<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Vector Database on Chen Kai Blog</title><link>https://www.chenk.top/en/tags/vector-database/</link><description>Recent content in Vector Database on Chen Kai Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 15 Nov 2025 09:00:00 +0000</lastBuildDate><atom:link href="https://www.chenk.top/en/tags/vector-database/index.xml" rel="self" type="application/rss+xml"/><item><title>NLP (10): RAG and Knowledge Enhancement Systems</title><link>https://www.chenk.top/en/nlp/rag-knowledge-enhancement/</link><pubDate>Sat, 15 Nov 2025 09:00:00 +0000</pubDate><guid>https://www.chenk.top/en/nlp/rag-knowledge-enhancement/</guid><description>&lt;p>A frozen language model is a confident liar. It can&amp;rsquo;t read yesterday&amp;rsquo;s incident report, your company wiki, or the patch notes that shipped this morning, so when you ask, it confabulates an answer that is grammatically perfect but factually wrong. &lt;strong>Retrieval-Augmented Generation (RAG)&lt;/strong> breaks the deadlock by separating &lt;em>memory&lt;/em> from &lt;em>reasoning&lt;/em>: keep the LLM small and stable, and put the volatile knowledge in an external store that you can update anytime. Before generating, retrieve the relevant evidence and condition the model on it.&lt;/p></description></item></channel></rss>