<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>PGVector :: 标签 :: x7peeps</title><link>https://x7peeps.com/tags/PGVector/index.html</link><description/><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Fri, 03 Jul 2026 07:21:56 +0000</lastBuildDate><atom:link href="https://x7peeps.com/tags/PGVector/index.xml" rel="self" type="application/rss+xml"/><item><title>Embedding 与向量数据库：模型选型、PGVector/Milvus/Chroma 对比</title><link>https://x7peeps.com/AI/04-RAG%E4%B8%8E%E7%9F%A5%E8%AF%86%E5%BA%93/Embedding%E4%B8%8E%E5%90%91%E9%87%8F%E6%95%B0%E6%8D%AE%E5%BA%93%E6%A8%A1%E5%9E%8B%E9%80%89%E5%9E%8BPGVectorMilvusChroma%E5%AF%B9%E6%AF%94/index.html</link><pubDate>Fri, 03 Jul 2026 07:21:56 +0000</pubDate><guid>https://x7peeps.com/AI/04-RAG%E4%B8%8E%E7%9F%A5%E8%AF%86%E5%BA%93/Embedding%E4%B8%8E%E5%90%91%E9%87%8F%E6%95%B0%E6%8D%AE%E5%BA%93%E6%A8%A1%E5%9E%8B%E9%80%89%E5%9E%8BPGVectorMilvusChroma%E5%AF%B9%E6%AF%94/index.html</guid><description>在 RAG（Retrieval-Augmented Generation）系统的技术栈中，Embedding 模型和向量数据库构成了检索能力的两大基石。前者决定了文本能否被精确地表示为数学向量，后者决定了这些向量能否被高效地存储和检索。选型不当的 Embedding 模型会导致语义匹配失准，而选型不当的向量数据库则会在规模增长时成为系统瓶颈。</description></item></channel></rss>