<?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 Re: How to serve a Unity Catalog ML model to external usage in Machine Learning</title>
    <link>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102229#M3849</link>
    <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/136530"&gt;@johndoe99012&lt;/a&gt;&amp;nbsp;,&lt;BR /&gt;&lt;BR /&gt;You pay for DBU-s.&lt;/P&gt;&lt;P&gt;If you select "scale to zero", you do not pay anything, but at the same time the endpoint is not started.&lt;BR /&gt;So the first HTTP request sent will take a while and this is not recommended for production.&lt;BR /&gt;&lt;BR /&gt;If you select Small compute without scaling to zero you will be using 1-4 DBUs,&lt;BR /&gt;So when there are no requests or there are limited number of requests you will pay for 1 DBUs, so 0.07 USD as per documentation. If there are many requests and the endpoint is scaled-out to its max 4 DBUs, you will pay 4 x 0.07 USD = 0.28 USD per hour.&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="filipniziol_0-1734349406586.png" style="width: 400px;"&gt;&lt;img src="https://community.databricks.com/t5/image/serverpage/image-id/13551i29DA0D46172FAD37/image-size/medium?v=v2&amp;amp;px=400" role="button" title="filipniziol_0-1734349406586.png" alt="filipniziol_0-1734349406586.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Mon, 16 Dec 2024 11:48:03 GMT</pubDate>
    <dc:creator>filipniziol</dc:creator>
    <dc:date>2024-12-16T11:48:03Z</dc:date>
    <item>
      <title>How to serve a Unity Catalog ML model to external usage</title>
      <link>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102201#M3846</link>
      <description>&lt;P&gt;Hello everyone&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I am following this notebook tutorial&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;A href="https://docs.databricks.com/en/machine-learning/manage-model-lifecycle/index.html#example-notebook" target="_blank"&gt;https://docs.databricks.com/en/machine-learning/manage-model-lifecycle/index.html#example-notebook&lt;/A&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Now I can register a machine learning model in Unity Catalog, but the tutorial only shows how to use that from databricks inside.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;How could I deploy the model for external usage, for instance, to call the model via an API from my computer (similar to AWS API Gateway)?&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Many thanks&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 16 Dec 2024 07:14:14 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102201#M3846</guid>
      <dc:creator>johndoe99012</dc:creator>
      <dc:date>2024-12-16T07:14:14Z</dc:date>
    </item>
    <item>
      <title>Re: How to serve a Unity Catalog ML model to external usage</title>
      <link>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102219#M3847</link>
      <description>&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Hi &lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/136530"&gt;@johndoe99012&lt;/a&gt;&amp;nbsp;,&lt;/P&gt;&lt;P&gt;If you want to make a registered Databricks model accessible via external calls—similar to how you might use AWS API Gateway—you can leverage &lt;STRONG&gt;Databricks Model Serving&lt;/STRONG&gt;. This feature allows you to host a model as a REST endpoint and interact with it from outside Databricks.&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="filipniziol_1-1734348633833.png" style="width: 400px;"&gt;&lt;img src="https://community.databricks.com/t5/image/serverpage/image-id/13549i19C8EA9C3FC74985/image-size/medium?v=v2&amp;amp;px=400" role="button" title="filipniziol_1-1734348633833.png" alt="filipniziol_1-1734348633833.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&lt;STRONG&gt;Key Steps:&lt;/STRONG&gt;&lt;/P&gt;&lt;OL&gt;&lt;LI&gt;&lt;P&gt;&lt;STRONG&gt;Enable Model Serving:&lt;/STRONG&gt;&lt;BR /&gt;Ensure that your workspace is in a region where Model Serving is supported. You can find the list of supported regions here:&lt;BR /&gt;&lt;A href="https://learn.microsoft.com/en-us/azure/databricks/resources/feature-region-support#azure-model-serving" target="_new" rel="noopener"&gt;&lt;SPAN&gt;Azure&lt;/SPAN&gt;&lt;SPAN&gt; Databricks&lt;/SPAN&gt;&lt;SPAN&gt; Feature&lt;/SPAN&gt;&lt;SPAN&gt; &amp;amp; Region&lt;/SPAN&gt;&lt;SPAN&gt; Support&lt;/SPAN&gt;&lt;SPAN&gt; – Model&lt;/SPAN&gt;&lt;SPAN&gt; Serving&lt;/SPAN&gt;&lt;/A&gt;&lt;/P&gt;&lt;/LI&gt;&lt;LI&gt;&lt;P&gt;&lt;STRONG&gt;Deploy Your Model to a Serving Endpoint:&lt;/STRONG&gt;&lt;BR /&gt;Once your model is registered in Unity Catalog, you can create a serving endpoint from the Databricks UI or via the CLI.&lt;BR /&gt;&lt;A href="https://docs.databricks.com/en/machine-learning/model-serving/index.html" target="_new" rel="noopener"&gt;&lt;SPAN&gt;Databricks&lt;/SPAN&gt;&lt;SPAN&gt; Documentation&lt;/SPAN&gt;&lt;SPAN&gt; on&lt;/SPAN&gt;&lt;SPAN&gt; Model&lt;/SPAN&gt;&lt;SPAN&gt; Serving&lt;/SPAN&gt;&lt;/A&gt;&lt;/P&gt;&lt;/LI&gt;&lt;LI&gt;&lt;P&gt;&lt;STRONG&gt;Obtain the Endpoint URL and Authentication Credentials:&lt;/STRONG&gt;&lt;BR /&gt;After the serving endpoint is live, Databricks provides a REST URL. You can call this URL from your external applications using standard HTTP requests. You'll need to include the appropriate authentication token.&lt;/P&gt;&lt;/LI&gt;&lt;/OL&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="filipniziol_2-1734348704381.png" style="width: 400px;"&gt;&lt;img src="https://community.databricks.com/t5/image/serverpage/image-id/13550iEBE7539652B0AEE7/image-size/medium?v=v2&amp;amp;px=400" role="button" title="filipniziol_2-1734348704381.png" alt="filipniziol_2-1734348704381.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 16 Dec 2024 11:32:09 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102219#M3847</guid>
      <dc:creator>filipniziol</dc:creator>
      <dc:date>2024-12-16T11:32:09Z</dc:date>
    </item>
    <item>
      <title>Re: How to serve a Unity Catalog ML model to external usage</title>
      <link>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102220#M3848</link>
      <description>&lt;P&gt;Thank you for your great answer. I am trying to understand the pricing of Mosaic pricing schema and I found this URL:&amp;nbsp;&lt;A href="https://www.databricks.com/product/pricing/model-serving" target="_blank"&gt;https://www.databricks.com/product/pricing/model-serving&lt;/A&gt;.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;If I understand correctly, Mosaic will charge me similar to Lambda in AWS, i.e. I pay as I call Mosaic API.&lt;/P&gt;</description>
      <pubDate>Mon, 16 Dec 2024 11:36:57 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102220#M3848</guid>
      <dc:creator>johndoe99012</dc:creator>
      <dc:date>2024-12-16T11:36:57Z</dc:date>
    </item>
    <item>
      <title>Re: How to serve a Unity Catalog ML model to external usage</title>
      <link>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102229#M3849</link>
      <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/136530"&gt;@johndoe99012&lt;/a&gt;&amp;nbsp;,&lt;BR /&gt;&lt;BR /&gt;You pay for DBU-s.&lt;/P&gt;&lt;P&gt;If you select "scale to zero", you do not pay anything, but at the same time the endpoint is not started.&lt;BR /&gt;So the first HTTP request sent will take a while and this is not recommended for production.&lt;BR /&gt;&lt;BR /&gt;If you select Small compute without scaling to zero you will be using 1-4 DBUs,&lt;BR /&gt;So when there are no requests or there are limited number of requests you will pay for 1 DBUs, so 0.07 USD as per documentation. If there are many requests and the endpoint is scaled-out to its max 4 DBUs, you will pay 4 x 0.07 USD = 0.28 USD per hour.&lt;/P&gt;&lt;P&gt;&lt;span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="filipniziol_0-1734349406586.png" style="width: 400px;"&gt;&lt;img src="https://community.databricks.com/t5/image/serverpage/image-id/13551i29DA0D46172FAD37/image-size/medium?v=v2&amp;amp;px=400" role="button" title="filipniziol_0-1734349406586.png" alt="filipniziol_0-1734349406586.png" /&gt;&lt;/span&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 16 Dec 2024 11:48:03 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102229#M3849</guid>
      <dc:creator>filipniziol</dc:creator>
      <dc:date>2024-12-16T11:48:03Z</dc:date>
    </item>
    <item>
      <title>Re: How to serve a Unity Catalog ML model to external usage</title>
      <link>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102286#M3850</link>
      <description>&lt;P&gt;&lt;SPAN&gt;Hi&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/136530"&gt;@johndoe99012&lt;/a&gt;&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;If the answer resolved your question, please consider marking it as the solution. &lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;It helps others in the community find answers more easily.&amp;nbsp;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 16 Dec 2024 18:02:33 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/how-to-serve-a-unity-catalog-ml-model-to-external-usage/m-p/102286#M3850</guid>
      <dc:creator>filipniziol</dc:creator>
      <dc:date>2024-12-16T18:02:33Z</dc:date>
    </item>
  </channel>
</rss>

