<?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>Faithfulness on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/faithfulness/</link><description>Recent content in Faithfulness on AI 实战派 · 从技术到赚钱</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, 08 Oct 2026 12:36:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/faithfulness/index.xml" rel="self" type="application/rss+xml"/><item><title>RAG 做出来不算完，用 Ragas 给它打个分：四个核心指标怎么读</title><link>https://guijiagi.com/posts/2026-10-08-rag-evaluation-ragas-loop/</link><pubDate>Thu, 08 Oct 2026 12:36:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-08-rag-evaluation-ragas-loop/</guid><description>RAG 系统好不好，不能只看 demo。Ragas 用 faithfulness、answer relevancy、context precision／recall 四个指标给出可量化的体检报告。</description></item></channel></rss>