<?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>图文检索 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%9B%BE%E6%96%87%E6%A3%80%E7%B4%A2/</link><description>Recent content in 图文检索 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>Tue, 30 Jun 2026 09:40:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%9B%BE%E6%96%87%E6%A3%80%E7%B4%A2/index.xml" rel="self" type="application/rss+xml"/><item><title>多模态RAG：图文混合检索的架构设计</title><link>https://guijiagi.com/posts/multimodal-rag-architecture/</link><pubDate>Tue, 30 Jun 2026 09:40:00 +0800</pubDate><guid>https://guijiagi.com/posts/multimodal-rag-architecture/</guid><description>多模态RAG让AI能同时理解和检索图片与文字，本文详解四种架构设计与Claude 4/GPT-5的实践方案</description></item></channel></rss>