<?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 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E5%90%91%E9%87%8F/</link><description>Recent content in 向量 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, 25 Jun 2026 12:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E5%90%91%E9%87%8F/index.xml" rel="self" type="application/rss+xml"/><item><title>AI 原生数据库设计：向量检索与结构化查询的融合</title><link>https://guijiagi.com/posts/ai-native-database/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/ai-native-database/</guid><description>系统讲解 AI 原生数据库的核心架构设计，涵盖向量索引、混合查询、存储引擎与性能优化</description></item><item><title>Embedding 模型选型指南：bge vs e5 vs OpenAI vs Cohere</title><link>https://guijiagi.com/posts/embedding-model-guide/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/embedding-model-guide/</guid><description>深度对比 2026 年主流 Embedding 模型：BGE-M3、E5-Mistral、OpenAI text-embedding-3、Cohere embed-v4 在 RAG、语义搜索、聚类等场景的表现与选型建议。</description></item><item><title>Embedding 模型选型：OpenAI/BGE/E5/Novus 对比</title><link>https://guijiagi.com/posts/embedding-model-selection/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/embedding-model-selection/</guid><description>Embedding 模型深度选型指南，涵盖 MTEB 排行、维度存储、多语言支持与领域微调</description></item></channel></rss>