Merge pull request #6026 from MicrosoftDocs/main

Auto Publish – main to live - 2025-07-14 22:06 UTC

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

articles/ai-foundry/agents/concepts/model-region-support.md

@@ -7,7 +7,7 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: conceptual
-ms.date: 07/10/2025
+ms.date: 07/14/2025
 ms.custom: azure-ai-agents, references_regions
 ---
 
@@ -46,47 +46,6 @@ Azure AI Foundry Agent Service supports the following Azure OpenAI models in the
 | westus           | X                            | X                  | X                  | X                  | X                       |             | X                       |                 | X                  |                    |
 | westus3          |                              | X                  | X                  | X                  | X                       |             | X                       |                 |                    |                    |
 
-## Non-Microsoft models
-
-The Azure AI Foundry Agent Service also supports the following models from the Azure AI Foundry model catalog.
-
-* Meta-Llama-405B-Instruct
-
-To use these models, you can use [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) to make a deployment, and then reference the deployment name in your agent. For example:
-
-```python
-agent = project_client.agents.create_agent( model="llama-3", name="my-agent", instructions="You are a helpful agent" ) 
-```
-## Azure AI Foundry models
-
-### Models with tool-calling 
-
-To best support agentic scenarios, we recommend using models that support tool-calling. The Azure AI Foundry Agent Service currently supports all agent-compatible models from the Azure AI Foundry model catalog. 
-
-To use these models, use the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) to make a model deployment, then reference the deployment name in your agent. For example: 
-
-`agent = project_client.agents.create_agent( model="llama-3", name="my-agent", instructions="You are a helpful agent")`
-
-> [!NOTE]
-> This option should only be used for open-source models (for example, Cepstral, Mistral, Llama) and not for OpenAI models, which are natively supported in the service. This option should also only be used for models that support tool-calling. 
-
-### Models without tool-calling 
-
-Though tool-calling support is a core capability for agentic scenarios, we now provide the ability to use models that don’t support tool-calling in our API and SDK. This option can be helpful when you have specific use-cases that don’t require tool-calling. 
-
-The following steps will allow you to utilize any chat-completion model that is available through a [serverless API](/azure/ai-foundry/how-to/model-catalog-overview): 
-
- 
-
-1. Deploy your desired model through serverless API. Model will show up on your **Models + Endpoints** page. 
-
-1. Click on model name to see model details, where you'll find your model's target URI and key. 
-
-1. Create a new Serverless connection on **Connected Resources** page, using the target URI and key. 
-
-The model can now be referenced in your code (`Target URI` + `@` + `Model Name`), for example: 
-
-`Model=https://Phi-4-mejco.eastus.models.ai.azure.com/@Phi-4-mejco`
 
 ## Next steps
 

articles/ai-foundry/includes/get-started-fdp.md

@@ -10,7 +10,7 @@ ms.custom:
   - include file
   - build-aifnd
   - build-2025
-  - update-code-3
+  - update-code-4
 ---
 
 In this quickstart, you use [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs) to:

articles/ai-foundry/openai/how-to/evaluations.md

@@ -50,7 +50,7 @@ Azure OpenAI evaluation enables developers to create evaluation runs to test aga
 - West US 2
 - West US 3
 
-If your preferred region is missing, refer to [Azure OpenAI regions](https://learn.microsoft.com/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#global-standard-model-availability) and check if it is one of the Azure OpenAI regional availability zones.
+If your preferred region is missing, refer to [Azure OpenAI regions](/azure/ai-services/openai/concepts/models?tabs=global-standard%2Cstandard-chat-completions#global-standard-model-availability) and check if it is one of the Azure OpenAI regional availability zones.
 
 ### Supported deployment types
 
@@ -63,7 +63,7 @@ If your preferred region is missing, refer to [Azure OpenAI regions](https://lea
 
 ## Evaluation API (preview)
 
-Evaluation API lets you test model outputs directly through API calls, and programmatically assess model quality and performance. To use Evaluation API, check out the [REST API documentation](https://learn.microsoft.com/azure/ai-services/openai/authoring-reference-preview#evaluation---get-list). 
+Evaluation API lets you test model outputs directly through API calls, and programmatically assess model quality and performance. To use Evaluation API, check out the [REST API documentation](/azure/ai-services/openai/authoring-reference-preview#evaluation---get-list). 
 
 ## Evaluation pipeline
 
@@ -127,7 +127,7 @@ The deployments available in your list depend on those you created within your A
 
 Testing criteria is used to assess the effectiveness of each output generated by the target model. These tests compare the input data with the output data to ensure consistency. You have the flexibility to configure different criteria to test and measure the quality and relevance of the output at different levels.
 
-:::image type="content" source="../media/how-to/evaluations/eval-testing-criteria.png" alt-text="Screenshot that shows the evaluations testing criteria options." lightbox="../media/how-to/evaluations/eval-testing-criteria.png":::
+:::image type="content" source="../media/how-to/evaluations/eval-testing-criteria.png" alt-text="Screenshot that shows the different testing criteria selections." lightbox="../media/how-to/evaluations/eval-testing-criteria.png":::
 
 When you click into each testing criteria, you will see different types of graders as well as preset schemas that you can modify per your own evaluation dataset and criteria. 
 
@@ -146,11 +146,11 @@ When you click into each testing criteria, you will see different types of grade
 
 4. Select your evaluation data which will be in `.jsonl` format. If you already have an existing data, you can select one, or upload a new data.
 
-    :::image type="content" source="../media/how-to/evaluations/upload-data-1.png" alt-text="Screenshot of data upload." lightbox="../media/how-to/evaluations/upload-data-1.png":::
+    :::image type="content" source="../media/how-to/evaluations/upload-data-1.png" alt-text="Screenshot of data upload options." lightbox="../media/how-to/evaluations/upload-data-1.png":::
 
    When you upload new data, you'll see the first three lines of the file as a preview on the right side:
 
-    :::image type="content" source="../media/how-to/evaluations/upload-data-2.png" alt-text="Screenshot of data upload." lightbox="../media/how-to/evaluations/upload-data-2.png":::
+    :::image type="content" source="../media/how-to/evaluations/upload-data-2.png" alt-text="Screenshot of data upload with example selection." lightbox="../media/how-to/evaluations/upload-data-2.png":::
 
    If you need a sample test file, you can use this sample `.jsonl` text. This sample contains sentences of various technical content, and we are going to be assessing semantic similarity across these sentences.
 
@@ -169,19 +169,19 @@ When you click into each testing criteria, you will see different types of grade
 
 5. If you would like to create new responses using inputs from your test data, you can select 'Generate new responses'. This will inject the input fields from our evaluation file into individual prompts for a model of your choice to generate output.
 
-:::image type="content" source="../media/how-to/evaluations/eval-generate-1.png" alt-text="Screenshot of the UX for generating model responses." lightbox="../media/how-to/evaluations/eval-generate-1.png":::
+:::image type="content" source="../media/how-to/evaluations/eval-generate-1.png" alt-text="Screenshot of the UX showing selected import test data." lightbox="../media/how-to/evaluations/eval-generate-1.png":::
 
 You will select the model of your choice. If you do not have a model, you can create a new model deployment. The selected model will take the input data and generate its own unique outputs, which in this case will be stored in a variable called `{{sample.output_text}}`. We'll then use that output later as part of our testing criteria. Alternatively, you could provide your own custom system message and individual message examples manually.
 
 :::image type="content" source="../media/how-to/evaluations/eval-generate-2.png" alt-text="Screenshot of the UX for generating model responses." lightbox="../media/how-to/evaluations/eval-generate-2.png":::
 
 6. For creating a test criteria, select **Add**. For the example file we provided, we are going to be assessing semantic similarity. Select **Model Scorer**, which contains test criteria presets for Semantic Similarity.
 
-    :::image type="content" source="../media/how-to/evaluations/eval-semantic-similarity-1.png" alt-text="Screenshot of the semantic similarity UX config." lightbox="../media/how-to/evaluations/eval-semantic-similarity-1.png":::
+    :::image type="content" source="../media/how-to/evaluations/eval-semantic-similarity-1.png" alt-text="Screenshot of the semantic similarity UX config highlighting Model scorer." lightbox="../media/how-to/evaluations/eval-semantic-similarity-1.png":::
 
    Select **Semantic Similarity** at the top. Scroll to the bottom, and in `User` section, specify `{{item.output}}` as `Ground truth`, and specify `{{sample.output_text}}` as `Output`. This will take the original reference output from your evaluation `.jsonl` file (the sample file provided) and compare it against the output that is generated by the model you chose in the previous step.
 
-    :::image type="content" source="../media/how-to/evaluations/eval-semantic-similarity-2.png" alt-text="Screenshot of the semantic similarity UX config." lightbox="../media/how-to/evaluations/eval-semantic-similarity-2.png":::
+    :::image type="content" source="../media/how-to/evaluations/eval-semantic-similarity-2.png" alt-text="Screenshot of the semantic similarity UX config with generated output." lightbox="../media/how-to/evaluations/eval-semantic-similarity-2.png":::
 
 :::image type="content" source="../media/how-to/evaluations/eval-semantic-similarity-3.png" alt-text="Screenshot of the semantic similarity UX config." lightbox="../media/how-to/evaluations/eval-semantic-similarity-3.png":::
 
@@ -190,7 +190,7 @@ You will select the model of your choice. If you do not have a model, you can cr
 8. You are ready to create your Evaluation. Provide your Evaluation name, review everything looks correct, and **Submit** to create the Evaluation job. You'll be taken to a status page for your evaluation job, which will show the status as "Waiting".
 
 :::image type="content" source="../media/how-to/evaluations/eval-submit-job.png" alt-text="Screenshot of the evaluation job submit UX." lightbox="../media/how-to/evaluations/eval-submit-job.png":::
-:::image type="content" source="../media/how-to/evaluations/eval-submit-job-2.png" alt-text="Screenshot of the evaluation job submit UX." lightbox="../media/how-to/evaluations/eval-submit-job-2.png":::
+:::image type="content" source="../media/how-to/evaluations/eval-submit-job-2.png" alt-text="Screenshot of the evaluation job submit UX, with a status of waiting." lightbox="../media/how-to/evaluations/eval-submit-job-2.png":::
 
 9. Once your evaluation job has created, you can select the job to view the full details of the job:
 

articles/ai-foundry/openai/includes/gpt-v-javascript.md

@@ -70,6 +70,9 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 
 Select an image from the [azure-samples/cognitive-services-sample-data-files](https://github.com/Azure-Samples/cognitive-services-sample-data-files/tree/master/ComputerVision/Images). Use the image URL in the code below or set the `IMAGE_URL` environment variable to the image URL.
 
+> [!IMPORTANT]
+> If you use a SAS URL to an image stored in Azure blob storage, you need to enable Managed Identity and assign the **Storage Blob Reader** role to your Azure OpenAI resource (do this in the Azure portal). This allows the model to access the image in blob storage.
+
 > [!TIP]
 > You can also use a base 64 encoded image data instead of a URL. For more information, see the [GPT-4 Turbo with Vision how-to guide](../how-to/gpt-with-vision.md#use-a-local-image).
 

articles/ai-services/content-understanding/tutorial/build-person-directory.md

@@ -81,7 +81,7 @@ Content-Type: application/json
 {
   "tags": {
     "name": "Alice",
-    "age": "20"
+    "employeeId": "E12345"
   }
 }
 ```
@@ -98,7 +98,7 @@ The API returns a `personId` that uniquely identifies the created person.
   "personId": "4f66b612-e57d-4d17-9ef7-b951aea2cf0f",
   "tags": {
     "name": "Alice",
-    "age": "20"
+    "employeeId": "E12345"
   }
 }
 ```
@@ -195,7 +195,7 @@ The API returns the detected bounding box of the face along with the top person
       "personId": "{personId1}",
       "tags": {
         "name": "Alice",
-        "age": "20"
+        "employeeId": "E12345"
       },
       "confidence": 0.92
     }

articles/ai-services/language-service/named-entity-recognition/overview.md

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure-ai-language
 ms.topic: overview
-ms.date: 02/15/2025
+ms.date: 07/14/2025
 ms.author: lajanuar
 ms.custom: language-service-ner
 ---
@@ -19,31 +19,29 @@ Named Entity Recognition (NER) is one of the features offered by [Azure AI Langu
 * [**How-to guides**](how-to-call.md) contain instructions for using the service in more specific or customized ways.
 * The [**conceptual articles**](concepts/named-entity-categories.md) provide in-depth explanations of the service's functionality and features.
 
-> [!NOTE]
-> [Entity Resolution](concepts/entity-resolutions.md) was upgraded to the [Entity Metadata](concepts/entity-metadata.md) starting in API version 2023-04-15-preview. If you're calling the preview version of the API equal or newer than 2023-04-15-preview, check out the [Entity Metadata](concepts/entity-metadata.md) article to use the resolution feature.
-
 [!INCLUDE [Typical workflow for pre-configured language features](../includes/overview-typical-workflow.md)]
 
 ## Get started with named entity recognition
 
 [!INCLUDE [development options](./includes/development-options.md)]
 
-[!INCLUDE [Developer reference](../includes/reference-samples-text-analytics.md)] 
+[!INCLUDE [Developer reference](../includes/reference-samples-text-analytics.md)]
 
-## Responsible AI 
+## Responsible AI
 
-An AI system includes not only the technology, but also the people who use it, the people who are affected by it, and the environment in which it's deployed. Read the [transparency note for NER](/azure/ai-foundry/responsible-ai/language-service/transparency-note-named-entity-recognition) to learn about responsible AI use and deployment in your systems. You can also see the following articles for more information:
+An AI system consists of more than just its core technology. It also includes the people who operate it, the people its use affects, and the broader deployment context.
+All these interconnected elements shape the effectiveness and outcomes of AI. Read the [transparency note for NER](/azure/ai-foundry/responsible-ai/language-service/transparency-note-named-entity-recognition) to learn about responsible AI use and deployment in your systems. For more information, *see* the following articles:
 
 [!INCLUDE [Responsible AI links](../includes/overview-responsible-ai-links.md)]
 
 ## Scenarios
 
-*	Enhance search capabilities and search indexing - Customers can build knowledge graphs based on entities detected in documents to enhance document search as tags.
-*	Automate business processes - For example, when reviewing insurance claims, recognized entities like name and location could be highlighted to facilitate the review. Or a support ticket could be generated with a customer's name and company automatically from an email.
-*	Customer analysis – Determine the most popular information conveyed by customers in reviews, emails, and calls to determine the most relevant topics that get brought up and determine trends over time. 
+* **Enhance search capabilities and search indexing**. Customers can build knowledge graphs based on entities detected in documents to enhance document search as tags.
+* **Automate business processes** - Insurance claims, recognized entities like name and location can be highlighted to facilitate review. Support tickets can be automatically generated with customer name and company from an email.
+* **In-depth customer analysis**. Determine the most popular information conveyed by customers in reviews, emails, and calls to determine relevant topics and trends over time.
 
 ## Next steps
 
 There are two ways to get started using the Named Entity Recognition (NER) feature:
 * [Azure AI Foundry](../../../ai-foundry/what-is-azure-ai-foundry.md) is a web-based platform that lets you use several Language service features without needing to write code.
-* The [quickstart article](quickstart.md) for instructions on making requests to the service using the REST API and client library SDK.  
+* The [quickstart article](quickstart.md) for instructions on making requests to the service using the REST API and client library SDK.

articles/ai-services/language-service/personally-identifiable-information/language-support.md

@@ -1,7 +1,7 @@
 ---
 title: Personally Identifiable Information (PII) detection language support
 titleSuffix: Azure AI services
-description: This article explains which natural languages are supported by the PII detection feature of Azure AI Language.
+description: This article explains which natural languages the PII detection feature supports of Azure AI Language.
 author: laujan
 manager: nitinme
 ms.service: azure-ai-language
@@ -11,9 +11,10 @@ ms.author: lajanuar
 ms.custom: language-service-pii, build-2024
 ---
 
-# Personally Identifiable Information (PII) detection language support 
+# Personally Identifiable Information (PII) detection language support
+
+Use this article to learn which natural languages text PII, document PII, and conversation PII features support.
 
-Use this article to learn which natural languages are supported by the text PII, document PII, and conversation PII features of Azure AI Language Service.
 # [Text PII](#tab/text)
 
 ## Text PII language support
@@ -190,7 +191,20 @@ Use this article to learn which natural languages are supported by the text PII,
 
 ## PII language support
 
-The Generally Available Conversational PII service currently supports English. Preview model version `2023-04-15-preview` supports English, German, Spanish, and French. 
+PII conversation preview version `2023-04-15-preview` supports the following languages:
+
+* English
+* French
+* German
+* Spanish
+
+
+PII conversation generally available (GA) version currently supports the following languages:
+
+* English
+* French
+* Spanish
+
 
 
 ---

articles/ai-services/language-service/sentiment-opinion-mining/includes/custom/rest-api/assign-resources.md

@@ -50,7 +50,7 @@ Use the following sample JSON as your body.
 
 |Key  |Placeholder  |Value  | Example |
 |---------|---------|----------|--|
-| `azureResourceId` | `{AZURE-RESOURCE-ID}` | The full resource ID path you want to assign. Found in the Azure portal under the **Properties** tab for the resource, in the **Resource ID** field. | `/subscriptions/aaaa0a0a-bb1b-cc2c-dd3d-eeeeee4e4e4e/resourceGroups/ContosoResourceGroup/providers/Microsoft.CognitiveServices/accounts/ContosoResource` |
+| `azureResourceId` | `{AZURE-RESOURCE-ID}` | The full resource ID path you want to assign. Found in the Azure portal under the **Properties** tab for the resource, in the **Resource ID** field. | `/subscriptions/a0a0a0a0-bbbb-cccc-dddd-e1e1e1e1e1e1/resourceGroups/ContosoResourceGroup/providers/Microsoft.CognitiveServices/accounts/ContosoResource` |
 | `customDomain` | `{CUSTOM-DOMAIN}` | The custom subdomain of the resource you want to assign. Found in the Azure portal under the **Keys and Endpoint** tab for the resource, as the **Endpoint** field in the URL `https://<your-custom-subdomain>.cognitiveservices.azure.com/` | `contosoresource`  |
 | `region` | `{REGION-CODE}` |  A region code specifying the region of the resource you want to assign. Found in the Azure portal under the **Keys and Endpoint** tab for the resource, in the **Location/Region** field. |`eastus`|