<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>DataStax on Jamie Ede</title>
    <link>https://www.jamieede.com/tags/datastax/</link>
    <description>Recent content in DataStax on Jamie Ede</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 22 May 2026 11:00:00 +0000</lastBuildDate>
    <atom:link href="https://www.jamieede.com/tags/datastax/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Building Astra Docs Chat: asking DataStax docs questions in plain English</title>
      <link>https://www.jamieede.com/posts/building-astra-docs-chat-rag-over-datastax-on-langflow-and-cloudflare-pages/</link>
      <pubDate>Fri, 22 May 2026 11:00:00 +0000</pubDate>
      <guid>https://www.jamieede.com/posts/building-astra-docs-chat-rag-over-datastax-on-langflow-and-cloudflare-pages/</guid>
      <description>&lt;p&gt;After working with distributed databases at DataStax, I kept doing the same thing: open five doc tabs, search, skim, repeat. The official &lt;strong&gt;Astra DB Serverless&lt;/strong&gt; documentation is thorough, but there is just a lot of it.&lt;/p&gt;&#xA;&lt;p&gt;I wanted a single place to ask normal questions (&lt;em&gt;How do I create a collection?&lt;/em&gt;, &lt;em&gt;What are PCU groups?&lt;/em&gt;, &lt;em&gt;How does hybrid search work?&lt;/em&gt;) and get answers grounded in the real docs, not a model’s best guess from training data.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
