Merge branch 'main' into phi-4-maas-support

Author: msakande

.openpublishing.publish.config.json

@@ -110,12 +110,6 @@
       "branch": "main",
       "branch_mapping": {}
     },
-    {
-      "path_to_root": "azureai-samples-temp",
-      "url": "https://github.com/sdgilley/azureai-samples",
-      "branch": "sdg-add-quickstart",
-      "branch_mapping": {}
-    },
     {
       "path_to_root": "azureai-samples-csharp",
       "url": "https://github.com/Azure-Samples/azureai-samples",

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

@@ -107,7 +107,7 @@
     },
     {
       "source_path_from_root": "/articles/ai-services/cognitive-services-development-options.md",
-      "redirect_url": "/azure/ai-services/ai-services-and-ecosystem",
+      "redirect_url": "/azure/ai-services/what-are-ai-services",
       "redirect_document_id": false
     },
     {
@@ -192,7 +192,7 @@
     },
     {
       "source_path_from_root": "/articles/ai-services/cognitive-services-and-machine-learning.md",
-      "redirect_url": "/azure/ai-services/ai-services-and-ecosystem",
+      "redirect_url": "/azure/ai-services/what-are-ai-services",
       "redirect_document_id": true
     },
     {
@@ -809,6 +809,11 @@
       "source_path_from_root": "/articles/ai-services/openai/how-to/integrate-synapseml.md",
       "redirect_url": "/azure/ai-services/openai/overview",
       "redirect_document_id": true
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/ai-services-and-ecosystem.md",
+      "redirect_url": "/azure/ai-services/what-are-ai-services",
+      "redirect_document_id": false
     }
   ]
 }

articles/ai-services/agents/faq.yml

@@ -7,7 +7,7 @@ metadata:
   manager: nitinme
   ms.service: azure-ai-agent-service
   ms.topic: faq
-  ms.date: 12/20/2024
+  ms.date: 01/15/2025
   ms.author: aahi
   author: aahill
 title: Azure AI Agent Service frequently asked questions
@@ -49,7 +49,7 @@ sections:
           * If you've enabled the Code Interpreter tool - for example your agent calls Code Interpreter simultaneously in two different threads, this would create two Code Interpreter sessions, each of which would be charged. Each session is active by default for one hour, which means that you would only pay this fee once if your user keeps giving instructions to Code Interpreter in the same thread for up to one hour.
           * File search is billed based on the vector storage used. 
 
-          For more information, see the [pricing page](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/).
+          For more information, see the [pricing page](https://azure.microsoft.com/pricing/details/ai-foundry/).
       - question: |
           Is there any additional pricing or quota for using AI Agent Service? 
         answer: |

articles/ai-services/agents/how-to/use-your-own-resources.md

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 12/11/2024
+ms.date: 01/15/2025
 author: fosteramanda
 ms.author: fosteramanda
 ms.custom: azure-ai-agents
@@ -17,7 +17,8 @@ ms.custom: azure-ai-agents
 Use this article if you want to use the Azure Agent Service with resources you already have. 
 
 > [!NOTE]
-> If you use an existing AI Services / Azure OpenAI Service resource, no model will be deployed. You can deploy a model to the resource after the agent setup is complete. 
+> * If you use an existing AI Services / Azure OpenAI Service resource, no model will be deployed. You can deploy a model to the resource after the agent setup is complete. 
+> * Make sure your Azure OpenAI resource and Azure AI Foundry project are in the same region. 
 
 ## Choose basic or standard agent setup
 

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

@@ -4,7 +4,7 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: include
-ms.date: 11/13/2024
+ms.date: 01/15/2025
 ---
 
 | [Reference documentation](/dotnet/api/overview/azure/ai.projects-readme) | [Samples](https://github.com/Azure/azure-sdk-for-net/tree/main/sdk/ai/Azure.AI.Projects/tests/Samples) | [Library source code](https://github.com/Azure/azure-sdk-for-net/tree/main/sdk/ai/Azure.AI.Projects) | [Package (NuGet)](https://www.nuget.org/packages/Azure.AI.Projects/) |
@@ -16,6 +16,8 @@ ms.date: 11/13/2024
 * Make sure you have the **Azure AI Developer** [RBAC role](../../../ai-studio/concepts/rbac-ai-studio.md) assigned at the appropriate level.
 * Install [the Azure CLI and the machine learning extension](/azure/machine-learning/how-to-configure-cli). If you have the CLI already installed, make sure it's updated to the latest version.
 
+[!INCLUDE [rbac-roles](rbac-roles.md)]
+
 [!INCLUDE [bicep-setup](bicep-setup.md)]
 
 ## Configure and run an agent
@@ -32,7 +34,8 @@ ms.date: 11/13/2024
 Install the .NET package to your project. For example if you're using the .NET CLI, run the following command.
 
 ```console
-dotnet add package Azure.AI.Projects --version 1.0.0-beta.1
+dotnet add package Azure.AI.Projects
+dotnet add package Azure.Identity
 ```
 
 Use the following code to create and run an agent. To run this code, you will need to create a connection string using information from your project. This string is in the format:
@@ -59,79 +62,62 @@ Set this connection string as an environment variable named `PROJECT_CONNECTION_
 
 #nullable disable
 
-using System;
-using System.Collections.Generic;
-using System.Threading.Tasks;
-using Azure.Core.TestFramework;
-using NUnit.Framework;
+using Azure.Identity;
 
 namespace Azure.AI.Projects.Tests;
 
-public partial class Sample_Agent_Basics : SamplesBase<AIProjectsTestEnvironment>
+public class Sample_Agent
 {
-    [Test]
-    public async Task BasicExample()
+    static async Task Main()
     {
         var connectionString = Environment.GetEnvironmentVariable("AZURE_AI_CONNECTION_STRING");
 
         AgentsClient client = new AgentsClient(connectionString, new DefaultAzureCredential());
-        #endregion
 
         // Step 1: Create an agent
-        #region Snippet:OverviewCreateAgent
         Response<Agent> agentResponse = await client.CreateAgentAsync(
-            model: "gpt-4o",
-            name: "Math Tutor",
-            instructions: "You are a personal math tutor. Write and run code to answer math questions.",
+            model: "gpt-4o-mini",
+            name: "My Agent",
+            instructions: "You are a helpful agent.",
             tools: new List<ToolDefinition> { new CodeInterpreterToolDefinition() });
         Agent agent = agentResponse.Value;
-        #endregion
 
         // Intermission: agent should now be listed
 
         Response<PageableList<Agent>> agentListResponse = await client.GetAgentsAsync();
 
         //// Step 2: Create a thread
-        #region Snippet:OverviewCreateThread
         Response<AgentThread> threadResponse = await client.CreateThreadAsync();
         AgentThread thread = threadResponse.Value;
-        #endregion
 
         // Step 3: Add a message to a thread
-        #region Snippet:OverviewCreateMessage
         Response<ThreadMessage> messageResponse = await client.CreateMessageAsync(
             thread.Id,
             MessageRole.User,
             "I need to solve the equation `3x + 11 = 14`. Can you help me?");
         ThreadMessage message = messageResponse.Value;
-        #endregion
 
         // Intermission: message is now correlated with thread
         // Intermission: listing messages will retrieve the message just added
 
         Response<PageableList<ThreadMessage>> messagesListResponse = await client.GetMessagesAsync(thread.Id);
-        Assert.That(messagesListResponse.Value.Data[0].Id == message.Id);
+        //Assert.That(messagesListResponse.Value.Data[0].Id == message.Id);
 
         // Step 4: Run the agent
-        #region Snippet:OverviewCreateRun
         Response<ThreadRun> runResponse = await client.CreateRunAsync(
             thread.Id,
             agent.Id,
-            additionalInstructions: "Please address the user as Jane Doe. The user has a premium account.");
+            additionalInstructions: "");
         ThreadRun run = runResponse.Value;
-        #endregion
 
-        #region Snippet:OverviewWaitForRun
         do
         {
             await Task.Delay(TimeSpan.FromMilliseconds(500));
             runResponse = await client.GetRunAsync(thread.Id, runResponse.Value.Id);
         }
         while (runResponse.Value.Status == RunStatus.Queued
             || runResponse.Value.Status == RunStatus.InProgress);
-        #endregion
 
-        #region Snippet:OverviewListUpdatedMessages
         Response<PageableList<ThreadMessage>> afterRunMessagesResponse
             = await client.GetMessagesAsync(thread.Id);
         IReadOnlyList<ThreadMessage> messages = afterRunMessagesResponse.Value.Data;
@@ -153,7 +139,6 @@ public partial class Sample_Agent_Basics : SamplesBase<AIProjectsTestEnvironment
                 Console.WriteLine();
             }
         }
-        #endregion
     }
 }
 ```

articles/ai-services/agents/includes/quickstart-python-openai.md

@@ -18,6 +18,8 @@ ms.date: 11/13/2024
 * You need the **Cognitive Services OpenAI User** role assigned to use the Azure AI Services resource.
 * Install [the Azure CLI and the machine learning extension](/azure/machine-learning/how-to-configure-cli). If you have the CLI already installed, make sure it's updated to the latest version.
 
+[!INCLUDE [rbac-roles](rbac-roles.md)]
+
 [!INCLUDE [bicep-setup](bicep-setup.md)]
 
 ## Configure and run an agent

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

@@ -17,6 +17,8 @@ ms.date: 11/13/2024
 * Make sure you have the **Azure AI Developer** [RBAC role](../../../ai-studio/concepts/rbac-ai-studio.md) assigned at the appropriate level.
 * Install [the Azure CLI and the machine learning extension](/azure/machine-learning/how-to-configure-cli). If you have the CLI already installed, make sure it's updated to the latest version.
 
+[!INCLUDE [rbac-roles](rbac-roles.md)]
+
 [!INCLUDE [bicep-setup](bicep-setup.md)]
 
 ## Configure and run an agent

articles/ai-services/agents/includes/rbac-roles.md

@@ -0,0 +1,22 @@
+---
+manager: nitinme
+author: aahill
+ms.author: aahi
+ms.service: azure-ai-agent-service
+ms.topic: include
+ms.date: 11/13/2024
+---
+
+### RBAC roles
+
+Make sure both developers and end users have the following permissions: 
+
+* `Microsoft.MachineLearningServices/workspaces/agents/read`
+* `Microsoft.MachineLearningServices/workspaces/agents/action`
+* `Microsoft.MachineLearningServices/workspaces/agents/delete`
+
+If you want to create custom permissions, make sure they have: 
+
+* `agents/*/read` 
+* `agents/*/action` 
+* `agents/*/delete` 

articles/ai-services/agents/overview.md

@@ -7,7 +7,7 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: overview
-ms.date: 12/11/2024
+ms.date: 01/10/2025
 ms.custom: azure-ai-agents
 ---
 
@@ -69,7 +69,7 @@ Both services enable you to build agents using the same API and SDKs, but if you
 
 **Flexible model selection** - Create agents that use Azure OpenAI models, or others such as Llama 3, Mistral and Cohere. Choose the most suitable model to meet your business needs.
 
-**Extensive data integrations** - Ground your AI agents with relevant, secure enterprise knowledge from various data sources, such as Microsoft Bing, Microsoft SharePoint, Microsoft Fabric, Azure AI Search, and other APIs. 
+**Extensive data integrations** - Ground your AI agents with relevant, secure enterprise knowledge from various data sources, such as Microsoft Bing, Azure AI Search, and other APIs. 
 
 **Enterprise grade security** - Ensure data privacy and compliance with secure data handling, keyless authentication, and no public egress.