<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>APIM on Jan-V.nl</title><link>https://jan-v.nl/tags/apim/</link><description>Recent content in APIM on Jan-V.nl</description><generator>Hugo</generator><language>en-us</language><copyright>© 2006-2026 Jan-V.nl All Rights Reserved.</copyright><lastBuildDate>Wed, 24 Jun 2026 12:48:50 +0200</lastBuildDate><atom:link href="https://jan-v.nl/tags/apim/index.xml" rel="self" type="application/rss+xml"/><item><title>Invoke different versions of your service using APIM</title><link>https://jan-v.nl/post/2026/invoke-different-versions-of-your-service-using-apim/</link><pubDate>Wed, 24 Jun 2026 12:48:50 +0200</pubDate><guid>https://jan-v.nl/post/2026/invoke-different-versions-of-your-service-using-apim/</guid><description>&lt;p&gt;I&amp;rsquo;m working on something where I need to deploy multiple versions of my software and validate whether there&amp;rsquo;s an improvement or regression. The solution heavily relies on deployed language models, so that&amp;rsquo;s something we want to evaluate first.&lt;br&gt;
The solution I&amp;rsquo;m working on looks fairly similar to the setup in my &lt;a href="https://github.com/Jandev/trial-and-error"&gt;Trial &amp;amp; Error GitHub repository&lt;/a&gt;, so I have a .NET frontend service and a Python backend service, both invoking language models deployed in Microsoft Foundry.&lt;/p&gt;</description></item></channel></rss>