Merge branch 'main' into release-aug-2025-search

Author: v-alje

.github/policies/disallow-edits.yml

@@ -62,15 +62,15 @@ configuration:
                 - isActivitySender:
                     user: laujan
                 - isActivitySender:
-                    user: patrickfarley
+                    user: PatrickFarley
                 - isActivitySender:
-                    user: heidisteen
+                    user: HeidiSteen
                 - isActivitySender:
                     user: haileytap
         then:
           - addReply:
               reply: >-
-                @${issueAuthor} - Please don't sign off on this PR. The area owners will sign off once they've reviewed your contribution.
+                ${issueAuthor} - Please don't sign off on this PR. The area owners will sign off once they've reviewed your contribution.
           - mentionUsers:
               mentionees:
                 - eric-urban

articles/ai-foundry/agents/how-to/tools/function-calling.md

@@ -23,7 +23,7 @@ Azure AI Agents supports function calling, which allows you to describe the stru
 
 ### Usage support
 
-|Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK | REST API | Basic agent setup | Standard agent setup |
+|Azure AI foundry support  | Python SDK |    C# SDK | JavaScript SDK | REST API | Basic agent setup | Standard agent setup |
 |---------|---------|---------|---------|---------|---------|---------|
 |      | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
 
@@ -381,6 +381,7 @@ Finally, clean up the created resources by deleting the thread and the agent.
 client.Threads.DeleteThread(threadId: thread.Id);
 // Delete the agent definition
 client.Administration.DeleteAgent(agentId: agent.Id);
+```
 
 ::: zone-end
 

articles/ai-foundry/concepts/architecture.md

@@ -7,7 +7,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: concept-article
-ms.date: 07/22/2025
+ms.date: 09/03/2025
 ms.reviewer: deeikele
 ms.author: sgilley
 author: sdgilley
@@ -79,12 +79,16 @@ Users can optionally connect their own Azure Storage accounts. Foundry tools can
 * **Customer-Managed Key Encryption**:
   By default, Azure services use Microsoft-managed encryption keys to encrypt data in transit and at rest. Data is encrypted and decrypted using FIPS 140-2 compliant 256-bit AES encryption. Encryption and decryption are transparent, meaning encryption and access are managed for you. Your data is secure by default and you don't need to modify your code or applications to take advantage of encryption.
 
-  When using customer-managed keys, your data on Microsoft-managed infrastructure is encrypted using your keys.  
+* **Bring your own Key Vault**:
+  By default, AI Foundry stores all API key-based connection secrets in a managed Azure Key Vault. For users that prefer to manage this themselves, they can connect to their key vault to the Foundry resource. One Azure Key Vault connection will manage all project and resource level connection secrets. Go to learn [how to set up an Azure Key Vault connection to AI Foundry](../how-to/set-up-key-vault-connection.md).
+
+  When using customer-managed keys, your data on Microsoft-managed infrastructure is encrypted using your keys.
+  
   To learn more about data encryption, see [customer-managed keys for encryption with Azure AI Foundry](encryption-keys-portal.md).
 
 ## Next steps
 
 * [Azure AI Foundry rollout across my organization](planning.md)
 * [Customer-managed keys for encryption with Azure AI Foundry](encryption-keys-portal.md)
 * [How to configure a private link for Azure AI Foundry](../how-to/configure-private-link.md)
-* [Bring-your-own resources with the Agent service](../agents/how-to/use-your-own-resources.md)
+* [Bring-your-own resources with the Agent service](../agents/how-to/use-your-own-resources.md)

articles/ai-foundry/how-to/connections-add.md

@@ -59,6 +59,7 @@ Here's a table of some of the available connection types in Azure AI Foundry por
 | Custom                        |         |                                        | Custom connections allow you to securely store and access keys while storing related properties, such as targets and versions. Custom connections are useful when you have many targets or cases where you wouldn't need a credential to access. LangChain scenarios are a good example where you would use custom service connections. Custom connections don't manage authentication, so you have to manage authentication on your own. |
 | Serverless Model              |    ✅    |                                        | Serverless Model connections allow you to serverless API deployment.                                                                                                                     |
 | Azure Databricks              |    ✅    |                                        | Azure Databricks connector allows you to connect your Azure AI Foundry Agents to Azure Databricks to access workflows and Genie Spaces during runtime. It supports three connection types - __Jobs__, __Genie__, and __Other__. You can pick the Job or Genie space you want associated with this connection while setting up the connection in the Foundry UI. You can also use the Other connection type and allow your agent to access workspace operations in Azure Databricks. Authentication is handled through Microsoft Entra ID for users or service principals. For examples of using this connector, see [Jobs](https://github.com/Azure-Samples/AI-Foundry-Connections/blob/main/src/samples/python/sample_agent_adb_job.py) and [Genie](https://github.com/Azure-Samples/AI-Foundry-Connections/blob/main/src/samples/python/sample_agent_adb_genie.py). Note: Usage of this connection is available only via the Foundry SDK in code and is integrated into agents as a FunctionTool (please see the samples above for details). Usage of this connection in AI Foundry Playground is currently not supported.|
+| Azure Key Vault| ✅ | | Azure service for securely storing and accessing secrets. AI Foundry stores connections details in a managed Azure Key Vault if no Key Vault connection is created. Users that prefer to manage their secrets themselves can bring their own Azure Key Vault via a connection. (See [limitations](#limits)) |
 
 ## Agent knowledge tool connections
 
@@ -167,4 +168,4 @@ For more on how to set private endpoints to your connected resources, see the fo
 ## Related content
 
 - [How to create vector indexes](../how-to/index-add.md)
-- [How to configure a managed network](configure-managed-network.md)
+- [How to configure a managed network](configure-managed-network.md)

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

@@ -321,7 +321,7 @@ Details about maximum request tokens and training data are available in the foll
 |`gpt-4o-realtime-preview` (2025-06-03) <br> GPT-4o audio | Audio model for real-time audio processing. |Input: 128,000  <br> Output: 4,096 | October 2023 |
 |`gpt-4o-realtime-preview` (2024-12-17) <br> GPT-4o audio | Audio model for real-time audio processing. |Input: 128,000  <br> Output: 4,096 | October 2023 |
 |`gpt-4o-mini-realtime-preview` (2024-12-17) <br> GPT-4o audio | Audio model for real-time audio processing. |Input: 128,000  <br> Output: 4,096 | October 2023 |
-|`gpt-4o-realtime` (2025-08-28) <br> GPT-4o audio | Audio model for real-time audio processing. |Input: 28,672  <br> Output: 4,096 | October 2023 |
+|`gpt-realtime` (2025-08-28) <br> GPT-4o audio | Audio model for real-time audio processing. |Input: 28,672  <br> Output: 4,096 | October 2023 |
 
 To compare the availability of GPT-4o audio models across all regions, refer to the [models table](#global-standard-model-availability).
 

articles/ai-foundry/openai/how-to/dall-e.md

@@ -1,11 +1,11 @@
 ---
-title: How to use image generation models
+title: How to Use Image Generation Models from OpenAI
 titleSuffix: Azure OpenAI in Azure AI Foundry Models
-description: Learn how to generate and edit images with image models, and learn about the configuration options that are available.
+description: Learn how to generate and edit images using Azure OpenAI image generation models. Discover configuration options and start creating images today.
 author: PatrickFarley
 ms.author: pafarley
 manager: nitinme
-ms.date: 04/23/2025
+ms.date: 09/02/2025
 ms.service: azure-ai-openai
 ms.topic: how-to
 ms.custom:
@@ -15,22 +15,26 @@ ms.custom:
 
 # How to use Azure OpenAI image generation models
 
-OpenAI's image generation models render images based on user-provided text prompts and optionally provided images. This guide demonstrates how to use the image generation models and configure their options through REST API calls.
+OpenAI's image generation models create images from user-provided text prompts and optional images. This article explains how to use these models, configure options, and benefit from advanced image generation capabilities in Azure.
 
 
 ## Prerequisites
 
+
 - An Azure subscription. You can [create one for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?icid=ai-services).
 - An Azure OpenAI resource created in a supported region. See [Region availability](/azure/ai-foundry/openai/concepts/models#model-summary-table-and-region-availability).
 - Deploy a `dall-e-3` or `gpt-image-1` model with your Azure OpenAI resource. For more information on deployments, see [Create a resource and deploy a model with Azure OpenAI](/azure/ai-foundry/openai/how-to/create-resource).
     - GPT-image-1 is the newer model and features a number of improvements over DALL-E 3. It's available in limited access: apply for access with [this form](https://aka.ms/oai/gptimage1access).
 
-## Call the Image Generation API
 
-The following command shows the most basic way to use an image model with code. If this is your first time using these models programmatically, we recommend starting with the [quickstart](/azure/ai-foundry/openai/dall-e-quickstart).
+## Call the image generation API
+
+
+The following command shows the most basic way to use an image model with code. If this is your first time using these models programmatically, start with the [quickstart](/azure/ai-foundry/openai/dall-e-quickstart).
 
 
 #### [GPT-image-1](#tab/gpt-image-1)
+
 Send a POST request to:
 
 ```
@@ -41,14 +45,18 @@ https://<your_resource_name>.openai.azure.com/openai/deployments/<your_deploymen
 **URL**:
 
 Replace the following values:
+
 - `<your_resource_name>` is the name of your Azure OpenAI resource.
 - `<your_deployment_name>` is the name of your DALL-E 3 or GPT-image-1 model deployment.
 - `<api_version>` is the version of the API you want to use. For example, `2025-04-01-preview`.
 
+
 **Required headers**:
+
 - `Content-Type`: `application/json`
 - `api-key`: `<your_API_key>`
 
+
 **Body**:
 
 The following is a sample request body. You specify a number of options, defined in later sections.
@@ -122,7 +130,7 @@ The response from a successful image generation API call looks like the followin
 } 
 ```
 > [!NOTE]
-> `response_format` parameter is not supported for GPT-image-1 which always returns base64-encoded images.
+> The `response_format` parameter isn't supported for GPT-image-1, which always returns base64-encoded images.
 
 #### [DALL-E 3](#tab/dalle-3)
 
@@ -144,7 +152,7 @@ The response from a successful image generation API call looks like the followin
 
 ### API call rejection
 
-Prompts and images are filtered based on our content policy, returning an error when a prompt or image is flagged.
+Prompts and images are filtered based on our content policy. The API returns an error when a prompt or image is flagged.
 
 If your prompt is flagged, the `error.code` value in the message is set to `contentFilter`. Here's an example:
 
@@ -172,9 +180,9 @@ It's also possible that the generated image itself is filtered. In this case, th
 }
 ```
 
-### Write text-to-image prompts
+### Write effective text-to-image prompts
 
-Your prompts should describe the content you want to see in the image, and the visual style of image.
+Your prompts should describe the content you want to see in the image and the visual style of the image.
 
 When you write prompts, consider that the Image APIs come with a content moderation filter. If the service recognizes your prompt as harmful content, it doesn't generate an image. For more information, see [Content filtering](../concepts/content-filter.md).
 
@@ -197,7 +205,7 @@ Specify the size of the generated images. Must be one of `1024x1024`, `1024x1536
 
 #### Quality
 
-There are three options for image quality: `low`, `medium`, and `high`.Lower quality images can be generated faster.
+There are three options for image quality: `low`, `medium`, and `high`. Lower quality images can be generated faster.
 
 The default value is `high`.
 
@@ -207,22 +215,22 @@ You can generate between one and 10 images in a single API call. The default val
 
 #### User ID
 
-Use the *user* parameter to specify a unique identifier for the user making the request. This is useful for tracking and monitoring usage patterns. The value can be any string, such as a user ID or email address.
+Use the *user* parameter to specify a unique identifier for the user making the request. This identifier is useful for tracking and monitoring usage patterns. The value can be any string, such as a user ID or email address.
 
 #### Output format
 
 Use the *output_format* parameter to specify the format of the generated image. Supported formats are `PNG` and `JPEG`. The default is `PNG`.
 
 > [!NOTE]
-> WEBP images are not supported in the Azure OpenAI in Azure AI Foundry Models.
+> WEBP images aren't supported in the Azure OpenAI in Azure AI Foundry Models.
 
 #### Compression
 
 Use the *output_compression* parameter to specify the compression level for the generated image. Input an integer between `0` and `100`, where `0` is no compression and `100` is maximum compression. The default is `100`.
 
 #### Streaming 
 
-Use the *stream* parameter to enable streaming responses. When set to `true`, the API returns partial images as they are generated. This provides faster visual feedback for users and improves perceived latency. Set the *partial_images* parameter to control how many partial images are generated (1-3).
+Use the *stream* parameter to enable streaming responses. When set to `true`, the API returns partial images as they're generated. This feature provides faster visual feedback for users and improves perceived latency. Set the *partial_images* parameter to control how many partial images are generated (1-3).
 
 
 #### [DALL-E 3](#tab/dalle-3)
@@ -251,23 +259,23 @@ The default value is `vivid`.
 
 #### Quality
 
-There are two options for image quality: `hd` and `standard`. The hd option creates images with finer details and greater consistency across the image. Standard images can be generated faster.
+There are two options for image quality: `hd` and `standard`. The hd option creates images with finer details and greater consistency across the image. Standard images are faster to generate.
 
 The default value is `standard`.
 
 #### Number
 
-With DALL-E 3, you can't generate more than one image in a single API call: the `n` parameter must be set to *1*. If you need to generate multiple images at once, make parallel requests.
+With DALL-E 3, you can't generate more than one image in a single API call: the `n` parameter must be set to *1*. To generate multiple images at once, make parallel requests.
 
 #### Response format
 
-The format in which DALL-E 3 generated images are returned. Must be one of `url` or `b64_json`. This parameter isn't supported for GPT-image-1 which always returns base64-encoded images.
+The format in which DALL-E 3 returns generated images. Must be one of `url` or `b64_json`. This parameter isn't supported for GPT-image-1, which always returns base64-encoded images.
 
 ---
 
-## Call the Image Edit API
+## Call the image edit API
 
-The Image Edit API allows you to modify existing images based on text prompts you provide. The API call is similar to the image generation API call, but you also need to provide an input image.
+The Image Edit API enables you to modify existing images based on text prompts you provide. The API call is similar to the image generation API call, but you also need to provide an input image.
 
 
 #### [GPT-image-1](#tab/gpt-image-1)
@@ -308,8 +316,7 @@ The following is a sample request body. You specify a number of options, defined
 -F "n=1" \
 -F "quality=high"
 ```
-
-### Output
+### API response output
 
 The response from a successful image editing API call looks like the following example. The `b64_json` field contains the output image data.
 
@@ -324,28 +331,28 @@ The response from a successful image editing API call looks like the following e
 } 
 ```
 
-### Specify API options
+### Specify image edit API options
 
 The following API body parameters are available for image editing models, in addition to the ones available for image generation models.
 
-### Image
+#### Image
 
 The *image* value indicates the image file you want to edit.
 
 #### Input fidelity 
 
-The *input_fidelity* parameter controls how much effort the model will exert to match the style and features, especially facial features, of input images 
+The *input_fidelity* parameter controls how much effort the model puts into matching the style and features, especially facial features, of input images. 
 
-This allows you to make subtle edits to an image without altering unrelated areas. When you use high input fidelity, faces are preserved more accurately than in standard mode. 
+This parameter lets you make subtle edits to an image without changing unrelated areas. When you use high input fidelity, faces are preserved more accurately than in standard mode. 
 
 
 #### Mask
 
-The *mask* parameter is the same type as the main *image* input parameter. It defines the area of the image that you want the model to edit, using fully transparent pixels (alpha of zero) in those areas. The mask must be a PNG file and have the same dimensions as the input image.
+The *mask* parameter uses the same type as the main *image* input parameter. It defines the area of the image that you want the model to edit, using fully transparent pixels (alpha of zero) in those areas. The mask must be a PNG file and have the same dimensions as the input image.
 
 #### Streaming 
 
-Use the *stream* parameter to enable streaming responses. When set to `true`, the API returns partial images as they are generated. This provides faster visual feedback for users and improves perceived latency. Set the *partial_images* parameter to control how many partial images are generated (1-3).
+Use the *stream* parameter to enable streaming responses. When set to `true`, the API returns partial images as they're generated. This feature provides faster visual feedback for users and improves perceived latency. Set the *partial_images* parameter to control how many partial images are generated (1-3).
 
 #### [DALL-E 3](#tab/dalle-3)