<?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>向量化 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%90%91%E9%87%8F%E5%8C%96/</link><description>Recent content in 向量化 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Thu, 16 Jul 2026 11:31:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%90%91%E9%87%8F%E5%8C%96/index.xml" rel="self" type="application/rss+xml"/><item><title>Embedding模型选型与优化：从通用到垂直领域</title><link>https://guijiagi.com/posts/b1-c4dac6e8/</link><pubDate>Thu, 16 Jul 2026 11:31:00 +0800</pubDate><guid>https://guijiagi.com/posts/b1-c4dac6e8/</guid><description>系统讲解Embedding模型的选型策略、微调方法和评估指标，助力构建高质量向量检索系统</description></item><item><title>RAG系统进阶：从朴素检索到自适应检索增强</title><link>https://guijiagi.com/posts/b1-f95dfde9/</link><pubDate>Thu, 16 Jul 2026 11:02:00 +0800</pubDate><guid>https://guijiagi.com/posts/b1-f95dfde9/</guid><description>从基础RAG到高级RAG的完整技术路线，涵盖混合检索、重排序、查询改写、自反思等关键技术</description></item></channel></rss>