Get started with the Azure AI Foundry integrations

🧪 Preview

Azure AI Foundry provides a unified platform for developing, testing, and deploying AI applications. The Aspire Azure AI Foundry integration enables you to connect to Azure AI Foundry services from your applications, providing access to various AI capabilities including model deployments, prompt flow, and more.

In this introduction, you’ll see how to install and use the Aspire Azure AI Foundry integrations in a simple configuration. If you already have this knowledge, see Azure AI Foundry Hosting integration for full reference details.

Note

To follow this guide, you must have created an Aspire solution to work with. To learn how to do that, see Build your first Aspire app.

Set up hosting integration

To begin, install the Aspire Azure AI Foundry Hosting integration in your Aspire AppHost project. This integration allows you to create and manage Azure AI Foundry resources from your Aspire hosting projects:

Aspire CLI

Aspire CLI — Ajouter le package Aspire.Hosting.Azure.AIFoundry

aspire add azure-aifoundry

La CLI Aspire est interactive ; choisissez le résultat approprié lorsque demandé :

Aspire CLI — Exemple de sortie

Select an integration to add:

> azure-aifoundry (Aspire.Hosting.Azure.AIFoundry)
> Other results listed as selectable options...

Note

S'il n'y a qu'un seul résultat, il est sélectionné automatiquement. Vous devez quand même confirmer la version.

apphost.cs (C# file-based app)

C# — AppHost.cs

#:package Aspire.Hosting.Azure.AIFoundry@*

PackageReference (*.csproj)

XML — Ajouter la référence de package Aspire.Hosting.Azure.AIFoundry

<PackageReference Include="Aspire.Hosting.Azure.AIFoundry" Version="*" />

Next, in the AppHost project, create an Azure AI Foundry resource and pass it to the consuming client projects:

C# — AppHost.cs

var builder = DistributedApplication.CreateBuilder(args);

var foundry = builder.AddAzureAIFoundry("foundry");

var chat = foundry.AddDeployment("chat", "Phi-4", "1", "Microsoft");

builder.AddProject<Projects.ExampleProject>()
    .WithReference(chat)
    .WaitFor(chat);

// After adding all resources, run the app...

builder.Build().Run();

The preceding code adds an Azure AI Foundry resource named foundry with a deployment named chat using the Phi-4 model to the AppHost project. The WithReference method passes the connection information to the ExampleProject project.

Attention

When you call AddAzureAIFoundry, it implicitly calls AddAzureProvisioning—which adds support for generating Azure resources dynamically during app startup. The app must configure the appropriate subscription and location. For more information, see Local provisioning: Configuration.

Astuce

This is the simplest implementation of Azure AI Foundry resources in the AppHost. There are many more options you can choose from to address your requirements. For full details, see Azure AI Foundry Hosting integration.

Set up client integration

The client integration for Azure AI Foundry is the Azure AI Inference integration. To use Azure AI Foundry from your client applications, install the Azure AI Inference integration in your client project.

For more information on using the client integration, see the Azure AI Inference integration documentation.

Next steps

Azure AI Foundry Hosting integration Learn more about the hosting integration features and capabilities

Azure AI Inference Client integration Learn how to use the Azure AI Inference client integration