<?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>Obsidian on Po-Wei Chen, MD — Physiatrist &amp; Builder</title><link>https://drpwchen.com/en/tags/obsidian/</link><description>Recent content in Obsidian 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>Thu, 23 Jul 2026 06:45:00 +0800</lastBuildDate><atom:link href="https://drpwchen.com/en/tags/obsidian/index.xml" rel="self" type="application/rss+xml"/><item><title>Too Many Notes is No Notes: The Design of note-supplement</title><link>https://drpwchen.com/en/posts/note-supplement/</link><pubDate>Thu, 23 Jul 2026 06:45:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/note-supplement/</guid><description>My note vault has only one rule: one note per topic. If the same thing is covered in five different places, it&amp;#39;s the same as having no notes. The hard part is holding this line as sources pile up. note-supplement handles merging outside materials back into existing notes, without breaking the things you already got right.</description></item><item><title>Cross-Textbook Automated Note-Generation Workflow: A Product of the Board Examination</title><link>https://drpwchen.com/en/posts/textbook-to-note/</link><pubDate>Sun, 19 Jul 2026 15:45:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/textbook-to-note/</guid><description>With over forty designated reference books for the board examination, and the same concepts scattered across multiple books, how could anyone possibly finish reading them? I tuned AI to my note-taking workflow, letting it organize textbooks structurally and with evidence. Today I open-sourced the whole setup, and this post covers the five hurdles I cleared along the way.</description></item><item><title>I turned Obsidian into a second brain that "searches notes by meaning" (and open-sourced it)</title><link>https://drpwchen.com/en/posts/obsidian-vault-search/</link><pubDate>Tue, 23 Jun 2026 17:00:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/obsidian-vault-search/</guid><description>Obsidian&amp;#39;s built-in search only looks for the exact words you type, but you rarely remember the words you used months ago. I cleaned up and open-sourced the &amp;#34;semantic search trio&amp;#34; I&amp;#39;ve been using for the past half-year. It&amp;#39;s completely local and MIT-licensed.</description></item><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>