What is Azure AI Foundry?<\/h2>\n
Azure AI Foundry is Microsoft’s managed platform that handles the entire AI application lifecycle, with key focus on generative AI and modern AI development. <\/p>\n
Think of it as like a complete toolkit for building modern AI applications at enterprise scale.<\/p>\n
Instead of starting from scratch, you get access to a massive catalog of over 1900+ pre-trained models<\/strong> from various providers. <\/p>\n You can also build RAG applications using your company’s data, manage prompts and LLM workflows, and handle both traditional MLOps and the newer LLMOps<\/strong> requirements.<\/p>\n In short, if you’re looking for a one-stop solution to build, train, deploy, and scale AI applications without stitching together multiple separate services, Azure AI Foundry is the service you need.<\/p>\n When we first started using Azure AI Foundry, it was quite confusing.<\/p>\n There is a separate AI Foundry portal, and then there is also an AI Foundry service inside the Azure portal.<\/p>\n So before you begin, it’s important to understand these two key concepts in Azure AI Foundry. In this blog, we will be looking at the AI Foundry service through the Azure portal.<\/p>\n The following image shows the architecture of Azure AI Foundry.<\/p>\n Azure AI Foundry Hub: <\/strong>The hub acts as the parent resource that provides shared infrastructure and centralized management. It centralizes and manages the following.<\/p>\n Azure AI Foundry Projects: <\/strong>Projects are individual workspaces within a hub where actual AI development happens (model training, deployment, etc.).. Each project contains the following.<\/p>\n And within Projects, you have access to two main categories of AI services.<\/p>\n Here is what we are going to do in this guide,<\/p>\n If you are setting up AI Foundry and need good governance, including advanced networking, security configurations, and enterprise-grade controls, you need to create a hub-based project starting from the Azure portal. This guide is based on AI Foundry hub management through the Azure portal<\/p><\/div>\n<\/div>\n The first step is to create a Hub.<\/p>\n Let’s get started.<\/p>\n In the search bar, type Navigate to the The resource creation page will open.<\/p>\n On the In the Along with you need to select one of the credentials store options to store the storage account and container registry credentials.<\/p>\n The next one is the The following section will be the On the On the Finally, add the tags and review the given configuration, then click to create the Hub.<\/p>\n The Hub creation will take a few minutes to complete.<\/p>\n Once the Hub creation is completed, navigate to the Azure AI Hub and click the You will be on a new dedicated page where you can manage your Hubs, Projects, and other services.<\/p>\n Now that we have the hub ready, the next step is to create a project under the hub.<\/p>\n We can create multiple projects under one hub so hub level configurations will be inherited by all the projects.<\/p>\n For the demo, we are going to create a single project under this hub ( In the overview section of the Hub, we can create a new project by giving a name.<\/p>\n Once the Project creation is complete, you will be redirected to the project page where you can view the endpoints.<\/p>\n In there, you will see three endpoints for various use cases.<\/p>\n In the Project overview page, we can see the following endpoints, <\/p>\n All the projects under the AI Hub can utilize the security, connections, and configurations of the Hub.<\/p><\/div>\n<\/div>\n Now, the project creation under the hub is completed so we can start deploying models and using them.<\/p>\n To deploy a model for the project, navigate to the For this demo, we will choose one of the base OpenAI models, but you can choose any from the available list. <\/p>\n Choosing the Once you select the model, it will show the description of the details about that model.<\/p>\n On the next page, deployment details will be available, and we can customize them as per the requirements, such as deployment type, tokens per minute, etc.<\/p>\n Once the deployment is successfully completed, we can see the API key, endpoint, and sample usage on the deployment page.<\/p>\n This is how we deploy a model on the Azure AI Projects and use it on our AI applications.<\/p>\n![\"architecture](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/07\/image-96.png\")
<\/figure>\n\n
\n
\n
\n
\n
Let’s Begin..<\/h2>\n
\n
Create an Azure AI Foundry Hub<\/h2>\n
Azure AI Foundry<\/code>and open the service.<\/p>\nAI Hubs<\/code> and click the + create<\/code> button to select the Hub<\/code> for the AI Hub creation.<\/p>\n![\"the](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-24.png\")
<\/figure>\nBasics<\/code> page, select the subscription, resource group, region, and name for the Hub.<\/p>\n
You can use the existing one, or it will create a new one.<\/div>\n<\/div>\n![\"The](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-25.png\")
<\/figure>\nStorage<\/code> section, you need a storage account to store your project artifacts. You can choose the existing one, or it will create a new one itself.<\/p>\n![\"The](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-26.png\")
<\/figure>\nInbound Access<\/code> section, where we can configure the network configuration for the clients to access the Hub.<\/p>\n![\"The](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-27.png\")
<\/figure>\nOutbound Access<\/code> section, where we can restrict outbound network access to the Hub.<\/p>\n![\"The](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-28.png\")
<\/figure>\nEncryption<\/code> section, we can configure the encryption so our data will be encrypted by the managed keys.<\/p>\n![\"The](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-29.png\")
<\/figure>\nIdentity<\/code> section, we define the identity so that the Hub can access the storage account, key vault, and container registry.<\/p>\n![\"The](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-30.png\")
<\/figure>\nLaunch Azure AI Foundry<\/code> to manage the resources.<\/p>\n![\"the](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-31.png\")
<\/figure>\n![\"the](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-32.png\")
<\/figure>\nCreate an Azure AI Project<\/h2>\n
Demo ai hub<\/code>)<\/p>\n![\"The](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-36.png\")
<\/figure>\n![\"listing](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-37.png\")
<\/figure>\n\n
Deploying a Model In the Project<\/h2>\n
Models + endpoints<\/code> section of the left side panel and select the + Deploy model<\/code> to choose the existing models or the fine-tuned models.<\/p>\n![\"the](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-97.png\")
<\/figure>\nDeploy base model<\/code> will show the list of all existing LLM models. We can choose them using the filters based on our use case.<\/p>\n![\"the](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-98.png\")
<\/figure>\n![\"the](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-99.png\")
<\/figure>\n![\"the](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-100.png\")
<\/figure>\n![\"the](\"https:\/\/storage.ghost.io\/c\/5f\/2f\/5f2f4d20-2abf-4534-8d40-7aa233aedd43\/content\/images\/2025\/06\/image-101.png\")
<\/figure>\n