<?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>长文档 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E9%95%BF%E6%96%87%E6%A1%A3/</link><description>Recent content in 长文档 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>Wed, 07 Oct 2026 12:54:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E9%95%BF%E6%96%87%E6%A1%A3/index.xml" rel="self" type="application/rss+xml"/><item><title>长上下文不是越长越好：把一份 100 页文档喂给大模型的正确姿势</title><link>https://guijiagi.com/posts/2026-10-07-long-context-document-strategy/</link><pubDate>Wed, 07 Oct 2026 12:54:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-07-long-context-document-strategy/</guid><description>128K、1M 上下文听着爽，真塞满了反而中间内容被忽略。长文档处理的正解是切块检索、分层摘要，而不是一股脑全塞进去。</description></item></channel></rss>