<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Retrieval on René Zander | AI Automation Consultant</title><link>https://renezander.com/tags/retrieval/</link><description>Recent content in Retrieval on René Zander | AI Automation Consultant</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 02 May 2026 08:00:00 +0000</lastBuildDate><atom:link href="https://renezander.com/tags/retrieval/index.xml" rel="self" type="application/rss+xml"/><item><title>Agentic Knowledge Base — Karpathy's LLM wiki, with adapters</title><link>https://renezander.com/blog/agentic-knowledge-base/</link><pubDate>Sat, 02 May 2026 08:00:00 +0000</pubDate><guid>https://renezander.com/blog/agentic-knowledge-base/</guid><description>&lt;p>When Karpathy&amp;rsquo;s &lt;a href="https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f">LLM Wiki&lt;/a> post landed, I already had semantic search over my TickTick — qdrant for the vector store, nomic-embed-text via ollama for embeddings, a daily cron to keep the index fresh, the works. The agent-side retrieval wasn&amp;rsquo;t the missing piece.&lt;/p>
&lt;p>What was missing was the &lt;em>structure&lt;/em>. Karpathy&amp;rsquo;s framing — designate a wiki, write notes for an LLM reader, lean on retrieval instead of taxonomy — surfaced the parts of my setup that didn&amp;rsquo;t have shape yet: where durable knowledge lives versus ephemeral tasks, how agents pull structured data out of notes humans wrote, why my existing semantic search sometimes returned the right answer and sometimes returned nothing useful.&lt;/p></description></item></channel></rss>