<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>PostgreSQL on Antoine Boucher</title><link>https://antoineboucher.info/CV/blog/tags/postgresql/</link><description>Recent content in PostgreSQL on Antoine Boucher</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 13 Apr 2026 12:00:00 -0400</lastBuildDate><atom:link href="https://antoineboucher.info/CV/blog/tags/postgresql/index.xml" rel="self" type="application/rss+xml"/><item><title>Exploring movie similarities with vector search algorithms</title><link>https://antoineboucher.info/CV/blog/posts/vector-databases-similar-movies/</link><pubDate>Mon, 13 Apr 2026 12:00:00 -0400</pubDate><guid>https://antoineboucher.info/CV/blog/posts/vector-databases-similar-movies/</guid><description>&lt;p&gt;This is a single walkthrough of a &lt;strong&gt;movie similarity&lt;/strong&gt; thread: &lt;strong&gt;Part 1&lt;/strong&gt; stores embeddings in &lt;strong&gt;PostgreSQL + pgvector&lt;/strong&gt; and runs nearest-neighbor search in SQL; &lt;strong&gt;Part 2&lt;/strong&gt; uses &lt;strong&gt;Qdrant&lt;/strong&gt; with &lt;strong&gt;MovieLens&lt;/strong&gt; (dense text vectors for semantic search and sparse rating vectors for collaborative-style recommendations); &lt;strong&gt;Part 3&lt;/strong&gt; turns the same pgvector-backed catalog into the retrieval layer for a small &lt;strong&gt;RAG&lt;/strong&gt; pipeline with &lt;strong&gt;LangChain&lt;/strong&gt; and &lt;strong&gt;Ollama&lt;/strong&gt;. Below are short GIFs from that work (&lt;code&gt;movie-similarities-1.gif&lt;/code&gt; … &lt;code&gt;3.gif&lt;/code&gt; in this page bundle).&lt;/p&gt;</description></item></channel></rss>