<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Production Grade AI system with Agents capability in Databricks in Generative AI</title>
    <link>https://community.databricks.com/t5/generative-ai/production-grade-ai-system-with-agents-capability-in-databricks/m-p/124780#M1011</link>
    <description>&lt;P&gt;Design AI System for Customer Sentiments Analysis with Agentic Bot.&lt;/P&gt;&lt;P&gt;May someone please share how to architect such system in Databricks.&lt;/P&gt;&lt;OL&gt;&lt;LI&gt;Infrastructure on Azure&lt;/LI&gt;&lt;LI&gt;Data Pipeline&lt;/LI&gt;&lt;LI&gt;Model Training&lt;/LI&gt;&lt;LI&gt;Model Testing&lt;/LI&gt;&lt;LI&gt;Choosing Best Model&lt;/LI&gt;&lt;LI&gt;Model Deployment&lt;/LI&gt;&lt;LI&gt;Model Consumtion&lt;/LI&gt;&lt;/OL&gt;&lt;P&gt;Please share your expertise on how to design from Data to AI to Model Deployment in Production&lt;/P&gt;&lt;P&gt;Do we also need Vector DB.&lt;/P&gt;&lt;P&gt;Kindly share your expertise.&lt;/P&gt;&lt;P&gt;Thanks a lot&lt;/P&gt;</description>
    <pubDate>Thu, 10 Jul 2025 11:22:41 GMT</pubDate>
    <dc:creator>Pratikmsbsvm</dc:creator>
    <dc:date>2025-07-10T11:22:41Z</dc:date>
    <item>
      <title>Production Grade AI system with Agents capability in Databricks</title>
      <link>https://community.databricks.com/t5/generative-ai/production-grade-ai-system-with-agents-capability-in-databricks/m-p/124780#M1011</link>
      <description>&lt;P&gt;Design AI System for Customer Sentiments Analysis with Agentic Bot.&lt;/P&gt;&lt;P&gt;May someone please share how to architect such system in Databricks.&lt;/P&gt;&lt;OL&gt;&lt;LI&gt;Infrastructure on Azure&lt;/LI&gt;&lt;LI&gt;Data Pipeline&lt;/LI&gt;&lt;LI&gt;Model Training&lt;/LI&gt;&lt;LI&gt;Model Testing&lt;/LI&gt;&lt;LI&gt;Choosing Best Model&lt;/LI&gt;&lt;LI&gt;Model Deployment&lt;/LI&gt;&lt;LI&gt;Model Consumtion&lt;/LI&gt;&lt;/OL&gt;&lt;P&gt;Please share your expertise on how to design from Data to AI to Model Deployment in Production&lt;/P&gt;&lt;P&gt;Do we also need Vector DB.&lt;/P&gt;&lt;P&gt;Kindly share your expertise.&lt;/P&gt;&lt;P&gt;Thanks a lot&lt;/P&gt;</description>
      <pubDate>Thu, 10 Jul 2025 11:22:41 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/production-grade-ai-system-with-agents-capability-in-databricks/m-p/124780#M1011</guid>
      <dc:creator>Pratikmsbsvm</dc:creator>
      <dc:date>2025-07-10T11:22:41Z</dc:date>
    </item>
    <item>
      <title>Re: Production Grade AI system with Agents capability in Databricks</title>
      <link>https://community.databricks.com/t5/generative-ai/production-grade-ai-system-with-agents-capability-in-databricks/m-p/124799#M1013</link>
      <description>&lt;P&gt;hi&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/143693"&gt;@Pratikmsbsvm&lt;/a&gt;&amp;nbsp;&lt;BR /&gt;That feels like a good sized project. My recommendation would be starting with a similar project and working from there. This might be a useful source for you to understand how this will look:&amp;nbsp;&lt;A href="https://www.databricks.com/blog/step-step-guide-ai-powered-customer-sentiment-analysis" target="_blank"&gt;https://www.databricks.com/blog/step-step-guide-ai-powered-customer-sentiment-analysis&lt;/A&gt;&lt;/P&gt;&lt;P&gt;I'd recommend you start with your steps laid out - get your infrastructure up, push your data into Databricks and then start looking to learn modelling.&lt;/P&gt;&lt;P&gt;Is there a particular part you're stuck on?&lt;/P&gt;</description>
      <pubDate>Thu, 10 Jul 2025 14:09:49 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/production-grade-ai-system-with-agents-capability-in-databricks/m-p/124799#M1013</guid>
      <dc:creator>TheOC</dc:creator>
      <dc:date>2025-07-10T14:09:49Z</dc:date>
    </item>
  </channel>
</rss>

