<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Postgres on Programmer.ie: Modern AI programming</title>
    <link>http://programmer.ie/categories/postgres/</link>
    <description>Recent content in Postgres on Programmer.ie: Modern AI programming</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 10 Mar 2025 21:35:37 +0000</lastBuildDate>
    <atom:link href="http://programmer.ie/categories/postgres/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>PostgreSQL for AI: Storing and Searching Embeddings with pgvector</title>
      <link>http://programmer.ie/post/pgvector/</link>
      <pubDate>Mon, 10 Mar 2025 21:35:37 +0000</pubDate>
      <guid>http://programmer.ie/post/pgvector/</guid>
      <description>&lt;h2 id=&#34;summary&#34;&gt;Summary&lt;/h2&gt;&#xA;&lt;p&gt;Vector databases are essential for modern AI applications like semantic search, recommendation systems, and natural language processing. They allow us to store and query high-dimensional vectors efficiently. With the &lt;a href=&#34;https://github.com/pgvector/pgvector&#34;&gt;pgvector&lt;/a&gt; extension &lt;a href=&#34;https://www.postgresql.org/download/&#34;&gt;PostgreSQL&lt;/a&gt; becomes a powerful vector database, enabling you to combine traditional relational data with vector-based operations.&lt;/p&gt;&#xA;&lt;p&gt;In this post, we will walk through the full process:&lt;/p&gt;&#xA;&lt;p&gt;Installing PostgreSQL and pgvector&#xA;Setting up a vector-enabled database&#xA;Generating embeddings using Ollama&#xA;Running similarity queries with Python&#xA;By the end, you&amp;rsquo;ll be able to store, query, and compare high-dimensional vectors in PostgreSQL, opening up new possibilities for AI-powered applications.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
