<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Vector-Search on Pi Stack</title>
    <link>https://www.pistack.xyz/tags/vector-search/</link>
    <description>Recent content in Vector-Search on Pi Stack</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 13 Oct 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://www.pistack.xyz/tags/vector-search/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Embedded Vector Search in 2026: LanceDB vs sqlite-vec vs pgvector (No Server Required)</title>
      <link>https://www.pistack.xyz/posts/2026-10-13-embedded-vector-search-lancedb-sqlite-vec-pgvector-guide/</link>
      <pubDate>Tue, 13 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://www.pistack.xyz/posts/2026-10-13-embedded-vector-search-lancedb-sqlite-vec-pgvector-guide/</guid>
      <description>&lt;p&gt;You do not need a cluster to do fast similarity search. That statement would have been controversial in 2022, when the default answer was &amp;ldquo;stand up a vector database service and point your app at it.&amp;rdquo; In 2026 the embedded tier is genuinely good — and it is the right answer for a surprising number of projects. The three options that matter are &lt;strong&gt;pgvector&lt;/strong&gt; (23,326 stars), &lt;strong&gt;LanceDB&lt;/strong&gt; (11,652 stars), and &lt;strong&gt;sqlite-vec&lt;/strong&gt; (8,183 stars). One bolts onto the database you already run, one is a columnar library that lives inside your process, and one is a single C extension that runs anywhere SQLite compiles. Picking the wrong one means either a migration later or paying operational costs for capacity you never needed.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
