Merge pull request #6270 from MicrosoftDocs/main

learn-build-service-prod[bot] · web-flow · commit 21a95c58e7df · 2025-07-29T11:03:20.000Z
Auto Publish – main to live - 2025-07-29 11:00 UTC
diff --git a/articles/ai-foundry/how-to/evaluation-azure-devops.md b/articles/ai-foundry/how-to/evaluation-azure-devops.md
@@ -5,7 +5,7 @@ description: How to run evaluation in Azure DevOps which enables offline evaluat
 manager: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: how-to
-ms.date: 05/19/2025
+ms.date: 07/25/2025
 ms.reviewer: hanch
 ms.author: lagayhar
 author: lgayhardt
@@ -21,8 +21,7 @@ Similar to the [Azure AI evaluation in GitHub Actions](evaluation-github-action.
 
 ## Prerequisites
 
-[!INCLUDE [hub-only-prereq](../includes/hub-only-prereq.md)]
-
+- Foundry project or Hubs based project. To learn more, see [Create a project](create-projects.md).
 - Install Azure AI evaluation extension.
   - Go to [Azure DevOps Marketplace](https://marketplace.visualstudio.com/azuredevops).
   - Search for Azure AI evaluation and install the extension into your Azure DevOps organization.
@@ -65,7 +64,51 @@ Similar to the [Azure AI evaluation in GitHub Actions](evaluation-github-action.
 
 A sample YAML file:
 
-```yml
+# [Foundry project](#tab/foundry-project)
+
+```yaml
+
+trigger: 
+- main 
+pool: 
+
+  vmImage: 'windows-latest'  
+
+steps: 
+
+- task: AzureCLI@2 
+  inputs: 
+    addSpnToEnvironment: true 
+    azureSubscription: ${{vars.Service_Connection_Name}}
+    scriptType: bash 
+    scriptLocation: inlineScript     
+
+    inlineScript: | 
+      echo "##vso[task.setvariable variable=ARM_CLIENT_ID]$servicePrincipalId"  
+      echo "##vso[task.setvariable variable=ARM_ID_TOEKN]$idToken" 
+      echo "##vso[task.setvariable variable=ARM_TENANT_ID]$tenantId" 
+
+- bash: | 
+
+   az login --service-principal -u $(ARM_CLIENT_ID) --tenant $(ARM_TENANT_ID) --allow-no-subscriptions --federated-token $(ARM_ID_TOEKN) 
+
+  displayName: 'Login Azure' 
+ 
+- task: UsePythonVersion@0 
+  inputs: 
+    versionSpec: '3.11' 
+- task: AIAgentEvaluation@0 
+  inputs: 
+    azure-ai-project-endpoint: "<your-ai-project-endpoint>"
+    deployment-name: "gpt-4o-mini" 
+    data-path: $(Build.SourcesDirectory)\tests\data\golden-dataset-medium.json 
+agent-ids: "<your-ai-agent-ids> 
+
+```
+
+# [Hub based project](#tab/hub-project)
+
+```yaml
 
 trigger: 
 - main 
@@ -105,6 +148,8 @@ agent-ids: "<your-ai-agent-ids>
 
 ```
 
+---
+
 ## Set up a new pipeline and trigger an evaluation run
 
 Commit and run the pipeline in Azure DevOps.
diff --git a/articles/ai-services/language-service/conversational-language-understanding/how-to/configure-azure-resources.md b/articles/ai-services/language-service/conversational-language-understanding/how-to/configure-azure-resources.md
@@ -118,7 +118,25 @@ Azure AI Foundry offers a unified platform where you can easily build, manage, a
 
    :::image type="content" source="../media/configure-resources/connect-language-resource.png" alt-text="Screenshot of connect search resource selector in the Azure AI Foundry.":::
 
-1. Your resources are now set up properly. Continue with setting up the fine-tuning task and customizing your CLU project.
+## Import an existing Azure AI project
+
+Azure AI Foundry allows you to connect to your existing Azure AI services resources. This means you can establish a connection within your Azure AI Foundry project to the Azure AI Language resource where your custom models are stored.
+
+To import an existing Azure AI services project with Azure AI Foundry, you need to create a connection to the Azure AI services resource within your Azure AI Foundry project. For more information, *see* [Connect Azure AI Services projects to Azure AI Foundry](../../../../ai-services/connect-services-ai-foundry-portal.md)
+
+## Export a project
+
+You can download a CLU project as a **config.json** file:
+
+1. Navigate to your project home page.
+1. At the top of the page, select your project from the right page ribbon area.
+1. Select **Download config file**.
+
+    :::image type="content" source="../media/create-project/download-config-json.png" alt-text="Screenshot of project drop-down menu with the download config file hyperlink in the Azure AI Foundry.":::
+
+
+
+That's it! Your resources are now set up properly. Continue with setting up the fine-tuning task and customizing your CLU project.
 
 ## Next Steps
 
diff --git a/articles/ai-services/language-service/conversational-language-understanding/how-to/create-project.md b/articles/ai-services/language-service/conversational-language-understanding/how-to/create-project.md
@@ -1,7 +1,7 @@
 ---
-title: Create Projects in Conversational Language Understanding
+title: Create a CLU fine-tuning task in Azure AI Foundry or with the REST API
 titleSuffix: Azure AI services
-description: This article shows you how to create projects in conversational language understanding (CLU).
+description: This article shows you how to create CLU fine-tuning task projects the Azure AI Foundry or using the REST API.
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
@@ -11,73 +11,100 @@ ms.author: lajanuar
 ms.custom: language-service-clu
 ---
 
-# Create a CLU project in Azure AI Foundry
+# Create a fine-tuning task project
 
-Azure AI Foundry projects help you organize your work when exploring new ideas or developing prototypes for specific use cases. A Foundry project is created on an Azure AI Foundry resource. This type of project offers an easy setup and provides access to agents and Azure AI models.
+A Conversational Language Understanding (CLU) fine-tuning task is a workspace project where you customize a language model to identify user intent and extract key information (entities) from user input (utterances). In this workspace, you define the intents and entities relevant to your application, label sample user utterances accordingly, and use this labeled data to fine-tune the model. This process tailors the model to better understand the specific needs and nuances of your conversational application. In this guide, we walk you through configuring a fine-tuning workspace in the Azure AI Foundry or using the REST API.
 
-If you already have an Azure AI Language or multi-service resource—whether used on its own or through Language Studio—you can continue to use those existing Language resources within the Azure AI Foundry portal. For more information, see [How to use Azure AI services in the Azure AI Foundry portal](../../../../ai-services/connect-services-ai-foundry-portal.md).
+> [!NOTE]
+>
+> If you already have an Azure AI Language or multi-service resource—whether used on its own or through Language Studio—you can continue to use those existing Language resources within the Azure AI Foundry portal. For more information, see [How to use Azure AI services in the Azure AI Foundry portal](../../../../ai-services/connect-services-ai-foundry-portal.md).
+>
+> In Azure AI Foundry, you set up a fine-tuning task to serve as your workspace when customizing your CLU model. Previously, a **fine-tuning task** was referred to as a **CLU project**. You might encounter both terms used interchangeably in older CLU documentation.
+>
 
 ## Prerequisites
 
 * An Azure subscription. If you don't have one, you can [create one for free](https://azure.microsoft.com/free/cognitive-services).
 * **Requisite permissions**. Make sure the person establishing the account and project is assigned as the Azure AI Account Owner role at the subscription level. Alternatively, having either the **Contributor** or **Cognitive Services Contributor** role at the subscription scope also meets this requirement. For more information, *see* [Role based access control (RBAC)](../../../openai/how-to/role-based-access-control.md#cognitive-services-contributor).
-* An [Azure AI Foundry resource](../../../multi-service-resource.md)
-  * For more information, *see* [Configure an Azure AI Foundry resource](configure-azure-resources.md#option-1-configure-an-azure-ai-foundry-resource).
-* After you create an Azure AI Foundry resource, [create a CLU project](#create-a-clu-project).
+*  An [Azure AI Foundry multi-service resource](../../../multi-service-resource.md). For more information, *see* [Configure an Azure AI Foundry resource](configure-azure-resources.md#option-1-configure-an-azure-ai-foundry-resource). Alternately, you can use an [Azure AI Language resource](https://portal.azure.com/?Microsoft_Azure_PIMCommon=true#create/Microsoft.CognitiveServicesTextAnalytics).
+* A Foundry project created in the Azure AI Foundry. For more information, *see* [Create an AI Foundry project](../../../../ai-foundry/how-to/create-projects.md).
 
-## Create a CLU project
+> [!NOTE]
+>
+> We highly recommend that you use an Azure AI Foundry resource in the AI Foundry; however, you can also follow these instructions using a Language resource.
 
- An Azure AI Foundry project is created using an Azure AI Foundry resource. Projects are designed to help you organize your work. They offer various tools and resources that support the development, customization, and management of AI applications all within a centralized environment.
+## Create a CLU fine-tuning task project
+
+ To create a CLU fine-tuning task project, you first configure your environment and then create a fine-tuning task, which serves as your workspace for customizing your CLU model.
 
 ### [Azure AI Foundry](#tab/azure-ai-foundry)
 
- To learn how to create a CLU Foundry project, *see* [Create an AI Foundry project](../../../../ai-foundry/how-to/create-projects.md).
+1. Navigate to the [Azure AI Foundry](https://ai.azure.com/).
+1. If you aren't already signed in, the portal prompts you to do so with your Azure credentials.
+1. Once signed in, you can create or access your existing projects within Azure AI Foundry.
+1. If you're not already at your project for this task, select it.
+1. Select Fine-tuning from the left navigation panel.
 
+   :::image type="content" source="../media/select-fine-tuning.png" alt-text="Screenshot of fine-tuning selector in the Azure AI Foundry.":::
 
-### [REST APIs](#tab/rest-api)
+1. Select **the AI Service fine-tuning** tab and then **+ Fine-tune** button.
 
-[!INCLUDE [create project](../includes/rest-api/create-project.md)]
+   :::image type="content" source="../media/fine-tune-button.png" alt-text="Screenshot of fine-tuning button in the Azure AI Foundry.":::
 
----
+1. From **Create service fine-tuning** window, choose the **Conversational language understanding** tab then select **Next**.
 
-## Import an existing Azure AI project
+   :::image type="content" source="../media/select-project.png" alt-text="Screenshot of conversational language understanding tab in the Azure AI Foundry.":::
 
-### [Azure AI Foundry](#tab/azure-ai-foundry)
+1. In **Create CLU fine-tuning task** window, complete the **Name** and **Language** fields. If you're planning to fine-tune a model using the free **Standard Training** mode, select **English** for the language field.
 
-To import an existing Azure AI services project with Azure AI Foundry, you need to create a connection to the Azure AI services resource within your Azure AI Foundry project. For more information, *see* [Connect Azure AI Services projects to Azure AI Foundry](../../../../ai-services/connect-services-ai-foundry-portal.md)
+1. Navigate to the [Azure AI Foundry](https://ai.azure.com/).
+1. If you aren't already signed in, the portal prompts you to do so with your Azure credentials.
+1. Once signed in, you can create or access your existing projects within Azure AI Foundry.
+1. If you're not already at your project for this task, select it.
+1. Select Fine-tuning from the left navigation panel.
 
-### [REST APIs](#tab/rest-api)
+    :::image type="content" source="../media/select-fine-tuning.png" alt-text="Screenshot of fine-tuning selector in the Azure AI Foundry.":::
 
-You can import a CLU JSON into the service.
+1. Select **the AI Service fine-tuning** tab and then **+ Fine-tune** button.
 
-[!INCLUDE [Import project](../includes/rest-api/import-project.md)]
+    :::image type="content" source="../media/fine-tune-button.png" alt-text="Screenshot of fine-tuning button in the Azure AI Foundry.":::
 
----
+1. From **Create service fine-tuning** window, choose the **Conversational language understanding** tab then select **Next**.
 
-## Export a project
+    :::image type="content" source="../media/select-project.png" alt-text="Screenshot of conversational language understanding tab in the Azure AI Foundry.":::
 
-### [Azure AI Foundry](#tab/azure-ai-foundry)
+1. In **Create CLU fine tuning task** window, select your **Connected service** from the drop-down menu, then complete the **Name** and **Language** fields. If you're using the free **Standard Training** mode, select **English** for the language field.
 
-You can download a CLU project as a **config.json** file:
+1. Select the  **Create** button. It can take a few minutes for the *creating* operation to complete.
 
-1. Navigate to your project home page.
-1. At the top of the page, select your project from the right page ribbon area.
-1. Select **Download config file**.
 
-    :::image type="content" source="../media/create-project/download-config-json.png" alt-text="Screenshot of project drop-down menu with the download config file hyperlink in the Azure AI Foundry.":::
+   > [!NOTE]
+   >
+   > * **Standard training** enables faster training times and quicker iterations; however it's only available for English.
+   > * **Advanced training** includes longer training durations and is supported for English, other languages, and multilingual projects.
+   > * For more information, *see* [Training modes](train-model.md#training-modes).
 
-### [REST APIs](#tab/rest-api)
+1. Once the task creation is complete, select the task from the AI Service fine-tuning window to arrive at the Getting started with fine-tuning page.
 
-You can export a CLU project as a JSON file at any time.
+   :::image type="content" source="../media/create-project/getting-started-fine-tuning.png" alt-text="Screenshot of the getting started with fine-tuning page in the Azure AI Foundry." lightbox="../media/create-project/getting-started-fine-tuning.png":::
 
-[!INCLUDE [Export project](../includes/rest-api/export-project.md)]
+### [REST APIs](#tab/rest-api)
+
+[!INCLUDE [create project](../includes/rest-api/create-project.md)]
 
 ---
 
+
+That's it! You can get started on your fine-tuning task project. For more information, *see* [Next steps](#next-steps).
+
 ## View and manage project details
 
+You can retrieve up-to-date information about your projects, make any necessary changes, and oversee project management tasks efficiently through the Azure AI Foundry or REST API endpoints.
+
 ### [Azure AI Foundry](#tab/azure-ai-foundry)
 
+Your Azure AI Foundry project overview page displays information about your fine-tuning task project, including its name, subscription, resource group, and connected resources. You can also access the project's resources in the Azure portal by selecting **Manage in Azure portal** on the overview page.
+
 * On the project Home page, information about the project is found in the **Project details** section.
 * To view project settings, select **Management center** from the bottom of the left navigation pane, then select one of the following tabs:
    *  **Overview** to view project details.
@@ -89,14 +116,56 @@ You can export a CLU project as a JSON file at any time.
 
 ### [REST APIs](#tab/rest-api)
 
+You can access, view, and manage all of your project details via the REST API.
+
 [!INCLUDE [REST APIs project details](../includes/rest-api/project-details.md)]
 
 ---
 
-## Delete a project
+## Import an existing Azure AI project
+
+Importing the configuration file allows you to bring your existing settings directly into the platform, making it easier to set up and customize your service based on your predefined preferences.
 
 ### [Azure AI Foundry](#tab/azure-ai-foundry)
 
+To import an existing Azure AI services project with Azure AI Foundry, you need to create a connection to the Azure AI services resource within your Azure AI Foundry project. For more information, *see* [Connect Azure AI Services projects to Azure AI Foundry](../../../../ai-services/connect-services-ai-foundry-portal.md)
+
+### [REST APIs](#tab/rest-api)
+
+You can import your CLU config.json file using the REST API
+
+[!INCLUDE [Import project](../includes/rest-api/import-project.md)]
+
+---
+
+## Export a fine-tuning project
+
+Exporting your configuration file enables you to save the current state of your project's settings and structure, making it easy to back up or transfer your project as needed.
+
+### [Azure AI Foundry](#tab/azure-ai-foundry)
+
+You can download an Azure Foundry fine fine-tuning task project as a **config.json** file:
+
+1. Navigate to your project home page.
+1. At the top of the page, select your project from the right page ribbon area.
+1. Select **Download config file**.
+
+    :::image type="content" source="../media/create-project/download-config-json.png" alt-text="Screenshot of project drop-down menu with the download config file hyperlink in the Azure AI Foundry.":::
+
+### [REST APIs](#tab/rest-api)
+
+You can export a CLU project as a config.json file.
+
+[!INCLUDE [Export project](../includes/rest-api/export-project.md)]
+
+---
+
+
+## Delete a project
+
+Deleting a project ensures that it and all of its associated data are permanently removed from the system.
+
+### [Azure AI Foundry](#tab/azure-ai-foundry)
 
 If you no longer need your project, you can delete it from the Azure AI Foundry.
 
@@ -113,19 +182,22 @@ To delete the hub along with all its projects:
 
    :::image type="content" source="../media/create-project/hub-details.png" alt-text="Screenshot of the hub details list in the Azure AI Foundry.":::
 
-1. On the right, select **Delete hub**. 
+1. On the right, select **Delete hub**.
 1. The link opens the Azure portal for you to delete the hub there.
 
    :::image type="content" source="../media/create-project/delete-hub.png" alt-text="Screenshot of the Delete hub button in the Azure AI Foundry.":::
 
 ### [REST APIs](#tab/rest-api)
 
-If you no longer need your project, delete it using the REST API.
+If your project is no longer required, you can delete it using the REST API. To proceed, access the REST API and follow the documented steps for project deletion to complete this action.
 
 [!INCLUDE [Delete project](../includes/rest-api/delete-project.md)]
 
 ---
 
-## Related content
+## Next steps
+
+After you create your fine-tuning workspace, start your fine-tuning task by defining your intents and entities and adding them to your schema:
 
-- [Build schema](./build-schema.md)
+* [Build your fine-tuning schema](build-schema.md)
+* [Label utterances](tag-utterances.md)
diff --git a/articles/ai-services/language-service/conversational-language-understanding/how-to/train-model.md b/articles/ai-services/language-service/conversational-language-understanding/how-to/train-model.md
@@ -103,7 +103,9 @@ Use the evaluation scores to guide your decisions. There may be times where a sp
 
    :::image type="content" source="../media/select-project.png" alt-text="Screenshot of conversational language understanding tab in the Azure AI Foundry.":::
 
-1. In **Create CLU fine tuning task** window, complete the **Name** and **Language** fields. If you're using the free **Standard Training** mode, select **English** for the language field.
+1. In **Create CLU fine tuning task** window, select your **Connected service** from the drop-down menu, then complete the **Name** and **Language** fields. If you're using the free **Standard Training** mode, select **English** for the language field.
+
+1. Select the  **Create** button. It may take a few minutes for the create operation to complete.
 
     > [!NOTE]
     >
diff --git a/articles/ai-services/language-service/conversational-language-understanding/media/create-project/getting-started-fine-tuning.png b/articles/ai-services/language-service/conversational-language-understanding/media/create-project/getting-started-fine-tuning.png
diff --git a/articles/ai-services/language-service/toc.yml b/articles/ai-services/language-service/toc.yml
@@ -148,10 +148,10 @@ items:
             href: ../containers/azure-container-instance-recipe.md?context=/azure/ai-services/language-service/context/context
           - name: Azure AI containers overview
             href: ../cognitive-services-container-support.md
-        - name: Create a CLU Foundry project 
+        - name: Create a fine-tuning task project
           href: conversational-language-understanding/how-to/create-project.md
           displayName: creation, clu project, setup
-        - name: Build a schema
+        - name: Build a fine-tuning schema
           href: conversational-language-understanding/how-to/build-schema.md
           displayName: design, intents, entities, conversational model
         - name: Label utterances

Original file line number	Diff line number	Diff line change
`@@ -103,7 +103,9 @@ Use the evaluation scores to guide your decisions. There may be times where a sp`
`103`	`103`
`104`	`104`	`:::image type="content" source="../media/select-project.png" alt-text="Screenshot of conversational language understanding tab in the Azure AI Foundry.":::`
`105`	`105`
`106`		`-1. In Create CLU fine tuning task window, complete the Name and Language fields. If you're using the free Standard Training mode, select English for the language field.`
	`106`	`+1. In Create CLU fine tuning task window, select your Connected service from the drop-down menu, then complete the Name and Language fields. If you're using the free Standard Training mode, select English for the language field.`
	`107`	`+`
	`108`	`+1. Select the Create button. It may take a few minutes for the create operation to complete.`
`107`	`109`
`108`	`110`	`> [!NOTE]`
`109`	`111`	`>`