<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Pg-Raggraph on Yonk-Labs</title><link>https://yonk.dev/tags/pg-raggraph/</link><description>Recent content in Pg-Raggraph on Yonk-Labs</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Yonk-Labs</copyright><lastBuildDate>Tue, 05 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://yonk.dev/tags/pg-raggraph/index.xml" rel="self" type="application/rss+xml"/><item><title>GraphRAG without a graph database. Yes, in postgres.</title><link>https://yonk.dev/blog/pg-raggraph-intro-postgres-native-graphrag/</link><pubDate>Tue, 05 May 2026 00:00:00 +0000</pubDate><guid>https://yonk.dev/blog/pg-raggraph-intro-postgres-native-graphrag/</guid><description>Most teams reach for Neo4j or Apache AGE the moment they read the Microsoft GraphRAG paper. The honest answer is most GraphRAG workloads don&amp;rsquo;t need a graph database — pgvector + recursive CTEs + tsvector handle 1-3 hop traversal in one ACID database.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://yonk.dev/blog/pg-raggraph-intro-postgres-native-graphrag/feature.jpg"/></item></channel></rss>