Merge pull request #3197 from MicrosoftDocs/main

2/26/2025 PM Publish

Author: Taojunshen

articles/ai-foundry/model-inference/includes/create-resources/bicep.md

@@ -30,19 +30,9 @@ The files for this example are in:
 cd azureai-model-inference-bicep/infra
 ```
 
-## Understand the resources
-
-The tutorial helps you create:
-
-> [!div class="checklist"]
-> * An Azure AI Services resource.
-> * A model deployment in the Global standard SKU for each of the models supporting pay-as-you-go.
-> * (Optionally) An Azure AI project and hub.
-> * (Optionally) A connection between the hub and the models in Azure AI Services.
-
-Notice that **you have to deploy an Azure AI project and hub** if you plan to use the Azure AI Foundry portal for managing the resource, using playground, or any other feature from the portal.
+## Create the resources
 
-You are using the following assets to create those resources:
+Follow these steps:
 
 1. Use the template `modules/ai-services-template.bicep` to describe your Azure AI Services resource:
 
@@ -72,10 +62,6 @@ You are using the following assets to create those resources:
 
     :::code language="bicep" source="~/azureai-model-inference-bicep/infra/modules/ai-services-connection-template.bicep":::
 
-## Create the resources
-
-In your console, follow these steps:
-
 1. Define the main deployment:
 
     __deploy-with-project.bicep__

articles/ai-foundry/model-inference/includes/create-resources/intro.md

@@ -11,6 +11,22 @@ ms.topic: include
 
 In this article, you learn how to create the resources required to use Azure AI model inference and consume flagship models from Azure AI model catalog.
 
+## Understand the resources
+
+Azure AI model inference is a capability in Azure AI Services resources in Azure. You can create model deployments under the resource to consume their predictions. You can also connect the resource to Azure AI Hubs and Projects in Azure AI Foundry to create intelligent applications if needed. The following picture shows the high level architecture.
+
+:::image type="content" source="../../media/create-resources/resources-architecture.png" alt-text="A diagram showing the high level architecture of the resources created in the tutorial." lightbox="../../media/create-resources/resources-architecture.png":::
+
+Azure AI Services resources don't require AI projects or AI hubs to operate and you can create them to consume flagship models from your applications. However, additional capabilities are available if you **deploy an Azure AI project and hub**, including playground, or agents.
+
+The tutorial helps you create:
+
+> [!div class="checklist"]
+> * An Azure AI Services resource.
+> * A model deployment for each of the models supported with pay-as-you-go.
+> * (Optionally) An Azure AI project and hub.
+> * (Optionally) A connection between the hub and the models in Azure AI Services.
+
 ## Prerequisites
 
 To complete this article, you need:

articles/ai-foundry/model-inference/media/create-resources/resources-architecture.png

@@ -460,6 +460,13 @@
       "redirect_url": "/azure/ai-services/speech-service/how-to-custom-speech-model-and-endpoint-lifecycle",
       "redirect_document_id": false
     },
+    {
+      "source_path_from_root": "/articles/ai-services/speech-service/custom-speech-ai-foundry-portal.md",
+      "redirect_url": "/azure/ai-services/speech-service/how-to-custom-speech-create-project",
+      "redirect_document_id": false
+    },
+
+    
     {
       "source_path_from_root": "/articles/ai-services/anomaly-detector/how-to/postman.md",
       "redirect_url": "/azure/ai-services/anomaly-detector/overview",
@@ -777,7 +784,7 @@
     },
     {
       "source_path_from_root": "/articles/ai-services/speech-service/custom-speech-ai-studio.md",
-      "redirect_url": "/azure/ai-services/speech-service/custom-speech-ai-foundry-portal",
+      "redirect_url": "/azure/ai-services/speech-service/how-to-custom-speech-create-project",
       "redirect_document_id": true
     },
     {

articles/ai-services/.openpublishing.redirection.ai-services.json

@@ -2,7 +2,7 @@
 manager: nitinme
 author: aahill
 ms.author: aahi
-ms.service: azure
+ms.service: azure-ai-agent-service
 ms.topic: include
 ms.date: 01/21/2025
 ---

articles/ai-services/agents/includes/quickstart-foundry.md

@@ -71,24 +71,35 @@ Passwordless authentication is more secure than key-based alternatives and is th
 
 ### Create the assistant
 
+>[!Note]
+> For this sample, the following libraries were used:
+>- Azure.AI.OpenAI(2.1.0-beta2)
+>- Azure.AI.OpenAI.Assistants(1.0.0-beta4)
+
 Update the `Program.cs` file with the following code to create an assistant:
 
 ```csharp
 using Azure;
-using Azure.AI.OpenAI.Assistants;
+using Azure.AI.OpenAI;
+using Azure.Identity;
+using Azure.Security.KeyVault.Secrets;
+using OpenAI.Assistants;
+using OpenAI.Files;
+using System.ClientModel;
 
 // Assistants is a beta API and subject to change
 // Acknowledge its experimental status by suppressing the matching warning.
 string endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT");
 string key = Environment.GetEnvironmentVariable("AZURE_OPENAI_API_KEY");
+string deploymentName = "<Replace with Deployment Name>"
 
 var openAIClient = new AzureOpenAIClient(new Uri(endpoint), new AzureKeyCredential(key));
 
 // Use for passwordless auth
 //var openAIClient = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential()); 
 
-FileClient fileClient = openAIClient.GetFileClient();
-AssistantClient assistantClient = openAIClient.GetAssistantClient();
+OpenAIFileClient fileClient = azureClient.GetOpenAIFileClient();
+AssistantClient assistantClient = azureClient.GetAssistantClient();
 
 // First, let's contrive a document we'll use retrieval with and upload it.
 using Stream document = BinaryData.FromString("""
@@ -120,13 +131,13 @@ using Stream document = BinaryData.FromString("""
             }
             """).ToStream();
 
-OpenAIFileInfo salesFile = await fileClient.UploadFileAsync(
+OpenAI.Files.OpenAIFile salesFile = await fileClient.UploadFileAsync(
     document,
     "monthly_sales.json",
     FileUploadPurpose.Assistants);
 
 // Now, we'll create a client intended to help with that data
-AssistantCreationOptions assistantOptions = new()
+OpenAI.Assistants.AssistantCreationOptions assistantOptions = new()
 {
     Name = "Example: Contoso sales RAG",
     Instructions =
@@ -136,7 +147,7 @@ AssistantCreationOptions assistantOptions = new()
     Tools =
             {
                 new FileSearchToolDefinition(),
-                new CodeInterpreterToolDefinition(),
+                new OpenAI.Assistants.CodeInterpreterToolDefinition(),
             },
     ToolResources = new()
     {
@@ -158,7 +169,9 @@ ThreadCreationOptions threadOptions = new()
     InitialMessages = { "How well did product 113045 sell in February? Graph its trend over time." }
 };
 
-ThreadRun threadRun = await assistantClient.CreateThreadAndRunAsync(assistant.Id, threadOptions);
+var initialMessage = new OpenAI.Assistants.ThreadInitializationMessage(OpenAI.Assistants.MessageRole.User, ["hi"]);
+
+ThreadRun threadRun = await assistantClient.CreateThreadAndRunAsync(assistant.Value.Id, threadOptions);
 
 // Check back to see when the run is done
 do
@@ -168,15 +181,15 @@ do
 } while (!threadRun.Status.IsTerminal);
 
 // Finally, we'll print out the full history for the thread that includes the augmented generation
-AsyncCollectionResult<ThreadMessage> messages
+AsyncCollectionResult<OpenAI.Assistants.ThreadMessage> messages
     = assistantClient.GetMessagesAsync(
         threadRun.ThreadId,
         new MessageCollectionOptions() { Order = MessageCollectionOrder.Ascending });
 
-await foreach (ThreadMessage message in messages)
+await foreach (OpenAI.Assistants.ThreadMessage message in messages)
 {
     Console.Write($"[{message.Role.ToString().ToUpper()}]: ");
-    foreach (MessageContent contentItem in message.Content)
+    foreach (OpenAI.Assistants.MessageContent contentItem in message.Content)
     {
         if (!string.IsNullOrEmpty(contentItem.Text))
         {
@@ -202,9 +215,9 @@ await foreach (ThreadMessage message in messages)
         }
         if (!string.IsNullOrEmpty(contentItem.ImageFileId))
         {
-            OpenAIFileInfo imageInfo = await fileClient.GetFileAsync(contentItem.ImageFileId);
+            OpenAI.Files.OpenAIFile imageFile = await fileClient.GetFileAsync(contentItem.ImageFileId);
             BinaryData imageBytes = await fileClient.DownloadFileAsync(contentItem.ImageFileId);
-            using FileStream stream = File.OpenWrite($"{imageInfo.Filename}.png");
+            using FileStream stream = File.OpenWrite($"{imageFile.Filename}.png");
             imageBytes.ToStream().CopyTo(stream);
 
             Console.WriteLine($"<image: {imageInfo.Filename}.png>");
@@ -214,6 +227,22 @@ await foreach (ThreadMessage message in messages)
 }
 ```
 
+It is recommended that you store the API Key in a secure location, such as a Key Vault. The following code snippet can replace the 
+```GetEnvironmentVariable``` lines to retrieve the Azure OpenAI API Key from your Key Vault instance:
+
+```csharp
+string keyVaultName = "<Replace with Key Vault Name>";
+var kvUri = $"https://{keyVaultName}.vault.azure.net/";
+
+var client = new SecretClient(new Uri(kvUri), new DefaultAzureCredential());
+
+KeyVaultSecret endpointSecret = await client.GetSecretAsync("AZURE-OPENAI-ENDPOINT");
+KeyVaultSecret apiKeySecret = await client.GetSecretAsync("AZURE-OPENAI-API-KEY");
+
+string endpoint = endpointSecret.Value;
+string key = apiKeySecret.Value;
+```
+
 Run the app using the [`dotnet run`](/dotnet/core/tools/dotnet-run) command:
 
 ```csharp

articles/ai-services/openai/includes/assistants-csharp.md

@@ -246,7 +246,7 @@ To use a custom speech model for batch transcription, you need the model's URI.
 > [!TIP]
 > A [hosted deployment endpoint](how-to-custom-speech-deploy-model.md) isn't required to use custom speech with the batch transcription service. You can conserve resources if you use the [custom speech model](how-to-custom-speech-train-model.md) only for batch transcription.
 
-Batch transcription requests for expired models fail with a 4xx error. Set the `model` property to a base model or custom model that isn't expired. Otherwise don't include the `model` property to always use the latest base model. For more information, see [Choose a model](how-to-custom-speech-create-project.md#choose-your-model) and [Custom speech model lifecycle](how-to-custom-speech-model-and-endpoint-lifecycle.md).
+Batch transcription requests for expired models fail with a 4xx error. Set the `model` property to a base model or custom model that isn't expired. Otherwise don't include the `model` property to always use the latest base model. For more information, see [Choose a model](./custom-speech-overview.md#choose-your-model) and [Custom speech model lifecycle](how-to-custom-speech-model-and-endpoint-lifecycle.md).
 
 ## Use a Whisper model