">
  <channel>
    <title>#RAG on Home</title>
    <link>https://yakinin.com/en/tags/%23rag/</link>
    <description>Recent content in #RAG on Home</description>
    <generator>Hugo -- 0.148.2</generator>
    <language>en</language>
    <lastBuildDate>Wed, 13 Aug 2025 15:52:57 +0000</lastBuildDate>
    <atom:link href="https://yakinin.com/en/tags/%23rag/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Vector Search Is Reaching Its Limits. Here’s What Comes Next.</title>
      <link>https://yakinin.com/en/posts/20250813-vector-search-limitations-what-comes-next/</link>
      <pubDate>Wed, 13 Aug 2025 15:52:57 +0000</pubDate>
      <guid>https://yakinin.com/en/posts/20250813-vector-search-limitations-what-comes-next/</guid>
      <description>&lt;p&gt;Vector databases have become a core component in modern AI, particularly for powering retrieval-augmented generation (RAG) through similarity search. However, as we build more sophisticated applications, the limitations of relying solely on vector representations are becoming clear.&lt;/p&gt;
&lt;p&gt;From my perspective, the core issue is that advanced AI systems need to understand more than just semantic similarity. They require a richer grasp of data that includes structured attributes, textual precision, and the relationships within and across different modalities like text, images, and video. Relying on basic vector search alone creates significant blind spots.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
