Merge pull request #6249 from MicrosoftDocs/main

Auto Publish – main to live - 2025-07-28 17:07 UTC

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

articles/ai-foundry/agents/how-to/virtual-networks.md

@@ -78,79 +78,24 @@ For customers without an existing virtual network, the Standard Setup with Priva
 
 ## Configure a new network-secured environment 
 
-**Network secured setup**: Agents use customer-owned, single-tenant search and storage resources. With this setup, you have full control and visibility over these resources, but you incur costs based on your usage. The following bicep template provides:
-
-* An account and project are created. 
-* A gpt-4o model is deployed. 
-* Azure resources for storing customer data — Azure Storage, Azure Cosmos DB, and Azure AI Search — are automatically created if existing resources are not provided. 
-* These resources are connected to your project to store files, threads, and vector data. 
-* A Microsoft-managed key vault is used by default. 
-
-
-### Manually deploy the bicep template
-
 > [!NOTE]
-> Using the Bicep template is the only way to deploy a network secured environment for Azure AI Foundry Agent Service.
+> - Programmatic deployment is required to set up a network-secured environment for Azure AI Foundry Agent Service. Deployment through the Azure portal is currently not supported.
+> - If you want to delete your Foundry resource and Standard Agent with secured network set-up, delete your AI Foundry resource and virtual network last. Before deleting the virtual network, ensure to delete and [purge](../../../ai-services/recover-purge-resources.md#purge-a-deleted-resource) your AI Foundry resource.
+> - In the Standard Setup, agents use customer-owned, single-tenant resources. You have full control and visibility over these resources, but you incur costs based on your usage.
 
-1. To deploy and customize the bicep templates, [download the template from GitHub](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/microsoft/infrastructure-setup/15-private-network-standard-agent-setup). Download the following from the `private-network-standard-agent-setup` folder:
-    1. `main-create.bicep`
-    1. `azuredeploy.parameters.json`
-    1. `modules-network-secured folder`
-1. To authenticate to your Azure subscription from the Azure CLI, use the following command: 
+You can deploy and customize the Standard Setup with Private Networking using either Bicep or Terraform. The provided samples allow you to bring your own virtual network and customize the deployment to meet your specific requirements:
 
-    ```console
-    az login
-    ```
-
-1. Create a resource group:
-
-    ```console
-    az group create --name {my_resource_group} --location eastus
-    ```
+* Foundry account and Foundry project are created.
+* A gpt-4o model is deployed.
+* Azure resources for storing customer data — Azure Storage, Azure Cosmos DB, and Azure AI Search — are automatically created if existing resources are not provided. 
+* These resources are connected to your project to store files, threads, and vector data.
+* Microsoft-managed encryption keys for Storage Account and Cognitive Account (AI Foundry) are used by default.
+ 
+Select one of the available deployment methods:
 
-    Make sure you have the Azure AI Developer role for the resource group you created. 
-
-1. Using the resource group you created in the previous step and one of the template files (`private-network-standard-agent-setup`), run one of the following commands: 
-
-    1. To use default resource names, run:
-
-        ```console
-        az deployment group create --resource-group {my_resource_group} --template-file main-create.bicep
-        ```
-
-1. Run the CheckCapabilityHostReadiness.ps1 and edit the command to add your subscription ID, resource group name, and your newly deployed AI Services account resource name.
-   
-   ```
-   .\CheckCapabilityHostReadiness.ps1 -subscriptionId "<your-sub-id>" -resourcegroup "<new-rg-name>" -accountname "<your-aiservices-name>"
-   ```
-   
-   If you don't want to run the PowerShell script, you can run a bash script instead, from the file CheckCapabilityHostReadiness.sh. Run the following two commands:
-   
-      ```
-      chmod +x CheckCapabilityHostReadiness.sh
-      ./CheckCapabilityHostReadiness.sh "<your-sub-id>" "<new-rg-name>" "<your-aiservices-name>"
-      ```
-      
-1. Deploy the main-project-caphost-create.bicep
-   
-   ```
-   az deployment group create --resource-group <new-rg-name> --template-file main-project-caphost-create.bicep
-   ```
-   
-   After running this script, you're required to input the following values:
-   
-   ```
-   Please provide string value for 'accountName' (? for help): <your-account-name>
-   Please provide string value for 'projectName' (? for help): <your-project-name>
-   Please provide string value for 'aiSearchName' (? for help): <your-search-name>
-   Please provide string value for 'azureStorageName' (? for help): <your-storage-name>
-   Please provide string value for 'cosmosDBName' (? for help): <your-cosmosdb-name>
-   ```
-
-For more details, see the [README](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/microsoft/infrastructure-setup/15-private-network-standard-agent-setup).
+- **Bicep templates**: follow instructions in [this sample from GitHub](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/microsoft/infrastructure-setup/15-private-network-standard-agent-setup).
 
-> [!NOTE]
-> If you want to delete your Foundry resource and Standard Agent with secured network set-up, delete your AI Foundry resource and virtual network last. Before deleting the virutal network, ensure to delete and purge your AI Foundry resource. Navigate to __Manage deleted resources__, then select your subscription and the Foundry resource you would like to purge. 
+- **Terraform configuration**: follow instructions in [this sample from GitHub](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/microsoft/infrastructure-setup-terraform/15b-private-network-standard-agent-setup-byovnet).
 
 ## Deep Dive Standard Setup with Private Networking Template
 When you use the Standard Setup with Private Networking Agent Template, the following will automatically be provisioned, unless you bring your own: 

articles/ai-foundry/foundry-agent/ask-foundry-agent.md

@@ -3,7 +3,7 @@ title: Ask the Foundry agent
 titleSuffix: Azure AI Foundry
 description: Learn how to ask the Foundry agent for help, getting your questions answered based on Azure AI Foundry documentation and model catalog.
 ms.service: azure-ai-foundry
-ms.date: 04/28/2025
+ms.date: 07/28/2025
 ms.reviewer: sgilley
 ms.author: jeomhove
 author: jfomhover
@@ -14,7 +14,9 @@ ms.topic: concept-article
 
 ## Overview
 
-The Foundry agent is an experimental feature that is here to assist you with questions about Azure AI Foundry. To start using the Foundry agent, simply click on its icon located in the top right bar of the interface. A chat window opens where you can type your questions and receive answers in real-time.
+The Foundry agent is an experimental feature that is here to assist you with questions about Azure AI Foundry. To start using the Foundry agent, simply click on its icon located in the top right bar of the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs). A chat window opens where you can type your questions and receive answers in real-time.
+
+:::image type="content" source="../media/ask-foundry-agent/ask-foundry.png" alt-text="Screenshot shows the Foundry agent in the top right bar of the Azure AI Foundry portal.":::
 
 [!INCLUDE [feature-preview](../includes/feature-preview.md)]
 

articles/ai-foundry/media/ask-foundry-agent/ask-foundry.png

@@ -75,6 +75,6 @@ To learn more about Microsoft's privacy and security commitments visit [the Micr
 
 ### No data trace
 
-When doing real-time speech to text, pronunciation assessment and speech translation, Microsoft does not retain or store the data provided by customers. In batch transcription, customers specify their own storage locations to send the audio input. Generated transcription text may be stored either in customer's own storage or Microsoft storage if no storage is specified. If output transcriptions are stored in Microsoft storage, customers may delete the data either by calling a deletion API or setting the timeToLive parameter to automatically delete the data in a specified time. See more details in [How to use batch transcription - Speech service - Azure AI services](/azure/cognitive-services/speech-service/batch-transcription).
+When doing real-time speech to text, fast transcription, pronunciation assessment, and speech translation, Microsoft does not retain or store the data provided by customers. In batch transcription, customers specify their own storage locations to send the audio input. Generated transcription text may be stored either in customer's own storage or Microsoft storage if no storage is specified. If output transcriptions are stored in Microsoft storage, customers may delete the data either by calling a deletion API or setting the timeToLive parameter to automatically delete the data in a specified time. See more details in [How to use batch transcription - Speech service - Azure AI services](/azure/cognitive-services/speech-service/batch-transcription).
 
 To learn more about Microsoft's privacy and security commitments visit the Microsoft [Trust Center](https://www.microsoft.com/TrustCenter/CloudServices/Azure/default.aspx).

articles/ai-foundry/responsible-ai/speech-service/speech-to-text/data-privacy-security.md

@@ -85,7 +85,7 @@ This table summarizes features available in the two project types:
 | Evaluations | ✅ | ✅ |
 | Playground | ✅ | ✅ |
 | Prompt flow |  | ✅ |
-| Content understanding  |  | ✅ |
+| Content understanding  | ✅ | ✅ |
 | Project files (directly upload files and start experimenting) | ✅ | |
 | Project-level isolation of files and outputs | ✅ | ✅|
 | Required Azure dependencies | - | Azure Storage account, Azure Key Vault |

articles/ai-foundry/what-is-azure-ai-foundry.md

@@ -285,7 +285,7 @@ The next sections describe specific cases of adjusting quotas.
 
 By default the number of transactions per second is limited to 15 transactions per second for a Document Intelligence resource. For the Standard pricing tier, this amount can be increased. Before submitting the request, ensure you're familiar with the material in [this section](#detailed-description-quota-adjustment-and-best-practices) and aware of these [best practices](#example-of-a-workload-pattern-best-practice).
 
-The fist step would be to enable auto scaling. Follow this document to enable auto scaling on your resource * [enable auto scaling](../../ai-services/autoscale.md). With auto scaling enabled your resource can continue to accept requests over the TPS limits configured if there's capacity on the service. It can still result in request throttled. 
+The first step would be to enable auto scaling. Follow this document to enable auto scaling on your resource * [enable auto scaling](../../ai-services/autoscale.md). With auto scaling enabled your resource can continue to accept requests over the TPS limits configured if there's capacity on the service. It can still result in request throttled. 
 
 Increasing the Concurrent Request limit does **not** directly affect your costs. Document Intelligence service uses "Pay only for what you use" model. The limit defines how high the Service can scale before it starts throttle your requests.
 

articles/ai-services/document-intelligence/service-limits.md

@@ -1,5 +1,15 @@
 {
     "redirections": [
+        {
+            "source_path_from_root": "/articles/search/cognitive-search-incremental-indexing-conceptual.md",
+            "redirect_url": "/azure/search/enrichment-cache-how-to-manage",
+            "redirect_document_id": true
+        },
+                {
+            "source_path_from_root": "/articles/search/search-howto-incremental-index.md",
+            "redirect_url": "/azure/search/enrichment-cache-how-to-configure",
+            "redirect_document_id": true
+        },
         {
             "source_path_from_root": "/articles/search/search-security-network-security-perimiter.md",
             "redirect_url": "/azure/search/search-security-network-security-perimeter",

articles/search/.openpublishing.redirection.search.json

@@ -321,7 +321,7 @@ A [query-time vectorizer](vector-search-how-to-configure-vectorizer.md) backed b
 Image extraction is an Azure AI Search operation that occurs when documents are cracked prior to enrichment. Image extraction is billable on all tiers, except for 20 free daily extractions on the free tier. Image extraction costs apply to image files inside blobs, embedded images in other files (PDF and other app files), and for images extracted using [Document Extraction](cognitive-search-skill-document-extraction.md). For image extraction pricing, see the [Azure AI Search pricing page](https://azure.microsoft.com/pricing/details/search/).
 
 > [!TIP]
-> To lower the cost of skillset processing, enable [incremental enrichment](cognitive-search-incremental-indexing-conceptual.md) to cache and reuse any enrichments that are unaffected by changes made to a skillset. Caching requires Azure Storage (see [pricing](https://azure.microsoft.com/pricing/details/storage/blobs/) but the cumulative cost of skillset execution is lower if existing enrichments can be reused, especially for skillsets that use image extraction and analysis.
+> To lower the cost of skillset processing, enable [incremental enrichment](enrichment-cache-how-to-configure.md) to cache and reuse any enrichments that are unaffected by changes made to a skillset. Caching requires Azure Storage (see [pricing](https://azure.microsoft.com/pricing/details/storage/blobs/) but the cumulative cost of skillset execution is lower if existing enrichments can be reused, especially for skillsets that use image extraction and analysis.
 
 ## Example: Estimate costs
 

articles/search/cognitive-search-attach-cognitive-services.md

@@ -43,7 +43,7 @@ The following diagram shows the progression of AI enrichment:
 
 + Enrichment starts when the indexer ["cracks documents"](search-indexer-overview.md#document-cracking) and extracts images and text. The kind of processing that occurs next depends on your data and which skills you've added to a skillset. If you have images, they can be forwarded to skills that perform image processing. Text content is queued for text and natural language processing. Internally, skills create an ["enriched document"](cognitive-search-working-with-skillsets.md#enrichment-tree) that collects the transformations as they occur.
 
-+ Enriched content is generated during skillset execution, and is temporary unless you save it. You can enable an [enrichment cache](cognitive-search-incremental-indexing-conceptual.md) to persist cracked documents and skill outputs for subsequent reuse during future skillset executions.
++ Enriched content is generated during skillset execution, and is temporary unless you save it. You can enable an [enrichment cache](enrichment-cache-how-to-configure.md) to persist cracked documents and skill outputs for subsequent reuse during future skillset executions.
 
 + To get content into a search index, the indexer must have mapping information for sending enriched content to target field. [Field mappings](search-indexer-field-mappings.md) (explicit or implicit) set the data path from source data to a search index. [Output field mappings](cognitive-search-output-field-mapping.md) set the data path from enriched documents to an index.
 
@@ -84,7 +84,7 @@ In Azure AI Search, an indexer saves the output it creates. A single indexer run
 |------------|----------|----------|-------------|
 | [**searchable index**](search-what-is-an-index.md) | Required | Search service | Used for full text search and other query forms. Specifying an index is an indexer requirement. Index content is populated from skill outputs, plus any source fields that are mapped directly to fields in the index. |
 | [**knowledge store**](knowledge-store-concept-intro.md) | Optional | Azure Storage | Used for downstream apps like knowledge mining or data science. A knowledge store is defined within a skillset. Its definition determines whether your enriched documents are projected as tables or objects (files or blobs) in Azure Storage. |
-| [**enrichment cache**](cognitive-search-incremental-indexing-conceptual.md) | Optional | Azure Storage | Used for caching enrichments for reuse in subsequent skillset executions. The cache stores imported, unprocessed content (cracked documents). It also stores the enriched documents created during skillset execution. Caching is helpful if you're using image analysis or OCR, and you want to avoid the time and expense of reprocessing image files. |
+| [**enrichment cache**](enrichment-cache-how-to-configure.md) | Optional | Azure Storage | Used for caching enrichments for reuse in subsequent skillset executions. The cache stores imported, unprocessed content (cracked documents). It also stores the enriched documents created during skillset execution. Caching is helpful if you're using image analysis or OCR, and you want to avoid the time and expense of reprocessing image files. |
 
 Indexes and knowledge stores are fully independent of each other. While you must attach an index to satisfy indexer requirements, if your sole objective is a knowledge store, you can ignore the index after it's populated.
 
@@ -126,7 +126,7 @@ Start with a subset of data in a [supported data source](search-indexer-overview
 
    An indexer is also where you specify field mappings and output field mappings that set up the data path to a search index.
 
-   Optionally, [enable enrichment caching](cognitive-search-incremental-indexing-conceptual.md) in the indexer configuration. This step allows you to reuse existing enrichments later on.
+   Optionally, [enable enrichment caching](enrichment-cache-how-to-configure.md) in the indexer configuration. This step allows you to reuse existing enrichments later on.
 
 1. [Run queries](search-query-create.md) to evaluate results or [start a debug session](cognitive-search-how-to-debug-skillset.md) to work through any skillset issues.
 

articles/search/cognitive-search-concept-intro.md

@@ -30,7 +30,7 @@ Rules for skillset definition include:
 Indexers drive skillset execution. You need an [indexer](search-howto-create-indexers.md), [data source](search-data-sources-gallery.md), and [index](search-what-is-an-index.md) before you can test your skillset.
 
 > [!TIP]
-> Enable [enrichment caching](cognitive-search-incremental-indexing-conceptual.md) to reuse the content you've already processed and lower the cost of development.
+> Enable [enrichment caching](enrichment-cache-how-to-configure.md) to reuse the content you've already processed and lower the cost of development.
 
 ## Add a skillset definition