<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>RAG on 知识铺的博客</title>
    <link>https://index.zshipu.com/geek/tags/RAG/</link>
    <description>Recent content in RAG on 知识铺的博客</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>zh-CN</language>
    <lastBuildDate>Mon, 31 Aug 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://index.zshipu.com/geek/tags/RAG/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>用 Milvus 和 Unstructured.io 搭建个人 EHR RAG 系统</title>
      <link>https://index.zshipu.com/geek/post/20260831/%E7%94%A8-Milvus-%E5%92%8C-Unstructured.io-%E6%90%AD%E5%BB%BA%E4%B8%AA%E4%BA%BA-EHR-RAG-%E7%B3%BB%E7%BB%9F/</link>
      <pubDate>Mon, 31 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://index.zshipu.com/geek/post/20260831/%E7%94%A8-Milvus-%E5%92%8C-Unstructured.io-%E6%90%AD%E5%BB%BA%E4%B8%AA%E4%BA%BA-EHR-RAG-%E7%B3%BB%E7%BB%9F/</guid>
      <description>crumpled hospital printouts、blurry scans 和 nested PDFs 堆成山，三年前的血检结果几乎无处可寻，医生的手写体直接把 OCR 变成最终 BOSS。教程用 Milvus 向量数据库和 Unstructured.io 把这些混乱数据转成可对话的个人 EHR RAG 系统。 Unstructured.io 把医疗 PDF 和扫描件拆成可检索块 Unstructured.io 的核心能力在于文档分区。它能读取嵌套 PDF、扫描图像和包含表格的医</description>
    </item>
  </channel>
</rss>
