<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Natural Language Processing</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Natural Language Processing feed</description>
    <item>
      <title>QCon London 2026: Reliable Retrieval for Production AI Systems</title>
      <link>https://www.infoq.com/news/2026/03/retrieval-production-ai/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Natural+Language+Processing</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/03/retrieval-production-ai/en/headerimage/generatedHeaderImage-1773755451286.jpg"/&gt;&lt;p&gt;At QCon London 2026, Lan Chu, AI tech lead at Rabobank, shared lessons from deploying a production AI search system used internally by more than 300 users across 10,000 documents. Her experience shows that most failures in RAG systems stem from indexing and retrieval, rather than the language model itself.&lt;/p&gt; &lt;i&gt;By Daniel Dominguez&lt;/i&gt;</description>
      <category>QCon Software Development Conference</category>
      <category>Artificial Intelligence</category>
      <category>Generative AI</category>
      <category>QCon London 2026</category>
      <category>Retrieval-Augmented Generation</category>
      <category>Natural Language Processing</category>
      <category>Data Science</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Tue, 17 Mar 2026 16:44:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/03/retrieval-production-ai/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Natural+Language+Processing</guid>
      <dc:creator>Daniel Dominguez</dc:creator>
      <dc:date>2026-03-17T16:44:00Z</dc:date>
      <dc:identifier>/news/2026/03/retrieval-production-ai/en</dc:identifier>
    </item>
  </channel>
</rss>
