<?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>Pipelines on Kent Yao</title>
    <link>https://yaooqinn.github.io/tags/pipelines/</link>
    <description>Recent content in Pipelines on Kent Yao</description>
    <generator>Hugo -- 0.157.0</generator>
    <language>en-us</language>
    <lastBuildDate>Sat, 28 Mar 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://yaooqinn.github.io/tags/pipelines/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Spark Declarative Pipelines: A Paradigm Shift for Data Engineering</title>
      <link>https://yaooqinn.github.io/posts/spark/spark-declarative-pipelines/</link>
      <pubDate>Sat, 28 Mar 2026 00:00:00 +0000</pubDate>
      <guid>https://yaooqinn.github.io/posts/spark/spark-declarative-pipelines/</guid>
      <description>Apache Spark 4.1 introduces Spark Declarative Pipelines (SDP) — a declarative framework that lets you define what your data should look like, not how to compute it. As a Spark PMC Member, here&amp;rsquo;s my take on what this means for data engineering.</description>
    </item>
  </channel>
</rss>
