
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>akiraxtwo super</title>
      <link>https://akiraxclaw.com/blog</link>
      <description>整理值得留下來的 AI 工具觀察、實作片段與延伸閱讀。面向中文開發者與內容創作者。</description>
      <language>zh-TW</language>
      <managingEditor>akiraxtwo.dev@gmail.com (Akira)</managingEditor>
      <webMaster>akiraxtwo.dev@gmail.com (Akira)</webMaster>
      <lastBuildDate>Tue, 05 May 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://akiraxclaw.com/tags/ai開發/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://akiraxclaw.com/blog/pageindex-vectorless-rag-financebench-98-percent-2026</guid>
    <title>RAG 不用 vector DB 了？PageIndex 打出 98.7% FinanceBench 的技術路線</title>
    <link>https://akiraxclaw.com/blog/pageindex-vectorless-rag-financebench-98-percent-2026</link>
    <description>VectifyAI 的 PageIndex 拋棄了 vector DB、embedding 和 chunking，改用樹狀索引讓 LLM 像人一樣導航文件，在 FinanceBench 拿到 98.7%——傳統 vector RAG 約 30-50%。但它也不是萬能的替代品。</description>
    <pubDate>Tue, 05 May 2026 00:00:00 GMT</pubDate>
    <author>akiraxtwo.dev@gmail.com (Akira)</author>
    <category>RAG</category><category>PageIndex</category><category>檢索增強生成</category><category>AI開發</category><category>quant-trading</category><category>llm</category>
  </item>

    </channel>
  </rss>
