Merge pull request #284206 from MicrosoftDocs/main

8/09/2024 AM Publish

Author: Albertyang0

articles/ai-studio/concepts/rbac-ai-studio.md

@@ -123,7 +123,7 @@ The following table is an example of how to set up role-based access control for
 | --- | --- | ---|
 | IT admin | Owner of the hub | The IT admin can ensure the hub is set up to their enterprise standards. They can assign managers the Contributor role on the resource if they want to enable managers to make new hubs. Or they can assign managers the Azure AI Developer role on the resource to not allow for new hub creation. |
 | Managers | Contributor or Azure AI Developer on the hub | Managers can manage the hub, audit compute resources, audit connections, and create shared connections. |
-| Team lead/Lead developer | Azure AI Developer on the hub | Lead developers can create projects for their team and create shared resources (ex: compute and connections) at the hub level. After project creation, project owners can invite other members. |
+| Team lead/Lead developer | Azure AI Developer on the hub | Lead developers can create projects for their team and create shared resources (such as compute and connections) at the hub level. After project creation, project owners can invite other members. |
 | Team members/developers | Contributor or Azure AI Developer on the project | Developers can build and deploy AI models within a project and create assets that enable development such as computes and connections. |
 
 ## Access to resources created outside of the hub

articles/ai-studio/how-to/flow-deploy.md

@@ -173,12 +173,12 @@ If you enable this, tracing data and system metrics during inference time (such
 ## Grant permissions to the endpoint
 
 > [!IMPORTANT]
-> Granting permissions (adding role assignment) is only enabled to the **Owner** of the specific Azure resources. You might need to ask your IT admin for help.
+> Granting permissions (adding role assignment) is only enabled to the **Owner** of the specific Azure resources. You might need to ask your Azure subscription owner (who might be your IT admin) for help.
 >
 > It's recommended to grant roles to the **user-assigned** identity **before the deployment creation**.
 > It might take more than 15 minutes for the granted permission to take effect.
 
-You can grant all permissions in Azure portal UI by following steps.
+You can grant the required permissions in Azure portal UI by following steps.
 
 1. Go to the Azure AI Studio project overview page in [Azure portal](https://ms.portal.azure.com/#home).
 

articles/ai-studio/includes/create-projects.md

@@ -15,7 +15,7 @@ To create a project in [Azure AI Studio](https://ai.azure.com), follow these ste
 1. Go to the **Home** page of [Azure AI Studio](https://ai.azure.com). 
 1. Select **+ New project**.
 1. Enter a name for the project.
-1. Select a hub from the dropdown to host your project. If you don't have access to a hub yet, select **Create a new hub**.
+1. Select a hub from the dropdown to host your project. For information about the relationship between hubs and projects, see the [hubs and projects overview](../concepts/ai-resources.md) documentation. If you don't yet have a hub, select **Create a new hub**.
 
     :::image type="content" source="../media/how-to/projects/projects-create-details.png" alt-text="Screenshot of the project details page within the create project dialog." lightbox="../media/how-to/projects/projects-create-details.png":::
 

articles/ai-studio/quickstarts/get-started-code.md

@@ -21,7 +21,7 @@ In this quickstart, we walk you through setting up your local development enviro
 ## Prerequisites
 
 > [!IMPORTANT]
-> You must have the necessary permissions to add role assignments for storage accounts in your Azure subscription. Granting permissions (adding role assignment) is only allowed by the **Owner** of the specific Azure resources. You might need to ask your IT admin for help to [grant access to call Azure OpenAI Service using your identity](#grant-access-to-call-azure-openai-service-using-your-identity).
+> You must have the necessary permissions to add role assignments for storage accounts in your Azure subscription. Granting permissions (adding role assignment) is only allowed by the **Owner** of the specific Azure resources. You might need to ask your Azure subscription owner (who might be your IT admin) for help to [grant access to call Azure OpenAI Service using your identity](#grant-access-to-call-azure-openai-service-using-your-identity).
 
 Before you can follow this quickstart, create the resources that you need for your application:
 - An [AI Studio hub](../how-to/create-azure-ai-resource.md) for connecting to external resources.

articles/ai-studio/reference/reference-model-inference-info.md

@@ -110,7 +110,7 @@ The information about the deployed model.
 
 ### ModelType
 
-The infernce task associated with the mode.
+The inference task associated with the mode.
 
 
 | Name | Type | Description |

articles/ai-studio/tutorials/copilot-sdk-build-rag.md

@@ -35,7 +35,7 @@ In this part one, you learn how to:
 ## Prerequisites
 
 > [!IMPORTANT]
-> You must have the necessary permissions to add role assignments in your Azure subscription. Granting permissions by role assignment is only allowed by the **Owner** of the specific Azure resources. You might need to ask your IT admin for help with completing the [assign access](#configure-access-for-the-azure-ai-search-service) section.
+> You must have the necessary permissions to add role assignments in your Azure subscription. Granting permissions by role assignment is only allowed by the **Owner** of the specific Azure resources. You might need to ask your Azure subscription owner (who might be your IT admin) for help with completing the [assign access](#configure-access-for-the-azure-ai-search-service) section.
 
 - You need to complete the [Build a custom chat app in Python using the prompt flow SDK quickstart](../quickstarts/get-started-code.md) to set up your environment. 
 

articles/ai-studio/tutorials/copilot-sdk-evaluate-deploy.md

@@ -29,7 +29,7 @@ In this part two, you learn how to:
 
 - You must complete [part 1 of the tutorial series](copilot-sdk-build-rag.md) to build the copilot application.
 
-- You must have the necessary permissions to add role assignments in your Azure subscription. Granting permissions by role assignment is only allowed by the **Owner** of the specific Azure resources. You might need to ask your IT admin for help with completing the [assign access](#assign-access-for-the-endpoint) section.
+- You must have the necessary permissions to add role assignments in your Azure subscription. Granting permissions by role assignment is only allowed by the **Owner** of the specific Azure resources. You might need to ask your Azure subscription owner (who might be your IT admin) for help with endpoint access later in the tutorial.
 
 ## Evaluate the quality of copilot responses
 
@@ -213,15 +213,13 @@ We recommend you test your application in the Azure AI Studio. If you prefer to
 
 Note your endpoint name, which you need for the next steps.
 
-### Assign access for the endpoint
-
-While you wait for your application to deploy, you or your administrator can assign role-based access to the endpoint. These roles allow the application to run without keys in the deployed environment, just like it did locally.
+### Endpoint access for Azure OpenAI resource
 
-Previously, you provided your account with a specific role to be able to access the resource using Microsoft Entra ID authentication. Now, assign the endpoint that same role.
+You might need to ask your Azure subscription owner (who might be your IT admin) for help with this section.
 
-### Endpoint access for Azure OpenAI resource
+While you wait for your application to deploy, you or your administrator can assign role-based access to the endpoint. These roles allow the application to run without keys in the deployed environment, just like it did locally.
 
-You or your administrator needs to grant your endpoint the **Cognitive Services OpenAI User** role on the Azure AI Services resource that you're using. This role lets your endpoint call the Azure OpenAI service.
+Previously, you provided your account with a specific role to be able to access the resource using Microsoft Entra ID authentication. Now, assign the endpoint that same **Cognitive Services OpenAI User** role.
 
 > [!NOTE]
 > These steps are similar to how you assigned a role for your user identity to use the Azure OpenAI Service in the [quickstart](../quickstarts/get-started-code.md).
@@ -259,6 +257,8 @@ To grant yourself access to the Azure AI Services resource that you're using:
 
 ### Endpoint access for Azure AI Search resource
 
+You might need to ask your Azure subscription owner (who might be your IT admin) for help with this section.
+
 Similar to how you assigned the **Search Index Data Contributor** [role to your Azure AI Search service](./copilot-sdk-build-rag.md#configure-access-for-the-azure-ai-search-service), you need to assign the same role for your endpoint.
 
 1. In Azure AI Studio, select **Settings** and navigate to the connected **Azure AI Search** service. 

articles/ai-studio/tutorials/deploy-chat-web-app.md

@@ -24,18 +24,17 @@ Your data source is used to help ground the model with specific data. Grounding
 
 The steps in this tutorial are:
 
-1. Deploy and test a chat model without your data
-1. Add your data
-1. Test the model with your data
-1. Deploy your web app
-
+1. Deploy and test a chat model without your data.
+1. Add your data.
+1. Test the model with your data.
+1. Deploy your web app.
 
 ## Prerequisites
 
 - An Azure subscription - <a href="https://azure.microsoft.com/free/cognitive-services" target="_blank">Create one for free</a>.
 - An [AI Studio hub](../how-to/create-azure-ai-resource.md), [project](../how-to/create-projects.md), and [deployed Azure OpenAI](../how-to/deploy-models-openai.md) chat model. Complete the [AI Studio playground quickstart](../quickstarts/get-started-playground.md) to create these resources if you haven't already.
 
-- An [Azure AI Search service connection](../how-to/connections-add.md#create-a-new-connection) to index the sample product and customer data. 
+- An [Azure AI Search service connection](../how-to/connections-add.md#create-a-new-connection) to index the sample product data. 
 
 - You need a local copy of product data. The [Azure-Samples/rag-data-openai-python-promptflow repository on GitHub](https://github.com/Azure-Samples/rag-data-openai-python-promptflow/) contains sample retail product information that's relevant for this tutorial scenario. Specifically, the `product_info_11.md` file contains product information about the TrailWalker hiking shoes that's relevant for this tutorial example. [Download the example Contoso Trek retail product data in a ZIP file](https://github.com/Azure-Samples/rag-data-openai-python-promptflow/raw/main/tutorial/data.zip) to your local machine.
 
@@ -51,7 +50,7 @@ Once you're satisfied with the experience in Azure AI Studio, you can deploy the
 
 ### Find your resource group in the Azure portal
 
-In this tutorial, your web app is deployed to the same resource group as your AI Studio hub. Later you configure authentication for the web app in the Azure portal.
+In this tutorial, your web app is deployed to the same resource group as your [AI Studio hub](../how-to/create-secure-ai-hub.md). Later you configure authentication for the web app in the Azure portal.
 
 Follow these steps to navigate from Azure AI Studio to your resource group in the Azure portal:
 
@@ -60,7 +59,7 @@ Follow these steps to navigate from Azure AI Studio to your resource group in th
 
     :::image type="content" source="../media/tutorials/chat/resource-group-manage-page.png" alt-text="Screenshot of the resource group in the Azure AI Studio." lightbox="../media/tutorials/chat/resource-group-manage-page.png":::
 
-1. You should now be in the Azure portal, viewing the contents of the resource group where you deployed the hub. Keep this page open in a browser tab - you return to it later.
+1. You should now be in the Azure portal, viewing the contents of the resource group where you deployed the hub. Keep this page open in a browser tab. You return to it later.
 
 ### Deploy the web app
 
@@ -124,7 +123,7 @@ You're almost there! Now you can test the web app.
 
     *If the authentication settings haven't yet taken effect, close the browser tab for your web app and return to the chat playground in Azure AI Studio. Then wait a little longer and try again.*
 
-1. In your web app, you can ask the same question as before ("How much are the TrailWalker hiking shoes"), and this time it uses information from your data to construct the response. You can expand the **references** button to see the data that was used.
+1. In your web app, you can ask the same question as before ("How much are the TrailWalker hiking shoes"), and this time it uses information from your data to construct the response. You can expand the **reference** button to see the data that was used.
 
    :::image type="content" source="../media/tutorials/chat/chat-with-data-web-app.png" alt-text="Screenshot of the chat experience via the deployed web app." lightbox="../media/tutorials/chat/chat-with-data-web-app.png":::
 
@@ -150,7 +149,7 @@ Once you've enabled chat history, your users will be able to show and hide it in
 
 If you delete the Cosmos DB resource but keep the chat history option enabled on the studio, your users will be notified of a connection error, but can continue to use the web app without access to the chat history.
 
-## Next steps
+## Related content
 
-- [Create a project in Azure AI Studio](../how-to/create-projects.md).
-- Learn more about what you can do in the [Azure AI Studio](../what-is-ai-studio.md).
+- [Build and deploy a question and answer copilot with prompt flow in Azure AI Studio.](./deploy-copilot-ai-studio.md).
+- [Build your own copilot with the prompt flow SDK.](./copilot-sdk-build-rag.md).

articles/ai-studio/tutorials/screen-reader.md

@@ -8,16 +8,14 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: quickstart
-ms.date: 5/21/2024
+ms.date: 8/9/2024
 ms.reviewer: ailsaleen
 ms.author: eur
 author: eric-urban
 ---
 
 # QuickStart: Get started using AI Studio with a screen reader
 
-[!INCLUDE [Feature preview](~/reusable-content/ce-skilling/azure/includes/ai-studio/includes/feature-preview.md)]
-
 This article is for people who use screen readers such as [Microsoft's Narrator](https://support.microsoft.com/windows/complete-guide-to-narrator-e4397a0d-ef4f-b386-d8ae-c172f109bdb1#WindowsVersion=Windows_11), JAWS, NVDA or Apple's Voiceover. In this quickstart, you'll be introduced to the basic structure of Azure AI Studio and discover how to navigate around efficiently. 
 
 ## Getting oriented in Azure AI Studio 
@@ -78,7 +76,6 @@ Once you have created or selected a project, go to the navigation landmark. Pres
 
 The prompt flow UI in Azure AI Studio is composed of the following main sections: the command toolbar, flow (includes list of the flow nodes), files, and graph view. The flow, files, and graph sections each have their own H2 headings that can be used for navigation.
 
-
 ### Flow 
 
 - This is the main working area where you can edit your flow, for example adding a new node, editing the prompt, selecting input data 

articles/api-management/TOC.yml

@@ -217,7 +217,7 @@
         href: sap-api.md
     - name: Import gRPC API
       href: grpc-api.md
-    - name: Azure OpenAI
+    - name: Azure OpenAI and LLM APIs
       items:
       - name: Import Azure OpenAI API
         href: azure-openai-api-from-specification.md
@@ -543,6 +543,14 @@
       href: json-to-xml-policy.md
     - name: limit-concurrency
       href: limit-concurrency-policy.md
+    - name: llm-emit-token-metric
+      href: llm-emit-token-metric-policy.md
+    - name: llm-semantic-cache-lookup
+      href: llm-semantic-cache-lookup-policy.md
+    - name: llm-semantic-cache-store
+      href: llm-semantic-cache-store-policy.md
+    - name: llm-token-limit
+      href: llm-token-limit-policy.md
     - name: log-to-eventhub
       href: log-to-eventhub-policy.md
     - name: mock-response