<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <title>links.lmorchard.com - #embedding</title>
    <link>/tags/embedding/</link>
    <description>Recent bookmarks tagged #embedding</description>
    <lastBuildDate>Mon, 02 Nov 2026 08:24:54 +0000</lastBuildDate>
    <item>
      <title>Introducing sqlite-lembed: A SQLite extension for generating text embeddings locally | Alex Garcia&#39;s Blog</title>
      <link>https://alexgarcia.xyz/blog/2024/sqlite-lembed-init/index.html</link>
      <description>sqlite-lembed is a SQLite extension for generating text embeddings, meant to work alongside sqlite-vec. With a single embeddings model file provided in the .gguf format, you can generate embeddings using regular SQL functions, and store them directly inside your SQLite database. No extra server, process, or configuration needed!&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #embedding #ml #search #sqlite&lt;/p&gt;</description>
      <pubDate>Wed, 02 Oct 2024 18:50:39 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:30484</guid>
      <category>ai</category>
      <category>embedding</category>
      <category>ml</category>
      <category>search</category>
      <category>sqlite</category>
    </item>
    <item>
      <title>KNN queries | sqlite-vec</title>
      <link>https://alexgarcia.xyz/sqlite-vec/features/knn.html</link>
      <description>The most common use-case for vectors in databases is for K-nearest-neighbors (KNN) queries. You&#39;ll have a table of vectors, and you&#39;ll want to find the K closest&lt;br/&gt;&#xA;&lt;p&gt;&lt;strong&gt;Tags:&lt;/strong&gt; #ai #embedding #ml #search #sqlite&lt;/p&gt;</description>
      <pubDate>Wed, 02 Oct 2024 18:43:43 +0000</pubDate>
      <guid isPermaLink="false">linkding-ssg:bookmark:30485</guid>
      <category>ai</category>
      <category>embedding</category>
      <category>ml</category>
      <category>search</category>
      <category>sqlite</category>
    </item>
  </channel>
</rss>
