Merge pull request #5809 from MicrosoftDocs/main

Merged by Learn.Build PR Management system

Author: learn-build-service-prod[bot]

articles/ai-foundry/concepts/prompt-flow.md

@@ -9,7 +9,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: concept-article
-ms.date: 03/18/2025
+ms.date: 06/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/foundry-models/how-to/monitor-models.md

@@ -5,7 +5,7 @@ author: ssalgadodev
 ms.author: ssalgado
 ms.service: azure-ai-model-inference
 ms.topic: how-to
-ms.date: 4/30/2025
+ms.date: 06/30/2025
 manager: scottpolly
 ms.reviewer: fasantia
 reviewer: santiagxf
@@ -26,7 +26,7 @@ To use monitoring capabilities for model deployments in Foundry Models, you need
 * An Azure AI services resource. For more information, see [Create an Azure AI Services resource](../../model-inference/how-to/quickstart-create-resources.md).
 
     > [!TIP]
-    > If you are using Serverless API Endpoints and you want to take advantage of monitoring capabilities explained in this document, [migrate your Serverless API Endpoints to Foundry Models](../../model-inference/how-to/quickstart-ai-project.md).
+    > If you're using Serverless API Endpoints and you want to take advantage of monitoring capabilities explained in this document, [migrate your Serverless API Endpoints to Foundry Models](../../model-inference/how-to/quickstart-ai-project.md).
 
 * At least one model deployment.
 
@@ -54,11 +54,15 @@ You can view metrics within Azure AI Foundry portal. To view them, follow these
 
 1. Select the tab **Metrics**.
 
-1. You can see a high level view of the most common metrics you may be interested about.
+1. You can access an overview of common metrics that might be of interest. For cost-related metrics, use the Azure Cost Management deep link, which provides access to detailed post-consumption cost metrics in the Cost analysis section located in the Azure portal. Cost data in Azure portal displays actual post-consumption charges for model consumption, including other AI resources within Azure AI Foundry. Follow this link for a full list of [AI resources](https://azure.microsoft.com/products/ai-services#tabs-pill-bar-oc14f0_tab0). There's approximately a five hour delay from the billing event to when it can be viewed in Azure portal cost analysis.
 
     :::image type="content" source="../media/monitor-models/deployment-metrics.png" alt-text="Screenshot showing the metrics displayed for model deployments in Azure AI Foundry portal." lightbox="../media/monitor-models/deployment-metrics.png":::
 
-1. To slice, filter, or view model details about the metrics you can **Open in Azure Monitor**, where you have more advanced options.
+    > [!IMPORTANT]
+    > The **Azure Cost Management deep link**  provides a direct link within the Azure portal, allowing users to access detailed cost metrics for deployed AI models. This deep link integrates with the Azure Cost Analysis service view, offering transparent and actionable insights into model-level costs.
+    > The deep link directs users to the Cost Analysis view in the Azure portal, providing a one-click experience to view deployments per resource, including input/output token cost/consumption. To view cost data, you need at least read access for an Azure account. For information about assigning access to Microsoft Cost Management data, see [Assign access to data](/azure/cost-management-billing/costs/assign-access-acm-data). 
+
+1. You can **view and analyze metrics with Azure Monitor metrics explorer** to further slice and filter your model deployment metrics.
 
     :::image type="content" source="../media/monitor-models/deployment-metrics-azmonitor.png" alt-text="Screenshot showing the option to open model deployment metrics in Azure Monitor." lightbox="../media/monitor-models/deployment-metrics-azmonitor.png":::
 
@@ -91,7 +95,7 @@ To use Azure Monitor, follow these steps:
 
     :::image type="content" source="../media/monitor-models/azmon-add-filter.png" alt-text="Screenshot showing how to apply a filter to a metric." lightbox="../media/monitor-models/azmon-add-filter.png":::
 
-1. It is useful to break down specific metrics by some of the dimensions. The following example shows how to break down the number of requests made to the resource by model by using the option **Add splitting**:
+1. It's useful to break down specific metrics by some of the dimensions. The following example shows how to break down the number of requests made to the resource by model by using the option **Add splitting**:
 
     :::image type="content" source="../media/monitor-models/azmon-add-splitting.png" alt-text="Screenshot showing how to split the metric by a given dimension." lightbox="../media/monitor-models/azmon-add-splitting.png":::
 

articles/ai-foundry/foundry-models/media/monitor-models/deployment-metrics-azmonitor.png

@@ -9,7 +9,7 @@ ms.custom:
   - build-2024
   - references_regions
 ms.topic: how-to
-ms.date: 10/24/2024
+ms.date: 06/30/2025
 ms.reviewer: minthigpen
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/foundry-models/media/monitor-models/deployment-metrics.png

@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
 ms.custom:
   - build-2024
 ms.topic: how-to
-ms.date: 02/14/2025
+ms.date: 06/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/develop/simulator-interaction-data.md

@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
 ms.custom:
   - build-2024
 ms.topic: reference
-ms.date: 01/29/2025
+ms.date: 06/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/flow-process-image.md

@@ -8,7 +8,7 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: reference
-ms.date: 01/29/2025
+ms.date: 06/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/prompt-flow-tools/azure-open-ai-gpt-4v-tool.md

@@ -8,7 +8,7 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: reference
-ms.date: 01/29/2025
+ms.date: 6/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/prompt-flow-tools/content-safety-tool.md

@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
 ms.custom:
   - build-2024
 ms.topic: reference
-ms.date: 01/29/2025
+ms.date: 6/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/prompt-flow-tools/embedding-tool.md

@@ -8,7 +8,7 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: reference
-ms.date: 1/29/2025
+ms.date: 6/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/prompt-flow-tools/index-lookup-tool.md

@@ -7,7 +7,7 @@ ms.service: azure-ai-foundry
 ms.custom:
   - build-2024
 ms.topic: reference
-ms.date: 01/29/2025
+ms.date: 6/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/prompt-flow-tools/llm-tool.md

@@ -8,7 +8,7 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: reference
-ms.date: 01/29/2025
+ms.date: 6/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/prompt-flow-tools/prompt-flow-tools-overview.md

@@ -6,7 +6,7 @@ manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom: ignite-2023, devx-track-python, build-2024, ignite-2024
 ms.topic: reference
-ms.date: 01/29/2025
+ms.date: 6/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/prompt-flow-tools/prompt-tool.md

@@ -5,7 +5,7 @@ description: This article introduces you to the Rerank tool for flows in Azure A
 manager: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: reference
-ms.date: 01/29/2025
+ms.date: 6/30/2025
 ms.reviewer: jingyizhu
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/prompt-flow-tools/python-tool.md

@@ -8,7 +8,7 @@ ms.custom:
   - ignite-2023
   - build-2024
 ms.topic: reference
-ms.date: 01/31/2025
+ms.date: 6/30/2025
 ms.reviewer: none
 ms.author: lagayhar
 author: lgayhardt

articles/ai-foundry/how-to/prompt-flow-tools/rerank-tool.md

@@ -7,16 +7,16 @@ ms.service: azure-ai-services
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 01/10/2025
+ms.date: 06/30/2025
 ---
 
 # Autoscale AI services limits
 
-This article provides guidance for how customers can access higher rate limits on certain Azure AI services resources.
+This article provides guidance on how customers can access higher rate limits on certain Azure AI services resources.
 
 ## Overview
 
-Each Azure AI services resource has a pre-configured static call rate (transactions per second) which limits the number of concurrent calls that customers can make to the backend service in a given time frame. The autoscale feature will automatically increase/decrease a customer's resource's rate limits based on near-real-time resource usage metrics and backend service capacity metrics.
+Each Azure AI services resource has a pre-configured static call rate (transactions per second) which limits the number of concurrent calls that customers can make to the service in a given time frame. The autoscale feature will automatically increase/decrease a customer's resource's rate limits based on near-real-time resource usage metrics and backend service capacity metrics.
 
 ## Get started with the autoscale feature
 
@@ -84,7 +84,7 @@ Be aware of potential errors and their consequences. If a bug in your client app
 Yes, you can disable the autoscale feature through Azure portal or CLI and return to your default call rate limit setting. If your resource was previously approved for a higher default TPS, it goes back to that rate. It can take up to five minutes for the changes to go into effect.
 
 
-## Next steps
+## Related content
 
 * [Plan and Manage costs for Azure AI services](../ai-foundry/how-to/costs-plan-manage.md).
 * [Optimize your cloud investment with Microsoft Cost Management](/azure/cost-management-billing/costs/cost-mgt-best-practices?WT.mc_id=costmanagementcontent_docsacmhorizontal_-inproduct-learn).

articles/ai-foundry/how-to/prompt-flow-tools/serp-api-tool.md

@@ -6,7 +6,7 @@ author: PatrickFarley
 manager: nitinme
 ms.service: azure-ai-vision
 ms.topic: how-to
-ms.date: 06/26/2024
+ms.date: 06/30/2025
 ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.update-cycle: 365-days
 ms.author: pafarley
@@ -15,7 +15,7 @@ keywords: on-premises, OCR, Docker, container
 
 # Install Azure AI Vision 3.2 GA Read OCR container
 
-Containers let you run the Azure AI Vision APIs in your own environment and can help you meet specific security and data governance requirements. In this article you'll learn how to download, install, and run the Azure AI Vision Read (OCR) container.
+Containers let you run the Azure AI Vision APIs in your own environment and can help you meet specific security and data governance requirements. In this article you learn how to download, install, and run the Azure AI Vision Read (OCR) container.
 
 The Read container allows you to extract printed and handwritten text from images and documents in JPEG, PNG, BMP, PDF, and TIFF file formats. For more information on the Read service, see the [Read API how-to guide](how-to/call-read-api.md).
 
@@ -30,7 +30,7 @@ The Read 3.2 OCR container is the latest GA model and provides:
 * Support for larger documents and images.
 * Confidence scores.
 * Support for documents with both print and handwritten text.
-* Ability to extract text from only selected page(s) in a document.
+* Ability to extract text from only selected pages in a document.
 * Choose text line output order from default to a more natural reading order for Latin languages only.
 * Text line classification as handwritten style or not for Latin languages only.
 
@@ -133,7 +133,7 @@ mcr.microsoft.com/azure-cognitive-services/vision/read:3.2-model-2022-04-30
 More [examples](./computer-vision-resource-container-config.md#example-docker-commands) of the `docker run` command are available. 
 
 > [!IMPORTANT]
-> The `Eula`, `Billing`, and `ApiKey` options must be specified to run the container; otherwise, the container won't start.  For more information, see [Billing](#billing).
+> The `Eula`, `Billing`, and `ApiKey` options must be specified to run the container; otherwise, the container won't start. For more information, see [Billing](#billing).
 
 <!--If you need higher throughput (for example, when processing multi-page files), consider deploying multiple containers [on a Kubernetes cluster](deploy-computer-vision-on-premises.md), using [Azure Storage](/azure/storage/common/storage-account-create) and [Azure Queue](/azure/storage/queues/storage-queues-introduction).-->
 
@@ -143,7 +143,7 @@ To find your connection string:
 
 1. Navigate to **Storage accounts** on the Azure portal, and find your account.
 2. Select on **Access keys** in the left pane.
-3. Your connection string will be located below **Connection string**
+3. Your connection string is located below **Connection string**
 
 [!INCLUDE [Running multiple containers on the same host](../includes/cognitive-services-containers-run-multiple-same-host.md)]
 
@@ -159,9 +159,9 @@ Use the host, `http://localhost:5000`, for container APIs. You can view the Swag
 
 ### Asynchronous Read
 
-You can use the `POST /vision/v3.2/read/analyze` and `GET /vision/v3.2/read/operations/{operationId}` operations in concert to asynchronously read an image, similar to how the Azure AI Vision service uses those corresponding REST operations. The asynchronous POST method will return an `operationId` that is used as the identifier to the HTTP GET request.
+You can use the `POST /vision/v3.2/read/analyze` and `GET /vision/v3.2/read/operations/{operationId}` operations in concert to asynchronously read an image, similar to how the Azure AI Vision service uses those corresponding REST operations. The asynchronous POST method returns an `operationId` that is used as the identifier to the HTTP GET request.
 
-From the swagger UI, select the `Analyze` to expand it in the browser. Then select **Try it out** > **Choose file**. In this example, we'll use the following image:
+From the swagger UI, select the `Analyze` to expand it in the browser. Then select **Try it out** > **Choose file**. In this example, we use the following image:
 
 ![tabs vs spaces](media/tabs-vs-spaces.png)
 
@@ -174,7 +174,7 @@ When the asynchronous POST has run successfully, it returns an **HTTP 202** stat
  server: Kestrel
 ```
 
-The `operation-location` is the fully qualified URL and is accessed via an HTTP GET. Here is the JSON response from executing the `operation-location` URL from the preceding image:
+The `operation-location` is the fully qualified URL and is accessed via an HTTP GET. Here's the JSON response from executing the `operation-location` URL from the preceding image:
 
 ```json
 {
@@ -284,7 +284,7 @@ The `operation-location` is the fully qualified URL and is accessed via an HTTP
 
 
 > [!IMPORTANT]
-> If you deploy multiple Read OCR containers behind a load balancer, for example, under Docker Compose or Kubernetes, you must have an external cache. Because the processing container and the GET request container might not be the same, an external cache stores the results and shares them across containers. For details about cache settings, see [Configure Azure AI Vision Docker containers](./computer-vision-resource-container-config.md).
+> If you deploy multiple Read OCR containers behind a load balancer, for example, under Docker Compose or Kubernetes, you must have an external cache. Because the processing container and the `GET` request container might not be the same, an external cache stores the results and shares them across containers. For details about cache settings, see [Configure Azure AI Vision Docker containers](./computer-vision-resource-container-config.md).
 
 ### Synchronous read
 

articles/ai-foundry/media/azure-openai-in-ai-studio/ai-studio-no-project.png

@@ -61,12 +61,12 @@ The following are the main steps of the image retrieval process using Multimodal
 
 ### Relevance score 
 
-The image and video retrieval services return a field called "relevance." The term "relevance" denotes a measure of similarity between a query and image or video frame embeddings. The relevance score is composed of two parts:
-1. The cosine similarity (that falls in the range of [0,1]) between the query and image or video frame embeddings.
-1. A metadata score, which reflects the similarity between the query and the metadata associated with the image or video frame.
+The image retrieval service returns a field called "relevance." The term "relevance" denotes a measure of similarity between a query and image embeddings. The relevance score is composed of two parts:
+1. The cosine similarity (that falls in the range of [0,1]) between the query and image embeddings.
+1. A metadata score, which reflects the similarity between the query and the metadata associated with the image.
 
 > [!IMPORTANT]
-> The relevance score is a good measure to rank results such as images or video frames with respect to a single query. However, the relevance score cannot be accurately compared across queries. Therefore, it's not possible to easily map the relevance score to a confidence level. It's also not possible to trivially create a threshold algorithm to eliminate irrelevant results based solely on the relevance score. 
+> The relevance score is a good measure to rank results such as images with respect to a single query. However, the relevance score cannot be accurately compared across queries. Therefore, it's not possible to easily map the relevance score to a confidence level. It's also not possible to trivially create a threshold algorithm to eliminate irrelevant results based solely on the relevance score. 
 
 ## Input requirements
 

articles/ai-foundry/media/azure-openai-in-ai-studio/ai-studio-project.png

@@ -9,7 +9,7 @@ ms.update-cycle: 365-days
 ms.author: pafarley
 ms.service: azure-ai-vision
 ms.topic: how-to
-ms.date: 06/01/2024
+ms.date: 06/30/2025
 ms.custom:  devx-track-python, devx-track-extended-java, devx-track-js
 zone_pivot_groups: programming-languages-computer-vision
 ---
@@ -49,7 +49,7 @@ This article demonstrates how to call the Image Analysis 4.0 API to return infor
 
 ::: zone-end
 
-## Next steps
+## Related content
 
 * Explore the [concept articles](../concept-describe-images-40.md) to learn more about each feature.
 * Explore the SDK code samples on GitHub:

articles/ai-foundry/media/azure-openai-in-ai-studio/model-catalog.png

@@ -4,18 +4,18 @@ manager: nitinme
 ms.service: ai-services
 ms.subservice: computer-vision
 ms.topic: include
-ms.date: 08/01/2023
+ms.date: 06/30/2025
 ms.collection: "ce-skilling-fresh-tier2, ce-skilling-ai-copilot"
 ms.update-cycle: 365-days
 ms.author: pafarley
 ---
 
 ## Prerequisites
 
-This guide assumes you have successfully followed the steps mentioned in the [quickstart](/azure/ai-services/computer-vision/quickstarts-sdk/image-analysis-client-library-40) page. This means:
+This guide assumes you've successfully followed the steps mentioned in the [quickstart](/azure/ai-services/computer-vision/quickstarts-sdk/image-analysis-client-library-40) page. This means:
 
-* You have <a href="https://portal.azure.com/#create/Microsoft.CognitiveServicesComputerVision"  title="created a Computer Vision resource"  target="_blank">created a Computer Vision resource </a> and obtained a key and endpoint URL.
-* You have successfully made a `curl.exe` call to the service (or used an alternative tool). You modify the `curl.exe` call based on the examples here.
+* You've <a href="https://portal.azure.com/#create/Microsoft.CognitiveServicesComputerVision"  title="created a Computer Vision resource"  target="_blank">created a Computer Vision resource </a> and obtained a key and endpoint URL.
+* You've successfully made a `curl.exe` call to the service (or used an alternative tool). You modify the `curl.exe` call based on the examples here.
 
 ## Authenticate against the service
 
@@ -69,7 +69,7 @@ A populated URL might look like this:
 
 ### Set model name when using a custom model
 
-You can also do image analysis with a custom trained model. To create and train a model, see [Create a custom Image Analysis model](/azure/ai-services/computer-vision/how-to/model-customization). Once your model is trained, all you need is the model's name. You do not need to specify visual features if you use a custom model.
+You can also do image analysis with a custom trained model. To create and train a model, see [Create a custom Image Analysis model](/azure/ai-services/computer-vision/how-to/model-customization). Once your model is trained, all you need is the model's name. You don't need to specify visual features if you use a custom model.
 
 
 To use a custom model, don't use the features query parameter. Instead, set the `model-name` parameter to the name of your model as shown here. Replace `MyCustomModelName` with your custom model name.
@@ -272,7 +272,7 @@ The service returns a `200` HTTP response, and the body contains the returned da
 
 ## Error codes
 
-On error, the Image Analysis service response contains a JSON payload that includes an error code and error message. It may also include other details in the form of and inner error code and message. For example:
+On error, the Image Analysis service response contains a JSON payload that includes an error code and error message. It might also include other details in the form of and inner error code and message. For example:
 
 ```json
 {