Merge pull request #6334 from MicrosoftDocs/main

Auto Publish – main to live - 2025-07-31 22:13 UTC

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

articles/ai-foundry/.openpublishing.redirection.ai-studio.json

@@ -467,7 +467,7 @@
           },
           {
             "source_path_from_root": "/articles/ai-foundry/foundry-models/supported-languages-openai.md",
-            "redirect_url": "/azure/ai-services/openai/supported-languages",
+            "redirect_url": "/azure/ai-foundry/openai/supported-languages",
             "redirect_document_id": false
           },
           {
@@ -945,8 +945,8 @@
         },
         {
             "source_path_from_root": "/articles/ai-studio/quickstarts/assistants.md",
-            "redirect_url": "/azure/ai-services/openai/assistants-quickstart",
-            "redirect_document_id": true
+            "redirect_url": "/azure/ai-foundry/openai/how-to/assistant",
+            "redirect_document_id": false
         },
         {
             "source_path_from_root": "/articles/ai-studio/how-to/prompt-flow-tools/vector-db-lookup-tool.md",
@@ -1110,7 +1110,7 @@
           },
           {
             "source_path_from_root": "/articles/ai-studio/quickstarts/multimodal-vision.md",
-            "redirect_url": "/azure/ai-services/openai/gpt-v-quickstart",
+            "redirect_url": "/azure/ai-foundry/openai/gpt-v-quickstart",
             "redirect_document_id": false
           },
           {

articles/ai-foundry/agents/how-to/tools/bing-grounding.md

@@ -21,7 +21,7 @@ You can ask questions such as "*what is the top news today*" or "*what is the re
 Developers and end users don't have access to raw content returned from Grounding with Bing Search. The model response, however, includes citations with links to the websites used to generate the response, and a link to the Bing query used for the search. You can retrieve the **model response** by accessing the data in the thread that was created. These two *references* must be retained and displayed in the exact form provided by Microsoft, as per Grounding with Bing Search's [Use and Display Requirements](https://www.microsoft.com/en-us/bing/apis/grounding-legal#use-and-display-requirements). See the [how to display Grounding with Bing Search results](#how-to-display-grounding-with-bing-search-results) section for details.
 
 >[!IMPORTANT]
-> 1. Your usage of Grounding with Bing Search can incur costs. See the [pricing page](https://www.microsoft.com/bing/apis/grounding-pricing) for details.
+> 1. Your usage of Grounding with Bing Search can incur costs. See the [pricing page](https://www.microsoft.com/en-us/bing/apis/grounding-pricing) for details.
 > 1. By creating and using a Grounding with Bing Search resource through code-first experience, such as Azure CLI, or deploying through deployment template, you agree to be bound by and comply with the terms available at https://www.microsoft.com/en-us/bing/apis/grounding-legal, which may be updated from time to time.
 > 1. When you use Grounding with Bing Search, your customer data is transferred outside of the Azure compliance boundary to the Grounding with Bing Search service. Grounding with Bing Search is not subject to the same data processing terms (including location of processing) and does not have the same compliance standards and certifications as the Azure AI Foundry Agent Service, as described in the [Grounding with Bing Search Terms of Use](https://www.microsoft.com/en-us/bing/apis/grounding-legal). It is your responsibility to assess whether use of Grounding with Bing Search in your agent meets your needs and requirements.
 

articles/ai-foundry/concepts/ai-resources.md

@@ -90,6 +90,6 @@ If not provided by you, the following dependent resources are automatically crea
 ## Next steps
 
 - [Create a [!INCLUDE [hub-project-name](../includes/hub-project-name.md)]](../how-to/create-projects.md?pivots=hub-project)
-- [Quickstart: Analyze images and video in the chat playground](/azure/ai-services/openai/gpt-v-quickstart)
+- [Quickstart: Analyze images and video in the chat playground](/azure/ai-foundry/openai/gpt-v-quickstart)
 - [Learn more about Azure AI Foundry](../what-is-azure-ai-foundry.md)
 - [Learn more about projects](../how-to/create-projects.md?pivots=hub-project)

articles/ai-foundry/concepts/foundry-models-overview.md

@@ -236,7 +236,7 @@ To set the public network access flag for the Azure AI Foundry hub:
 
 * If you have an Azure AI Foundry hub with MaaS deployments created before July 11, 2024, and you enable a private endpoint on this hub, the existing serverless API deployments won't follow the hub's networking configuration. For serverless API deployments in the hub to follow the hub's networking configuration, you need to create the deployments again.
 
-* Currently, [Azure OpenAI On Your Data](/azure/ai-services/openai/concepts/use-your-data) support isn't available for serverless API deployments in private hubs, because private hubs have the public network access flag disabled.
+* Currently, [Azure OpenAI On Your Data](/azure/ai-foundry/openai/concepts/use-your-data) support isn't available for serverless API deployments in private hubs, because private hubs have the public network access flag disabled.
 
 * Any network configuration change (for example, enabling or disabling the public network access flag) might take up to five minutes to propagate.
 

articles/ai-foundry/concepts/model-benchmarks.md

@@ -107,7 +107,7 @@ Performance metrics are calculated as an aggregate over 14 days, based on 24 tra
 
 | Parameter                             | Value                                                                                              | Applicable For                                                                                                                                                                                                                              |
 |---------------------------------------|----------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| Region                                | East US/East US2                                                                                   | [serverless API deployments](../how-to/model-catalog-overview.md#serverless-api-deployment-pay-per-token-offer-billing) and [Azure OpenAI](/azure/ai-services/openai/overview)                                                                                          |
+| Region                                | East US/East US2                                                                                   | [serverless API deployments](../how-to/model-catalog-overview.md#serverless-api-deployment-pay-per-token-offer-billing) and [Azure OpenAI](/azure/ai-foundry/openai/overview)                                                                                          |
 | Tokens per minute (TPM) rate limit    | 30k (180 RPM based on Azure OpenAI) for non-reasoning and 100k for reasoning models <br> N/A (serverless API deployments) | For Azure OpenAI models, selection is available for users with rate limit ranges based on deployment type (serverless API, global, global standard, and so on.) <br> For serverless API deployments, this setting is abstracted.                             |
 | Number of requests                    | Two requests in a trail for every hour (24 trails per day)                                         | serverless API deployments, Azure OpenAI                                                                                                                                                                                                               |
 | Number of trails/runs                 | 14 days with 24 trails per day for 336 runs                                                        | serverless API deployments, Azure OpenAI                                                                                                                                                                                                               |

articles/ai-foundry/concepts/model-catalog-content-safety.md

@@ -2,10 +2,10 @@
 title: Guardrails & controls for Models Sold Directly by Azure 
 titleSuffix: Azure AI Foundry
 description: Learn about content safety for models deployed using serverless API deployments, using Azure AI Foundry.
-manager: scottpolly
+manager: nitinme
 ms.service: azure-ai-foundry
 ms.topic: concept-article
-ms.date: 05/19/2025
+ms.date: 07/31/2025
 ms.author: mopeakande 
 author: msakande
 ms.reviewer: ositanachi
@@ -22,7 +22,7 @@ In this article, learn about content safety capabilities for models from the mod
 
 ## Content filter defaults
 
-Azure AI uses a default configuration of [Azure AI Content Safety](/azure/ai-services/content-safety/overview) content filters to detect harmful content across four categories including hate and fairness, self-harm, sexual, and violence for models deployed via serverless API deployments. To learn more about content filtering, see [Understand harm categories](#understand-harm-categories).
+Azure AI uses a default configuration of [Azure AI Content Safety](/azure/ai-services/content-safety/overview) content filters to detect harmful content across four categories including hate and fairness, self-harm, sexual, and violence for models deployed via [serverless API deployments](deployments-overview.md#serverless-api-endpoint). To learn more about content filtering, see [Understand harm categories](#understand-harm-categories).
 
 The default content filtering configuration for text models is set to filter at the medium severity threshold, filtering any detected content at this level or higher. For image models, the default content filtering configuration is set at the low configuration threshold, filtering at this level or higher. For models deployed using the [Azure AI Foundry Models](../../ai-foundry/model-inference/how-to/configure-content-filters.md), you can create configurable filters by selecting the **Content filters** tab within the **Guardrails & controls** page of the Azure AI Foundry portal.
 

articles/ai-foundry/concepts/rbac-azure-ai-foundry.md

@@ -590,7 +590,7 @@ When using Microsoft Entra ID authenticated connections in the chat playground,
 
 ## Scenario: Use an existing Azure OpenAI resource
 
-When you create a connection to an existing Azure OpenAI resource, you must also assign roles to your users so they can access the resource. You should assign either the **Cognitive Services OpenAI User** or **Cognitive Services OpenAI Contributor** role, depending on the tasks they need to perform. For information on these roles and the tasks they enable, see [Azure OpenAI roles](/azure/ai-services/openai/how-to/role-based-access-control#azure-openai-roles).
+When you create a connection to an existing Azure OpenAI resource, you must also assign roles to your users so they can access the resource. You should assign either the **Cognitive Services OpenAI User** or **Cognitive Services OpenAI Contributor** role, depending on the tasks they need to perform. For information on these roles and the tasks they enable, see [Azure OpenAI roles](/azure/ai-foundry/openai/how-to/role-based-access-control#azure-openai-roles).
 
 ## Scenario: Use Azure Container Registry
 
@@ -615,7 +615,7 @@ Azure Application Insights is an optional dependency for Azure AI Foundry hub. T
 
 ## Scenario: Provisioned throughput unit procurer
 
-The following example defines a custom role that can procure [provisioned throughput units (PTU)](/azure/ai-services/openai/concepts/provisioned-throughput).
+The following example defines a custom role that can procure [provisioned throughput units (PTU)](/azure/ai-foundry/openai/concepts/provisioned-throughput).
 
 ```json
 {
@@ -659,7 +659,7 @@ The following example defines a custom role that can procure [provisioned throug
 
 ## Scenario: Azure OpenAI Assistants API
 
-The following example defines a role for a developer using [Azure OpenAI Assistants](/azure/ai-services/openai/how-to/assistant).
+The following example defines a role for a developer using [Azure OpenAI Assistants](/azure/ai-foundry/openai/how-to/assistant).
 
 ```json
 {

articles/ai-foundry/concepts/vulnerability-management.md

@@ -6,6 +6,7 @@ manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - build-2024
+  - hub-only
 ms.topic: concept-article
 ms.date: 04/29/2025
 ms.reviewer: deeikele

articles/ai-foundry/faq.yml

@@ -14,7 +14,7 @@ metadata:
   author: sdgilley
 title: Azure AI Foundry frequently asked questions
 summary: |
-  FAQ for [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs). If you can't find answers to your questions in this document, and still need help check the [Azure AI services support options guide](../ai-services/cognitive-services-support-options.md?context=/azure/ai-services/openai/context/context). Azure OpenAI is part of Azure AI services.
+  FAQ for [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs). If you can't find answers to your questions in this document, and still need help check the [Azure AI services support options guide](../ai-services/cognitive-services-support-options.md?context=/azure/ai-foundry/openai/context/context). Azure OpenAI is part of Azure AI services.
 sections:
   - name: General questions
     questions:

articles/ai-foundry/foundry-models/concepts/deployment-types.md

@@ -78,7 +78,7 @@ Key use cases include:
 
 Data zone standard deployments are available in the same Azure AI Foundry resource as all other AI Foundry Models deployment types but allow you to leverage Azure global infrastructure to dynamically route traffic to the data center within the Microsoft defined data zone with the best availability for each request. Data zone standard provides higher default quotas than our Azure geography-based deployment types. 
 
-Customers with high consistent volume may experience greater latency variability. The threshold is set per model. See the [Quotas and limits](/azure/ai-services/openai/quotas-limits#usage-tiers) page to learn more. For workloads that require low latency variance at large volume, we recommend leveraging the provisioned deployment offerings. 
+Customers with high consistent volume may experience greater latency variability. The threshold is set per model. See the [Quotas and limits](/azure/ai-foundry/openai/quotas-limits#usage-tiers) page to learn more. For workloads that require low latency variance at large volume, we recommend leveraging the provisioned deployment offerings. 
 
 ## Data zone provisioned
 
@@ -110,7 +110,7 @@ Standard deployments are optimized for low to medium volume workloads with high
 
 **SKU name in code:** `ProvisionedManaged`
 
-Provisioned deployments allow you to specify the amount of throughput you require in a deployment. The service then allocates the necessary model processing capacity and ensures it's ready for you. Throughput is defined in terms of provisioned throughput units (PTU) which is a normalized way of representing the throughput for your deployment. Each model-version pair requires different amounts of PTU to deploy and provide different amounts of throughput per PTU. Learn more from our [Provisioned throughput concepts article](/azure/ai-services/openai/concepts/provisioned-throughput).
+Provisioned deployments allow you to specify the amount of throughput you require in a deployment. The service then allocates the necessary model processing capacity and ensures it's ready for you. Throughput is defined in terms of provisioned throughput units (PTU) which is a normalized way of representing the throughput for your deployment. Each model-version pair requires different amounts of PTU to deploy and provide different amounts of throughput per PTU. Learn more from our [Provisioned throughput concepts article](/azure/ai-foundry/openai/concepts/provisioned-throughput).
 
 
 ## Control deployment options