<?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>检索 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%A3%80%E7%B4%A2/</link><description>Recent content in 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>Thu, 25 Jun 2026 12:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%A3%80%E7%B4%A2/index.xml" rel="self" type="application/rss+xml"/><item><title>RAG 重排序指南：Cohere Rerank vs bge-reranker vs Cross-Encoder</title><link>https://guijiagi.com/posts/rag-reranking-guide/</link><pubDate>Thu, 25 Jun 2026 12:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/rag-reranking-guide/</guid><description>深入对比三种主流 RAG 重排序方案：Cohere Rerank API、BAAI bge-reranker、自训练 Cross-Encoder，涵盖原理、部署方式、代码实现、延迟测试与效果对比，给出不同场景的最佳选择。</description></item></channel></rss>