<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Rag on Shaharia Azam&#39;s Website | DevOps, Platform Engineering &amp; AI Insights</title>
    <link>https://shaharia.com/tags/rag/</link>
    <description>Recent content in Rag on Shaharia Azam&#39;s Website | DevOps, Platform Engineering &amp; AI Insights</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Sat, 16 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://shaharia.com/tags/rag/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Embedded Vector Databases for Go in 2026: chromem-go vs sqlite-vec vs Bleve vs LanceDB</title>
      <link>https://shaharia.com/blog/choosing-embeddable-vector-database-go-application/</link>
      <pubDate>Sat, 25 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://shaharia.com/blog/choosing-embeddable-vector-database-go-application/</guid>
      <description>TL;DR — if you just want the answer&#xA;&amp;lt; ~100k vectors, pure-Go, no CGO, want it to &amp;ldquo;just work&amp;rdquo;: use chromem-go. Lexical + vector search in one engine, pure-Go: use Bleve. Millions of vectors, OK with CGO, SQL filters: use sqlite-vec (via mattn/go-sqlite3) or DuckDB + VSS. You can run a separate process: stop reading — use Qdrant or Chroma server. The whole point of this post is the single-binary constraint below.</description>
    </item>
  </channel>
</rss>
