Merge pull request #6616 from MicrosoftDocs/main

Auto Publish – main to live - 2025-08-15 22:06 UTC

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

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

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 04/15/2025
+ms.date: 08/15/2025
 author: aahill
 ms.author: aahi
 ms.custom: azure-ai-agents
@@ -73,7 +73,7 @@ When you create or update a configuration, enter the following information:
     > * Domain and path (for example, `https://www.microsoft.com/surface`) 
     > * Webpage (for example, `https://www.microsoft.com/en-us/p/surface-earbuds/8r9cpq146064`) 
 
-    1. Allowed domains to search against. For allowed domains, if you want to include subpages, please make sure the domains have at most 2 levels of subpages. 
+    1. Allowed domains to search against. For allowed domains, if you want to include subpages, make sure the domains have at most two levels of subpages. 
 
     1. Blocked domains to exclude from the search space. 
 
@@ -112,9 +112,9 @@ When you add the Grounding with Bing Custom Search tool to your agent, you can p
 
 |Name|Value|Type|Required |
 |-|-|-|- |
-|`count`|The number of search results to return in the response. The default is 5 and the maximum value is 50. The actual number delivered may be less than requested. It's possible for multiple pages to include some overlap in results. This parameter affects only web page results. It's possible that AI model might not use all search results returned by Bing.|`UnsignedShort`|No |
+|`count`|The number of search results to return in the response. The default is 5 and the maximum value is 50. The actual number delivered might be less than requested. It's possible for multiple pages to include some overlap in results. This parameter affects only web page results. It's possible that AI model might not use all search results returned by Bing.|`UnsignedShort`|No |
 |`freshness`|Filter search results by the following case-insensitive age values: <br/> **Day**: Return webpages that Bing discovered within the last 24 hours.<br/> **Week**: Return webpages that Bing discovered within the last 7 days.<br/> **Month**: Return webpages that Bing discovered within the last 30 days. To get articles discovered by Bing during a specific timeframe, specify a date range in the form: `YYYY-MM-DD..YYYY-MM-DD`. For example, `freshness=2019-02-01..2019-05-30`. To limit the results to a single date, set this parameter to a specific date. For example, `freshness=2019-02-04`.|String|No |
-|`market`|The market where the results come from. Typically, `mkt` is the country where the user is making the request from. However, it could be a different country if the user isn't located in a country where Bing delivers results. The market must be in the form: `<language>-<country/region>`. For example, `en-US`. The string is case insensitive. For a list of possible market values, see [Market codes](/bing/search-apis/bing-web-search/reference/market-codes). If known, you're encouraged to always specify the market. Specifying the market helps Bing route the request and return an appropriate and optimal response. If you specify a market that is not listed in Market codes, Bing uses a best fit market code based on an internal mapping that is subject to change. |String|No |
+|`market`|The market where the results come from. Typically, `mkt` is the country/region where the user is making the request from. However, it could be a different country/region if the user isn't located in a country/region where Bing delivers results. The market must be in the form: `<language>-<country/region>`. For example, `en-US`. The string is case insensitive. For a list of possible market values, see [Market codes](/bing/search-apis/bing-web-search/reference/market-codes). If known, you're encouraged to always specify the market. Specifying the market helps Bing route the request and return an appropriate and optimal response. If you specify a market that is not listed in Market codes, Bing uses a best fit market code based on an internal mapping that is subject to change. |String|No |
 |`set_lang`|The language to use for user interface strings. You may specify the language using either a 2-letter or 4-letter code. Using 4-letter codes is preferred.<br/> For a list of supported language codes, see [Bing supported languages](/bing/search-apis/bing-web-search/reference/market-codes#bing-supported-language-codes).<br/> Bing loads the localized strings if `setlang` contains a valid 2-letter neutral culture code (`fr`) or a valid 4-letter specific culture code (`fr-ca`). For example, for `fr-ca`, Bing loads the `fr` neutral culture code strings.<br/> If `setlang` isn't valid (for example, `zh`) or Bing doesn’t support the language (for example, `af`, `af-na`), Bing defaults to `en` (English).<br/> To specify the 2-letter code, set this parameter to an ISO 639-1 language code.<br/> To specify the 4-letter code, use the form `<language>-<country/region>` where `<language>` is an ISO 639-1 language code (neutral culture) and `<country/region>` is an ISO 3166 country/region (specific culture) code. For example, use `en-US` for United States English.<br/> Although optional, you should always specify the language. Typically, you set `setLang` to the same language specified by `mkt` unless the user wants the user interface strings displayed in a different language. |String|No |
 
 

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

@@ -3,6 +3,7 @@ title: Prompt flow in Azure AI Foundry portal
 titleSuffix: Azure AI Foundry
 description: This article introduces prompt flow in Azure AI Foundry portal.
 ms.service: azure-ai-foundry
+ms.subservice: azure-ai-prompt-flow
 ms.custom:
   - ignite-2023
   - build-2024

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

@@ -112,7 +112,7 @@ See [the Microsoft model collection in Azure AI Foundry portal](https://ai.azure
 
 | Model | Type | Capabilities | Project type 
 | ------ | ---- | ------------ | ------------ |
-| [mistral-document-ai-2505]() | Image-to-Text | - **Input:** image or PDF pages ( 30 pages, max 30MB PDF file) <br /> - **Output:** text  <br /> - **Languages:** en <br />  - **Tool calling:** no  <br /> - **Response formats:** Text, JSON, Markdown  | Foundry |
+| [mistral-document-ai-2505](https://ai.azure.com/explore/models/mistral-document-ai-2505/version/1/registry/azureml-mistral) | Image-to-Text | - **Input:** image or PDF pages ( 30 pages, max 30MB PDF file) <br /> - **Output:** text  <br /> - **Languages:** en <br />  - **Tool calling:** no  <br /> - **Response formats:** Text, JSON, Markdown  | Foundry |
 
 See [the Mistral model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=mistral).  There are also several Mistral models available [from partners and community](#mistral-ai).
 

articles/ai-foundry/how-to/develop/sdk-overview.md

@@ -6,8 +6,9 @@ ms.service: azure-ai-foundry
 ms.custom:
   - build-2024
   - ignite-2024
+ai-usage: ai-assisted
 ms.topic: how-to
-ms.date: 07/01/2025
+ms.date: 08/15/2025
 ms.reviewer: dantaylo
 ms.author: sgilley
 author: sdgilley
@@ -41,6 +42,10 @@ The Azure AI Foundry SDK is a set of client libraries and services designed to w
 
 ## Unified Projects client library
 
+The following examples show how to connect to your Azure AI Foundry project using different programming languages. This connection is the first step to accessing models, data, and AI services through the SDK. Each code block demonstrates how to authenticate and create a client for your project endpoint.
+
+> [!TIP]
+> The code samples below are starting points. You’ll use these clients to interact with models, run evaluations, and more, as described in the client libraries section below.
 
 
 ::: zone pivot="programming-language-python"
@@ -62,6 +67,7 @@ The [Azure AI Foundry Projects client library for Python](/python/api/overview/a
     project = AIProjectClient(
       endpoint="your_project_endpoint",  # Replace with your endpoint
       credential=DefaultAzureCredential())
+    # The AIProjectClient lets you access models, data, and services in your project.
     ```
 ::: zone-end
 
@@ -88,6 +94,7 @@ The [Azure AI Foundry Projects client library for Java (preview)](/java/api/over
         .credential(new DefaultAzureCredential())
         .endpoint(endpoint)
         .buildClient();
+    // The ProjectsClient enables unified access to your project's resources.
     ```
 
 
@@ -113,6 +120,7 @@ The [Azure AI Foundry Projects client library for JavaScript](/javascript/api/ov
     
     const endpoint = "your_project_endpoint"; // Replace with your actual endpoint
     const project = new AIProjectClient(endpoint, new DefaultAzureCredential());
+    // The AIProjectClient lets you access models, data, and services in your project.
     ```
 
 
@@ -147,16 +155,20 @@ The [Azure AI Foundry Projects client library for .NET](/dotnet/api/overview/azu
         credential, 
         new string[] { "https://cognitiveservices.azure.com/.default" }
     );
+    // The PerRetry position ensures the authentication policy is applied to every retry attempt.
+    // This is important for robust authentication in distributed/cloud environments.
     clientOptions.AddPolicy(tokenPolicy, HttpPipelinePosition.PerRetry);
     
     var projectClient = new ChatCompletionsClient(
         endpointUrl, 
         credential,
         clientOptions
     );
+    // The ChatCompletionsClient lets you interact with models and services in your project.
     ```
 
 ::: zone-end
+After you create a client, you can use it to access models, run evaluations, and connect to other AI services. The next section lists the available client libraries and shows how to use them for specific Azure AI services.
 
 <a name="azure-ai-foundry-agent-service"></a>
 * Using the project endpoint, you can:

articles/ai-foundry/how-to/flow-bulk-test-evaluation.md

@@ -3,6 +3,7 @@ title: Submit batch run and evaluate a flow
 titleSuffix: Azure AI Foundry
 description: Learn how to submit batch run and use built-in evaluation methods in prompt flow to evaluate how well your flow performs with a large dataset with Azure AI Foundry.
 ms.service: azure-ai-foundry
+ms.subservice: azure-ai-prompt-flow
 ms.custom:
   - ignite-2023
   - build-2024

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

@@ -3,6 +3,7 @@ title: Deploy a Flow as a Managed Online Endpoint for Real-Time Inference
 titleSuffix: Azure AI Foundry
 description: Learn how to deploy a flow as a managed online endpoint for real-time inference with Azure AI Foundry.
 ms.service: azure-ai-foundry
+ms.subservice: azure-ai-prompt-flow
 ms.custom:
   - ignite-2023
   - build-2024

articles/ai-foundry/how-to/flow-develop-evaluation.md

@@ -3,6 +3,7 @@ title: Develop an evaluation flow
 titleSuffix: Azure AI Foundry
 description: Learn how to customize or create your own evaluation flow tailored to your tasks and objectives, and then use in a batch run as an evaluation method in prompt flow with Azure AI Foundry.
 ms.service: azure-ai-foundry
+ms.subservice: azure-ai-prompt-flow
 ms.custom:
   - ignite-2023
   - build-2024

articles/ai-foundry/how-to/flow-develop.md

@@ -3,6 +3,7 @@ title: How to build with prompt flow
 titleSuffix: Azure AI Foundry
 description: This article provides instructions on how to build with prompt flow.
 ms.service: azure-ai-foundry
+ms.subservice: azure-ai-prompt-flow
 ms.custom:
   - ignite-2023
   - build-2024

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

@@ -3,6 +3,7 @@ title: Process images in prompt flow
 titleSuffix: Azure AI Foundry
 description: Learn how to use images in prompt flow.
 ms.service: azure-ai-foundry
+ms.subservice: azure-ai-prompt-flow
 ms.custom:
   - build-2024
   - hub-only

articles/ai-foundry/how-to/flow-tune-prompts-using-variants.md

@@ -3,6 +3,7 @@ title: Tune prompts using variants
 titleSuffix: Azure AI Foundry
 description: Learn how to tune prompts using variants in Prompt flow with Azure AI Foundry.
 ms.service: azure-ai-foundry
+ms.subservice: azure-ai-prompt-flow
 ms.custom:
   - ignite-2023
   - build-2024