CINXE.COM
<!doctype html> <html lang="en" dir="ltr" class="blog-wrapper blog-post-page plugin-blog plugin-id-blog-60daysofIA" data-has-hydrated="false"> <head> <meta charset="UTF-8"> <meta name="generator" content="Docusaurus v3.0.0"> <title data-rh="true">2.1 Forecasting Energy Usage with Intelligent Apps Part 1: Laying the Groundwork with AKS, KAITO, and LLaMA | Build Intelligent Apps On Azure</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docusaurus_tag" content="default"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docsearch:docusaurus_tag" content="default"><meta data-rh="true" name="og:title" content="#IntelligentApps start today | Microsoft Azure"><meta data-rh="true" name="og:description" content="Develop adaptive, responsive, and personalized experiences by building and modernizing intelligent applications with Azure!"><meta data-rh="true" name="og:url" content="https://aka.ms/FallForIA"><meta data-rh="true" name="twitter:site" content="@AzureAdvocates"><meta data-rh="true" name="awa-env" content="Production"><meta data-rh="true" name="description" content="In this series, you’ll create an Intelligent App powered by Azure Kubernetes Service (AKS) to forecast energy usage and cost."><meta data-rh="true" name="keywords" content="Cloud-Scale,Data,AI,AI/ML,intelligent apps,cloud-native,60-days,enterprise apps,digital experiences,app modernization"><meta data-rh="true" property="article:published_time" content="2024-03-05T09:00:00.000Z"><meta data-rh="true" property="article:author" content="https://azure.github.io/Cloud-Native/Build-IA/"><meta data-rh="true" property="article:tag" content="Build-Intelligent-Apps,60-days-of-IA,learn-live,hack-together,community-buzz,ask-the-expert,azure-kubernetes-service,azure-functions,azure-openai,azure-container-apps,azure-cosmos-db,github-copilot,github-codespaces,github-actions"><meta data-rh="true" property="og:url" content="https://azure.github.io/cloud-native/60daysofia/forecasting-energy-usage-with-intelligent-apps-1"><meta data-rh="true" property="og:type" content="website"><meta data-rh="true" property="og:title" content="Build Intelligent Apps | AI Apps on Azure"><meta data-rh="true" property="og:description" content="In this series, you'll create an Intelligent App powered by Azure Kubernetes Service (AKS) to forecast energy usage and cost."><meta data-rh="true" property="og:image" content="https://github.com/Azure/Cloud-Native/blob/main/website/static/img/ogImage.png"><meta data-rh="true" name="twitter:url" content="https://azure.github.io/Cloud-Native/60daysofIA/forecasting-energy-usage-with-intelligent-apps-1"><meta data-rh="true" name="twitter:title" content="Build Intelligent Apps | AI Apps on Azure"><meta data-rh="true" name="twitter:description" content="In this series, you'll create an Intelligent App powered by Azure Kubernetes Service (AKS) to forecast energy usage and cost."><meta data-rh="true" name="twitter:image" content="https://azure.github.io/Cloud-Native/img/ogImage.png"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" name="twitter:creator" content="@devanshidiaries"><link data-rh="true" rel="icon" href="/Cloud-Native/img/favicon.ico"><link data-rh="true" rel="alternate" href="https://azure.github.io/Cloud-Native/60DaysOfIA/forecasting-energy-usage-with-intelligent-apps-1" hreflang="en"><link data-rh="true" rel="alternate" href="https://azure.github.io/Cloud-Native/60DaysOfIA/forecasting-energy-usage-with-intelligent-apps-1" hreflang="x-default"><link data-rh="true" rel="canonical" href="https://azure.github.io/Cloud-Native/60daysofIA/forecasting-energy-usage-with-intelligent-apps-1"><link rel="alternate" type="application/rss+xml" href="/Cloud-Native/blog/rss.xml" title="Build Intelligent Apps On Azure RSS Feed"> <link rel="alternate" type="application/atom+xml" href="/Cloud-Native/blog/atom.xml" title="Build Intelligent Apps On Azure Atom Feed"> <link rel="alternate" type="application/rss+xml" href="/Cloud-Native/cnny-2023/rss.xml" title="Build Intelligent Apps On Azure RSS Feed"> <link rel="alternate" type="application/atom+xml" href="/Cloud-Native/cnny-2023/atom.xml" title="Build Intelligent Apps On Azure Atom Feed"> <link rel="alternate" type="application/rss+xml" href="/Cloud-Native/30DaysOfIA/rss.xml" title="Build Intelligent Apps On Azure RSS Feed"> <link rel="alternate" type="application/atom+xml" href="/Cloud-Native/30DaysOfIA/atom.xml" title="Build Intelligent Apps On Azure Atom Feed"> <link rel="alternate" type="application/rss+xml" href="/Cloud-Native/60DaysOfIA/rss.xml" title="Build Intelligent Apps On Azure RSS Feed"> <link rel="alternate" type="application/atom+xml" href="/Cloud-Native/60DaysOfIA/atom.xml" title="Build Intelligent Apps On Azure Atom Feed"> <link rel="alternate" type="application/rss+xml" href="/Cloud-Native/30-days-of-ia-2024/rss.xml" title="Build Intelligent Apps On Azure RSS Feed"> <link rel="alternate" type="application/atom+xml" href="/Cloud-Native/30-days-of-ia-2024/atom.xml" title="Build Intelligent Apps On Azure Atom Feed"> <script>!function(t,e,n,c,a,r,s){t[n]=t[n]||function(){(t[n].q=t[n].q||[]).push(arguments)},(r=e.createElement(c)).async=1,r.src="https://www.clarity.ms/tag/d61n997vq9",(s=e.getElementsByTagName(c)[0]).parentNode.insertBefore(r,s)}(window,document,"clarity","script")</script> <script src="https://code.jquery.com/jquery-3.7.1.min.js"></script> <script src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js"></script><link rel="stylesheet" href="/Cloud-Native/assets/css/styles.cf5fa7e1.css"> <script src="/Cloud-Native/assets/js/runtime~main.ae48de5c.js" defer="defer"></script> <script src="/Cloud-Native/assets/js/main.4bf38dd3.js" defer="defer"></script> </head> <body class="navigation-with-keyboard"> <script>!function(){function t(t){document.documentElement.setAttribute("data-theme",t)}var e=function(){try{return new URLSearchParams(window.location.search).get("docusaurus-theme")}catch(t){}}()||function(){try{return localStorage.getItem("theme")}catch(t){}}();null!==e?t(e):window.matchMedia("(prefers-color-scheme: dark)").matches?t("dark"):(window.matchMedia("(prefers-color-scheme: light)").matches,t("light"))}(),function(){try{const c=new URLSearchParams(window.location.search).entries();for(var[t,e]of c)if(t.startsWith("docusaurus-data-")){var a=t.replace("docusaurus-data-","data-");document.documentElement.setAttribute(a,e)}}catch(t){}}()</script><div id="__docusaurus"><div role="region" aria-label="Skip to main content"><a class="skipToContent_fXgn" href="#__docusaurus_skipToContent_fallback">Skip to main content</a></div><header><div></div></header><nav aria-label="Main" class="navbar navbar--fixed-top"><div class="navbar__inner"><div class="navbar__items"><a class="navbar__brand" href="/Cloud-Native/"></a></div><div class="navbar__items navbar__items--right"><div class="toggle_vylO colorModeToggle_DEke"><button class="clean-btn toggleButton_gllP toggleButtonDisabled_aARS" type="button" disabled="" title="Switch between dark and light mode (currently light mode)" aria-label="Switch between dark and light mode (currently light mode)" aria-live="polite"><svg viewBox="0 0 24 24" width="24" height="24" class="lightToggleIcon_pyhR"><path fill="currentColor" d="M12,9c1.65,0,3,1.35,3,3s-1.35,3-3,3s-3-1.35-3-3S10.35,9,12,9 M12,7c-2.76,0-5,2.24-5,5s2.24,5,5,5s5-2.24,5-5 S14.76,7,12,7L12,7z M2,13l2,0c0.55,0,1-0.45,1-1s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S1.45,13,2,13z M20,13l2,0c0.55,0,1-0.45,1-1 s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S19.45,13,20,13z M11,2v2c0,0.55,0.45,1,1,1s1-0.45,1-1V2c0-0.55-0.45-1-1-1S11,1.45,11,2z M11,20v2c0,0.55,0.45,1,1,1s1-0.45,1-1v-2c0-0.55-0.45-1-1-1C11.45,19,11,19.45,11,20z M5.99,4.58c-0.39-0.39-1.03-0.39-1.41,0 c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0s0.39-1.03,0-1.41L5.99,4.58z M18.36,16.95 c-0.39-0.39-1.03-0.39-1.41,0c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0c0.39-0.39,0.39-1.03,0-1.41 L18.36,16.95z M19.42,5.99c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06c-0.39,0.39-0.39,1.03,0,1.41 s1.03,0.39,1.41,0L19.42,5.99z M7.05,18.36c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06 c-0.39,0.39-0.39,1.03,0,1.41s1.03,0.39,1.41,0L7.05,18.36z"></path></svg><svg viewBox="0 0 24 24" width="24" height="24" class="darkToggleIcon_wfgR"><path fill="currentColor" d="M9.37,5.51C9.19,6.15,9.1,6.82,9.1,7.5c0,4.08,3.32,7.4,7.4,7.4c0.68,0,1.35-0.09,1.99-0.27C17.45,17.19,14.93,19,12,19 c-3.86,0-7-3.14-7-7C5,9.07,6.81,6.55,9.37,5.51z M12,3c-4.97,0-9,4.03-9,9s4.03,9,9,9s9-4.03,9-9c0-0.46-0.04-0.92-0.1-1.36 c-0.98,1.37-2.58,2.26-4.4,2.26c-2.98,0-5.4-2.42-5.4-5.4c0-1.81,0.89-3.42,2.26-4.4C12.92,3.04,12.46,3,12,3L12,3z"></path></svg></button></div><div class="navbarSearchContainer_Bca1"></div></div></div><div role="presentation" class="navbar-sidebar__backdrop"></div></nav><div class="announcementBarBackground_Iz1u"><div class="container"><div class="row"><div class="col col--8 col--offset-2 announcementBarContainer_QNjo"><div class="col-demo"><p class="announcementBarContent_tvcd">Learn to use <a class="announcementLink_qKCm" target="_blank" href="https://developer.microsoft.com/reactor/events/23599/?ocid=biafy25h1_cn_webpage_azuremktg" data-bi-area="AnnouncementBar" data-bi-name="Announcement">Azure Functions OpenAI to ingest your own content</a> | Give us a 🌟 <a class="announcementLink_qKCm" target="_blank" href="https://github.com/azure/cloud-native" data-bi-area="AnnouncementBar" data-bi-name="Give us a star on GitHub">on GitHub</a></p></div></div><div class="col col--2 announcementBarIconContainer_GQot"><div class="col-demo"><a href="https://github.com/azure/cloud-native" target="_blank" class="icon_QeTG" aria-label="Visit us on GitHub"><svg width="24" height="24" viewBox="0 0 24 24" xmlns="http://www.w3.org/2000/svg" fill="#FFFFFF"><path d="M12 .297c-6.63 0-12 5.373-12 12 0 5.303 3.438 9.8 8.205 11.385.6.113.82-.258.82-.577 0-.285-.01-1.04-.015-2.04-3.338.724-4.042-1.61-4.042-1.61C4.422 18.07 3.633 17.7 3.633 17.7c-1.087-.744.084-.729.084-.729 1.205.084 1.838 1.236 1.838 1.236 1.07 1.835 2.809 1.305 3.495.998.108-.776.417-1.305.76-1.605-2.665-.3-5.466-1.332-5.466-5.93 0-1.31.465-2.38 1.235-3.22-.135-.303-.54-1.523.105-3.176 0 0 1.005-.322 3.3 1.23.96-.267 1.98-.399 3-.405 1.02.006 2.04.138 3 .405 2.28-1.552 3.285-1.23 3.285-1.23.645 1.653.24 2.873.12 3.176.765.84 1.23 1.91 1.23 3.22 0 4.61-2.805 5.625-5.475 5.92.42.36.81 1.096.81 2.22 0 1.606-.015 2.896-.015 3.286 0 .315.21.69.825.57C20.565 22.092 24 17.592 24 12.297c0-6.627-5.373-12-12-12"></path></svg></a><a href="https://azure.github.io/Cloud-Native/60DaysOfIA/rss.xml" target="_blank" class="icon_QeTG" aria-label="Subscribe to RSS"><svg width="24" height="24" viewBox="0 0 333333 333333" xmlns="http://www.w3.org/2000/svg" fill="#f49c4f"><path d="M166667 0c92048 0 166667 74619 166667 166667s-74619 166667-166667 166667S0 258715 0 166667 74619 0 166667 0zm-57698 203357c-11551 0-20938 9418-20938 20897 0 11537 9386 20857 20938 20857 11587 0 20967-9320 20967-20857 0-11479-9378-20897-20967-20897zm-20918-61899v30148c19632 0 38081 7677 51977 21585 13883 13868 21548 32406 21548 52114h30276c0-57254-46585-103838-103801-103838v-9zm38-53431v30154c70007 0 126979 57031 126979 127116l30235 3c0-86697-70539-157270-157212-157270l-2-3z"></path></svg></a><svg viewBox="0 0 24 24" width="24" height="24" class="icon_Kj6K"><path fill="white" d="M12,9c1.65,0,3,1.35,3,3s-1.35,3-3,3s-3-1.35-3-3S10.35,9,12,9 M12,7c-2.76,0-5,2.24-5,5s2.24,5,5,5s5-2.24,5-5 S14.76,7,12,7L12,7z M2,13l2,0c0.55,0,1-0.45,1-1s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S1.45,13,2,13z M20,13l2,0c0.55,0,1-0.45,1-1 s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S19.45,13,20,13z M11,2v2c0,0.55,0.45,1,1,1s1-0.45,1-1V2c0-0.55-0.45-1-1-1S11,1.45,11,2z M11,20v2c0,0.55,0.45,1,1,1s1-0.45,1-1v-2c0-0.55-0.45-1-1-1C11.45,19,11,19.45,11,20z M5.99,4.58c-0.39-0.39-1.03-0.39-1.41,0 c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0s0.39-1.03,0-1.41L5.99,4.58z M18.36,16.95 c-0.39-0.39-1.03-0.39-1.41,0c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0c0.39-0.39,0.39-1.03,0-1.41 L18.36,16.95z M19.42,5.99c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06c-0.39,0.39-0.39,1.03,0,1.41 s1.03,0.39,1.41,0L19.42,5.99z M7.05,18.36c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06 c-0.39,0.39-0.39,1.03,0,1.41s1.03,0.39,1.41,0L7.05,18.36z"></path></svg></div></div></div></div></div><div id="__docusaurus_skipToContent_fallback" class="main-wrapper mainWrapper_z2l0"><div class="container margin-vert--lg"><div class="row"><aside class="col col--3"><nav class="sidebar_re4s thin-scrollbar" aria-label="Blog recent posts navigation"><div class="sidebarItemTitle_pO2u margin-bottom--md">#60DaysOfIA</div><ul class="sidebarItemList_Yudw clean-list"><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/kick-off">Kick-off #60Days of IA</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/harnessing-the-power-of-intelligent-apps">1. Harnessing the power of Intelligent Apps</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/power-up-crafting-an-intelligent-energy-forecasting-application-using-azure-kubernetes-service">2. Power Up: Crafting an Intelligent Energy Forecasting Application Using Azure Kubernetes Service</a></li><li class="sidebarItem__DBe"><a aria-current="page" class="sidebarItemLink_mo7H sidebarItemLinkActive_I1ZP" href="/Cloud-Native/60DaysOfIA/forecasting-energy-usage-with-intelligent-apps-1">2.1 Forecasting Energy Usage with Intelligent Apps Part 1: Laying the Groundwork with AKS, KAITO, and LLaMA</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/forecasting-energy-usage-with-intelligent-apps-2">2.2 Forecasting Energy Usage with Intelligent Apps Part 2</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/forecasting-energy-usage-with-intelligent-apps-3">2.3 Forecasting Energy Usage with Intelligent Apps Part 3</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/cosmos-db-and-intelligent-apps-a-match-made-for-innovation">3. Cosmos DB and Intelligent Apps: A Match Made for Innovation</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/dynamic-repricing-of-products-using-intelligent-apps-part-1">3.1 Dynamic Repricing of Products Using Intelligent Apps Part 1</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/dynamic-repricing-of-products-using-intelligent-apps-part-2">3.2 Dynamic Repricing of Products Using Intelligent Apps Part 2</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/dynamic-repricing-of-products-using-intelligent-apps-part-3">3.3 Dynamic Repricing of Products Using Intelligent Apps Part 3: Graphing and Displaying Price Forecasts in a Web Interface</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/fuel-your-intelligent-apps-with-azure-ai">4. Fuel Your Intelligent Apps with Azure AI</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/build-contoso-chat-end-to-end">4.1 Build Contoso Chat End-to-End</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/build-a-copilot-code-first-with-the-azure-ai-python-sdk">4.2 Build A Copilot Code-First with the Azure AI Python SDK</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/build-a-copilot-on-azure-code-first-with-prompt-flow">4.3 Build a Copilot on Azure Code-First with Prompt Flow</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/build-a-copilot-on-azure-code-first-with-langchain">4.4 Build a Copilot on Azure Code-First with Langchain</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/deploying-your-copilot-on-azure">4.5 Deploying Your Copilot On Azure</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/the-role-of-platform-engineering-in-developing-intelligent-apps">5 The Role of Platform Engineering in Developing Intelligent Apps</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/creating-a-virtual-stylist-chatbot-part-1">6.1 Creating a Virtual Stylist Chatbot — Part 1: Analyzing Images with AI</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/creating-a-virtual-stylist-chatbot-part-2">6.2 Creating a Virtual Stylist Chatbot — Part 2: Adding a Chatbot Interface</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/creating-a-virtual-stylist-chatbot-part-3">6.3 Creating a Virtual Stylist Chatbot — Part 3: Deploying the App</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/building-a-multichannel-notification-system-1">6.4 Building a Multichannel Notification System (1)</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/building-a-multichannel-notification-system-2">6.5 Building a Multichannel Notification System (2)</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/personalizing-education-with-generative-ai-and-retrieval-augmented-generation-1">7.1 Personalizing Education with Generative AI and Retrieval Augmented Generation Part 1</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/personalizing-education-with-generative-ai-and-retrieval-augmented-generation-2">7.2 Personalizing Education with Generative AI and Retrieval Augmented Generation Part 2</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/personalizing-education-with-generative-ai-and-retrieval-augmented-generation-3">7.3 Personalizing Education with Generative AI and Retrieval Augmented Generation Part 3</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/real-time-voice-sentiment-analysis-system-1">7.4 Real-time Voice Sentiment Analysis System 1</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/real-time-voice-sentiment-analysis-system-2">7.5 Real-time Voice Sentiment Analysis System 2</a></li><li class="sidebarItem__DBe"><a class="sidebarItemLink_mo7H" href="/Cloud-Native/60DaysOfIA/managing-the-cost-of-intelligent-apps">8 Managing the Cost of Intelligent Apps</a></li></ul></nav></aside><main class="col col--7" itemscope="" itemtype="https://schema.org/Blog"><article itemprop="blogPost" itemscope="" itemtype="https://schema.org/BlogPosting"><meta itemprop="description" content="In this series, you’ll create an Intelligent App powered by Azure Kubernetes Service (AKS) to forecast energy usage and cost."><link itemprop="image" href="https://github.com/Azure/Cloud-Native/blob/main/website/static/img/ogImage.png"><meta itemprop="keywords" content="Cloud-Scale,Data,AI,AI/ML,intelligent apps,cloud-native,60-days,enterprise apps,digital experiences,app modernization"><header><h1 class="title_f1Hy" itemprop="headline">2.1 Forecasting Energy Usage with Intelligent Apps Part 1: Laying the Groundwork with AKS, KAITO, and LLaMA</h1><div class="container_mt6G margin-vert--md"><time datetime="2024-03-05T09:00:00.000Z" itemprop="datePublished">March 5, 2024</time> · <!-- -->7 min read</div><div class="margin-top--md margin-bottom--sm row"><div class="col col--6 authorCol_Hf19"><div class="avatar margin-bottom--sm"><a href="https://azure.github.io/Cloud-Native/Build-IA/" target="_blank" rel="noopener noreferrer" class="avatar__photo-link"><img class="avatar__photo" src="https://azure.github.io/Cloud-Native/img/logo-2024.png" alt="#60Days Of IA" itemprop="image"></a><div class="avatar__intro" itemprop="author" itemscope="" itemtype="https://schema.org/Person"><div class="avatar__name"><a href="https://azure.github.io/Cloud-Native/Build-IA/" target="_blank" rel="noopener noreferrer" itemprop="url"><span itemprop="name">#60Days Of IA</span></a></div><small class="avatar__subtitle" itemprop="description">BuildIA Content Team</small></div></div></div></div></header><div id="__blog-post-container" class="markdown" itemprop="articleBody"> <p><img loading="lazy" alt="Forecasting Energy Usage with Intelligent Apps: Laying the Groundwork with AKS, KAITO, and LLaMA" src="/Cloud-Native/assets/images/2-1-1-f0fc40a7278794b517cea5c2e8b4a789.jpg" width="700" height="426" class="img_ev3q"></p> <p><em>This three-part series demonstrates how to create an Intelligent App that forecasts future energy consumption and pricing based on historical data. In this first article, you’ll set up an Azure Kubernetes Service (AKS) environment, install KAITO, and set up KAITO to work with the LLaMA 2 model.</em></p> <h2 class="anchor anchorWithStickyNavbar_LWe7" id="forecasting-energy-usage-with-intelligent-apps-part-1-laying-the-groundwork-with-aks-kaito-and-llama">Forecasting Energy Usage with Intelligent Apps Part 1: Laying the Groundwork with AKS, KAITO, and LLaMA<a href="#forecasting-energy-usage-with-intelligent-apps-part-1-laying-the-groundwork-with-aks-kaito-and-llama" class="hash-link" aria-label="Direct link to Forecasting Energy Usage with Intelligent Apps Part 1: Laying the Groundwork with AKS, KAITO, and LLaMA" title="Direct link to Forecasting Energy Usage with Intelligent Apps Part 1: Laying the Groundwork with AKS, KAITO, and LLaMA"></a></h2> <p>Intelligent Apps leverage artificial intelligence (AI) and machine learning (ML) technologies to enhance traditional applications with advanced capabilities. They enable businesses to make smarter decisions, automate tasks, and drive innovation by extracting actionable insights from vast amounts of data.</p> <p>In this series, you’ll create an Intelligent App powered by <a href="https://azure.microsoft.com/en-ca/products/kubernetes-service" target="_blank" rel="noopener noreferrer">Azure Kubernetes Service</a> (AKS) to forecast energy usage and cost. Each article will demonstrate the use of core Azure technologies, particularly AKS, to build an application that generates forecasts based on AI capabilities applied to user input and historical data analysis.</p> <p>Let’s get started!</p> <h3 class="anchor anchorWithStickyNavbar_LWe7" id="prerequisites">Prerequisites<a href="#prerequisites" class="hash-link" aria-label="Direct link to Prerequisites" title="Direct link to Prerequisites"></a></h3> <p>To follow this tutorial, ensure you have the following:</p> <ul> <li>An <a href="https://azure.microsoft.com/en-us/free/search" target="_blank" rel="noopener noreferrer">Azure Subscription</a> that supports the GPU-enabled <a href="https://learn.microsoft.com/en-us/azure/virtual-machines/ncv3-series" target="_blank" rel="noopener noreferrer">Standard_NC12s_v3 instance type</a> in the selected region. You might need to request an increase in vCPU quota.</li> <li>Basic understanding of <a href="https://azure.microsoft.com/en-us/products/kubernetes-service" target="_blank" rel="noopener noreferrer">AKS</a> and Kubernetes</li> </ul> <h3 class="anchor anchorWithStickyNavbar_LWe7" id="building-an-intelligent-app-with-azure-kubernetes-service-and-kaito">Building an Intelligent App with Azure Kubernetes Service and KAITO<a href="#building-an-intelligent-app-with-azure-kubernetes-service-and-kaito" class="hash-link" aria-label="Direct link to Building an Intelligent App with Azure Kubernetes Service and KAITO" title="Direct link to Building an Intelligent App with Azure Kubernetes Service and KAITO"></a></h3> <p>This first article walks you through setting up an AKS environment and the Kubernetes AI Toolchain Operator (KAITO) to automate AI/ML model deployment in the AKS cluster.</p> <h4 class="anchor anchorWithStickyNavbar_LWe7" id="downloading-the-llama-2-model">Downloading the LLaMA 2 Model<a href="#downloading-the-llama-2-model" class="hash-link" aria-label="Direct link to Downloading the LLaMA 2 Model" title="Direct link to Downloading the LLaMA 2 Model"></a></h4> <p>A fundamental piece in your Intelligent App’s architecture is the target model. Here, you’ll use LLaMA 2, an open-source project developed by Meta in partnership with Microsoft.</p> <p>LLaMA 2 is a large-scale training and inference framework for ML models. It provides a distributed computing infrastructure that enables executing ML tasks across multiple nodes or clusters, using parallelism and optimization techniques to improve performance.</p> <p>To configure your model, download LLaMA 2 by following the instructions in <a href="https://github.com/Azure/kaito/tree/main/presets/models/llama2" target="_blank" rel="noopener noreferrer">this document</a>. Ensure you download the LLaMA 2 7B Chat (llama2-7b-chat) model.</p> <h4 class="anchor anchorWithStickyNavbar_LWe7" id="configuring-the-aks-cluster-and-kaito">Configuring the AKS Cluster and KAITO<a href="#configuring-the-aks-cluster-and-kaito" class="hash-link" aria-label="Direct link to Configuring the AKS Cluster and KAITO" title="Direct link to Configuring the AKS Cluster and KAITO"></a></h4> <p><img loading="lazy" alt="engergy-usage-aks model" src="/Cloud-Native/assets/images/2-1-2-330abba56cfa621014fbd395b9b6297c.jpg" width="1484" height="694" class="img_ev3q"></p> <p>Creating an AKS environment is the first step for onboarding large AI inference models onto Kubernetes. Later, you’ll integrate the node provisioner controller with AKS APIs, letting you dynamically add GPU nodes to the cluster to promote scalability and optimal resource use.</p> <p>Additionally, AKS facilitates testing service endpoints within the cluster, providing a reliable environment for validating and fine-tuning AI inference services.</p> <p>KAITO is an open-source operator that transforms how you deploy AI models on Kubernetes. It streamlines the process, automating critical tasks like infrastructure provisioning and resource optimization. It intelligently selects the optimal hardware configuration for your specific model, using available CPU and GPU resources on AKS. KAITO eliminates the manual setup complexities, accelerating your deployment time and reducing associated costs.</p> <p>To set up an AKS cluster and install KAITO, follow <a href="https://github.com/Azure/kaito/blob/main/docs/installation.md" target="_blank" rel="noopener noreferrer">this tutorial</a>, adjusting the KAITO installation steps to match the <strong>llama2-7b</strong> model you downloaded earlier.</p> <div class="theme-admonition theme-admonition-info admonition_xJq3 alert alert--info"><div class="admonitionHeading_Gvgb"><span class="admonitionIcon_Rf37"><svg viewBox="0 0 14 16"><path fill-rule="evenodd" d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path></svg></span>info</div><div class="admonitionContent_BuS1"><p>Checkout the <strong><a href="https://aka.ms/learn-live-building-intelligent-apps-aks-ep2?ocid=buildia24_60days_blogs" target="_blank" rel="noopener noreferrer">Intelligent Apps on AKS: Episode 2</a></strong>, a hands-on training with an expert on how to use AKS to run your own AI Models with KAITO.</p></div></div> <h4 class="anchor anchorWithStickyNavbar_LWe7" id="pushing-llama-2-chat-model-to-azure-container-registry">Pushing LLaMA 2 Chat Model to Azure Container Registry<a href="#pushing-llama-2-chat-model-to-azure-container-registry" class="hash-link" aria-label="Direct link to Pushing LLaMA 2 Chat Model to Azure Container Registry" title="Direct link to Pushing LLaMA 2 Chat Model to Azure Container Registry"></a></h4> <p>Now that you have AKS with the KAITO installation, you need to push the local model image to the AKS cluster.</p> <p>Create an Azure Container Registry (ACR) resource using Azure CLI with the following command, replacing <code><YOUR-ACR-NAME></code> with a new ACR name:</p> <div class="codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-text codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">az acr create --name <YOUR-ACR-NAME> --resource-group $RESOURCE_GROUP --sku Standard --location $LOCATION</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div> <p>Now, push your local LLaMA 2 model’s Docker image to the ACR hosted at <code><YOUR-ACR-NAME>.azurecr.io</code> by running:</p> <div class="codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-text codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">docker push <YOUR-ACR-NAME>.azurecr.io/llama2_7b_chat_model:latest</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div> <p>Finally, run the command to update the AKS cluster to attach it to your ACR, allowing the cluster to pull the model container image from <code><YOUR-ACR-NAME>.azurecr.io</code>:</p> <div class="codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-text codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">az aks update -g $RESOURCE_GROUP -n $MY_CLUSTER --attach-acr <YOUR-ACR-NAME></span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div> <h4 class="anchor anchorWithStickyNavbar_LWe7" id="starting-the-inference-service">Starting the Inference Service<a href="#starting-the-inference-service" class="hash-link" aria-label="Direct link to Starting the Inference Service" title="Direct link to Starting the Inference Service"></a></h4> <p>After installing KAITO, run the following command to start a <code>llama-2-7b</code> inference service, replacing <code><YOUR-ACR-NAME></code> with the ACR name you created previously:</p> <div class="codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-text codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">$ cat examples/kaito_workspace_llama2_7b.yaml</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">apiVersion: kaito.sh/v1alpha1</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">kind: Workspace</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">metadata:</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> name: workspace-llama-2-7b</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">resource:</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> instanceType: "Standard_NC12s_v3"</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> labelSelector:</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> matchLabels:</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> apps: llama-2-7b-chat</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">inference:</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> preset:</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> name: "llama-2-7b-chat"</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> accessMode: private</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> presetOptions:</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> image: <YOUR-ACR-NAME>.azurecr.io/llama2_chat_model:latest</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> imagePullSecrets:</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"> - energy-usage-secret</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">$ kubectl apply -f examples/kaito_workspace_llama2_7b-chat.yaml</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div> <p>Kubernetes uses this YAML code to instantiate a workspace resource with the specified configurations. This enables deploying and managing inference workloads within the cluster.</p> <p>You can monitor the workspace status by executing the command below. The model deployment has been completed once the <code>WORKSPACEREADY</code> column becomes <code>True</code>:</p> <div class="codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-text codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">$ kubectl get workspace workspace-llama-2-7b-chat</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">| NAME | INSTANCE | RESOURCEREADY | INFERENCEREADY | WORKSPACEREADY | AGE |</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">| workspace-llama-2-7b-chat | Standard_NC12s_v3 | True | True | True | 4d2h |</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div> <p><strong>Note</strong>: Achieving machine and workspace readiness may take up to 20 minutes.</p> <p>Now, run the command below to find the inference service’s cluster IP:</p> <div class="codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-text codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">$ kubectl get svc workspace-llama-2-7b-chat</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">| NAME | TYPE | CLUSTER-IP | EXTERNAL-IP | PORT(S) | AGE |</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">| workspace-llama-2-7b-chat | ClusterIP | <CLUSTERIP> | <none> | 80/TCP,29500/TCP | 4d2h |</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div> <p>Finally, run a curl pod to test the service endpoint in the cluster:</p> <div class="codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-text codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">export CLUSTERIP=$(kubectl get svc workspace-llama-2-7b-chat -o jsonpath="{.spec.clusterIPs[0]}")</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain" style="display:inline-block"></span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">$ kubectl run -it --rm --restart=Never curl --image=curlimages/curl -- curl -X POST http://$CLUSTERIP/generate -H "accept: application/json" -H "Content-Type: application/json" -d "{\"input_data\": {\"input_string\":[[ {\"role\": \"user\", \"content\": \"What is the capital of India?\"}]]}, \"parameters\": {\"max_gen_len\": 64, \"temperature\": 0}}"</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div> <p>You should receive these results:</p> <div class="codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_biex"><pre tabindex="0" class="prism-code language-text codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">{"results":[[{"role":"User","content":"What is the capital of India?"},{"role":"Assistant","content":" The capital of India is New Delhi."}]]}</span><br></span></code></pre><div class="buttonGroup__atx"><button type="button" aria-label="Copy code to clipboard" title="Copy" class="clean-btn"><span class="copyButtonIcons_eSgA" aria-hidden="true"><svg viewBox="0 0 24 24" class="copyButtonIcon_y97N"><path fill="currentColor" d="M19,21H8V7H19M19,5H8A2,2 0 0,0 6,7V21A2,2 0 0,0 8,23H19A2,2 0 0,0 21,21V7A2,2 0 0,0 19,5M16,1H4A2,2 0 0,0 2,3V17H4V3H16V1Z"></path></svg><svg viewBox="0 0 24 24" class="copyButtonSuccessIcon_LjdS"><path fill="currentColor" d="M21,7L9,19L3.5,13.5L4.91,12.09L9,16.17L19.59,5.59L21,7Z"></path></svg></span></button></div></div></div> <p><strong>Note</strong>: You can test with your own questions, but there may be inaccuracies within the response. This is because AKS hasn’t fine-tuned the model for your scenario.</p> <p>That’s it! You’ve successfully established your AKS environment and familiarized yourself with setting up KAITO to deploy the LLaMA 2 model within your Kubernetes environment. You’re now ready to analyze a model and make predictions using Azure’s AI services.</p> <h2 class="anchor anchorWithStickyNavbar_LWe7" id="next-steps">Next Steps<a href="#next-steps" class="hash-link" aria-label="Direct link to Next Steps" title="Direct link to Next Steps"></a></h2> <p>In this article, you established an AKS cluster and configured KAITO to integrate with the LLaMA 2 model for advanced ML capabilities. In part 2, you’ll use AKS and KAITO to analyze historical energy consumption data with advanced ML models. You’ll create a dynamic web interface for users to input data, generate predictions, and visualize results seamlessly.</p> <p>Be sure to join the <a href="https://azure.github.io/Cloud-Native/Build-IA/CloudSkills" target="_blank" rel="noopener noreferrer">Cloud Skill Challenge</a> to level up your cloud computing skills and gain hands-on experience. You can also register for the <a href="https://aka.ms/learn-live-building-intelligent-apps-aks-ep3?ocid=buildia24_60days_blogs" target="_blank" rel="noopener noreferrer">next episode</a> on <strong>Intelligent Apps with Azure Kubernetes Service</strong>, an instructor led live learning experience to deploy your app on AKS. And, join the AKS product and engineering team at <em>KubeCon EU 2024</em>—the premier conference for cloud-native technologies, for <strong>AKS <a href="https://aka.ms/aks-day" target="_blank" rel="noopener noreferrer">Customer</a> and <a href="https://aka.ms/aks-lab-day" target="_blank" rel="noopener noreferrer">Lab</a> Days</strong>.</p></div><footer class="row docusaurus-mt-lg blogPostFooterDetailsFull_mRVl"><div class="col"><b>Tags:</b><ul class="tags_jXut padding--none margin-left--sm"><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/build-intelligent-apps">Build-Intelligent-Apps</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/60-days-of-ia">60-days-of-IA</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/learn-live">learn-live</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/hack-together">hack-together</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/community-buzz">community-buzz</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/ask-the-expert">ask-the-expert</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/azure-kubernetes-service">azure-kubernetes-service</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/azure-functions">azure-functions</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/azure-openai">azure-openai</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/azure-container-apps">azure-container-apps</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/azure-cosmos-db">azure-cosmos-db</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/github-copilot">github-copilot</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/github-codespaces">github-codespaces</a></li><li class="tag_QGVx"><a class="tag_zVej tagRegular_sFm0" href="/Cloud-Native/60DaysOfIA/tags/github-actions">github-actions</a></li></ul></div></footer></article><nav class="pagination-nav docusaurus-mt-lg" aria-label="Blog post page navigation"><a class="pagination-nav__link pagination-nav__link--prev" href="/Cloud-Native/60DaysOfIA/power-up-crafting-an-intelligent-energy-forecasting-application-using-azure-kubernetes-service"><div class="pagination-nav__sublabel">Newer Post</div><div class="pagination-nav__label">2. Power Up: Crafting an Intelligent Energy Forecasting Application Using Azure Kubernetes Service</div></a><a class="pagination-nav__link pagination-nav__link--next" href="/Cloud-Native/60DaysOfIA/forecasting-energy-usage-with-intelligent-apps-2"><div class="pagination-nav__sublabel">Older Post</div><div class="pagination-nav__label">2.2 Forecasting Energy Usage with Intelligent Apps Part 2</div></a></nav></main><div class="col col--2"><div class="tableOfContents_bqdL thin-scrollbar"><ul class="table-of-contents table-of-contents__left-border"><li><a href="#forecasting-energy-usage-with-intelligent-apps-part-1-laying-the-groundwork-with-aks-kaito-and-llama" class="table-of-contents__link toc-highlight">Forecasting Energy Usage with Intelligent Apps Part 1: Laying the Groundwork with AKS, KAITO, and LLaMA</a><ul><li><a href="#prerequisites" class="table-of-contents__link toc-highlight">Prerequisites</a></li><li><a href="#building-an-intelligent-app-with-azure-kubernetes-service-and-kaito" class="table-of-contents__link toc-highlight">Building an Intelligent App with Azure Kubernetes Service and KAITO</a></li></ul></li><li><a href="#next-steps" class="table-of-contents__link toc-highlight">Next Steps</a></li></ul></div></div></div></div></div><footer><div></div></footer></div> </body> </html>