<?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>向量数据库 on Kada's Notes</title><link>https://kadaliao.github.io/tags/%E5%90%91%E9%87%8F%E6%95%B0%E6%8D%AE%E5%BA%93/</link><description>Recent content in 向量数据库 on Kada's Notes</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Mon, 30 Oct 2023 00:00:00 +0000</lastBuildDate><atom:link href="https://kadaliao.github.io/tags/%E5%90%91%E9%87%8F%E6%95%B0%E6%8D%AE%E5%BA%93/index.xml" rel="self" type="application/rss+xml"/><item><title>向量数据库横评：Chroma vs Pinecone vs Weaviate vs Milvus</title><link>https://kadaliao.github.io/posts/vector-database-comparison/</link><pubDate>Mon, 30 Oct 2023 00:00:00 +0000</pubDate><guid>https://kadaliao.github.io/posts/vector-database-comparison/</guid><description>向量数据库是 RAG 系统的核心存储组件。这篇文章从工程角度对比几个主流选项，帮你选出适合的方案。</description></item><item><title>RAG 系统从零搭建：检索增强生成的原理与实践</title><link>https://kadaliao.github.io/posts/rag-from-scratch/</link><pubDate>Tue, 15 Aug 2023 00:00:00 +0000</pubDate><guid>https://kadaliao.github.io/posts/rag-from-scratch/</guid><description>RAG 是目前解决 LLM 知识局限性最主流的方案。这篇文章从原理出发，完整实现一个最小可用的 RAG 系统。</description></item></channel></rss>