<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>RAG on Po-Wei Chen, MD — Physiatrist &amp; Builder</title><link>https://drpwchen.com/en/tags/rag/</link><description>Recent content in RAG on Po-Wei Chen, MD — Physiatrist &amp; Builder</description><image><title>Po-Wei Chen, MD — Physiatrist &amp; Builder</title><url>https://drpwchen.com/og-default.png</url><link>https://drpwchen.com/og-default.png</link></image><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 22 Jun 2026 15:00:00 +0800</lastBuildDate><atom:link href="https://drpwchen.com/en/tags/rag/index.xml" rel="self" type="application/rss+xml"/><item><title>Adding graph retrieval to my medical LLM Wiki, and it actually works this time</title><link>https://drpwchen.com/en/posts/vault-graph-rag/</link><pubDate>Mon, 22 Jun 2026 15:00:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/vault-graph-rag/</guid><description>I threw a new paper on SQL-RAG at Claude to verify it myself: useless for a redundant textbook library, but a great fit for finding &amp;#34;related notes&amp;#34; in a sparse Obsidian medical note vault. After swapping the ranking to personalized PageRank, the proportion of correctly finding related notes jumped from 34% to 84%, and I put it straight into production.</description></item></channel></rss>