Merge pull request #2509 from MicrosoftDocs/main

1/24/2025 PM Publish

Author: Taojunshen

articles/ai-foundry/model-inference/overview.md

@@ -7,7 +7,7 @@ author: msakande
 reviewer: santiagxf
 ms.service: azure-ai-model-inference
 ms.topic: concept-article
-ms.date: 1/21/2025
+ms.date: 01/24/2025
 ms.author: mopeakande
 ms.reviewer: fasantia
 ms.custom: generated
@@ -20,7 +20,7 @@ Azure AI model inference provides access to the most powerful models available i
 
 Azure AI model inference provides a way to **consume models as APIs without hosting them on your infrastructure**. Models are hosted in a Microsoft-managed infrastructure, which enables API-based access to the model provider's model. API-based access can dramatically reduce the cost of accessing a model and simplify the provisioning experience.
 
-Azure AI model inference is part of Azure AI Services and users can access the service through [REST APIs](../../ai-studio/reference/reference-model-inference-api.md), [SDKs in several languages](supported-languages.md) including Python, C#, JavaScript, and Java. It can also be used from [Azure AI Foundry by configuring a connection](how-to/configure-project-connection.md).
+Azure AI model inference is part of Azure AI Services, and users can access the service through [REST APIs](../../ai-studio/reference/reference-model-inference-api.md), [SDKs in several languages](supported-languages.md) such as Python, C#, JavaScript, and Java. You can also use the Azure AI model inference from [Azure AI Foundry by configuring a connection](how-to/configure-project-connection.md).
 
 ## Models
 
@@ -42,9 +42,9 @@ You can get access to the key model providers in the industry including OpenAI,
 
 ## Pricing
 
-Models that are offered by non-Microsoft providers (for example, Meta AI and Mistral models) are billed through Azure Marketplace. For such models, you're required to subscribe to the particular model offering in accordance with the [Microsoft Commercial Marketplace Terms of Use](/legal/marketplace/marketplace-terms). Users accept license terms for use of the models. Pricing information for consumption is provided during deployment.
+For models from non-Microsoft providers (for example, Meta AI and Mistral models), billing is through Azure Marketplace. For such models, you're required to subscribe to the particular model offering in accordance with the [Microsoft Commercial Marketplace Terms of Use](/legal/marketplace/marketplace-terms). Users accept license terms for use of the models. Pricing information for consumption is provided during deployment.
 
-Models that are offered by Microsoft (for example, Phi-3 models and Azure OpenAI models) don't have this requirement, and they're billed via Azure meters as First Party Consumption Services. As described in the [Product Terms](https://www.microsoft.com/licensing/terms/welcome/welcomepage), you purchase First Party Consumption Services by using Azure meters, but they aren't subject to Azure service terms.
+For Microsoft models (for example, Phi-3 models and Azure OpenAI models) billing is via Azure meters as First Party Consumption Services. As described in the [Product Terms](https://www.microsoft.com/licensing/terms/welcome/welcomepage), you purchase First Party Consumption Services by using Azure meters, but they aren't subject to Azure service terms.
 
 > [!TIP]
 > Learn how to [monitor and manage cost](how-to/manage-costs.md) in Azure AI model inference.
@@ -53,7 +53,7 @@ Models that are offered by Microsoft (for example, Phi-3 models and Azure OpenAI
 
 At Microsoft, we're committed to the advancement of AI driven by principles that put people first. Generative models such as the ones available in Azure AI models have significant potential benefits, but without careful design and thoughtful mitigations, such models have the potential to generate incorrect or even harmful content. 
 
-Microsoft has made significant investments to help guard against abuse and unintended harm. These investments include:
+Microsoft helps guard against abuse and unintended harm by taking the following actions:
 
 - Incorporating Microsoft's [principles for responsible AI use](https://www.microsoft.com/ai/responsible-ai)
 - Adopting a [code of conduct](/legal/cognitive-services/openai/code-of-conduct?context=/azure/ai-services/openai/context/context) for use of the service
@@ -62,9 +62,9 @@ Microsoft has made significant investments to help guard against abuse and unint
 
 ## Getting started
 
-Azure AI Models is a new feature offering on Azure AI Services resources. You can get started with it the same way as any other Azure product where you [create and configure your resource for Azure AI model inference](how-to/quickstart-create-resources.md), or instance of the service, in your Azure Subscription. You can create as many resources as needed and configure them independently in case you have multiple teams with different requirements.
+Azure AI model inference is a new feature offering on Azure AI Services resources. You can get started with it the same way as any other Azure product where you [create and configure your resource for Azure AI model inference](how-to/quickstart-create-resources.md), or instance of the service, in your Azure Subscription. You can create as many resources as needed and configure them independently in case you have multiple teams with different requirements.
 
-Once you create an Azure AI Services resource, you must deploy a model before you can start making API calls. By default, no models are available on it so you can control which ones to start from. See the tutorial [Create your first model deployment in Azure AI model inference](how-to/create-model-deployments.md).
+Once you create an Azure AI Services resource, you must deploy a model before you can start making API calls. By default, no models are available on it, so you can control which ones to start from. See the tutorial [Create your first model deployment in Azure AI model inference](how-to/create-model-deployments.md).
 
 ## Next steps
 

articles/ai-services/agents/how-to/tools/overview.md

@@ -30,7 +30,7 @@ Agents can access multiple tools in parallel. These can be both Azure OpenAI-hos
 |---------|---------|---------|---------|---------|---------|
 | [Grounding with Bing Search](./bing-grounding.md)     | Allows your agents to incorporate real-time public web data when generating responses.         | ✔️ | ✔️ | ✔️ | ✔️ |
 |[File search](./file-search.md)    | Augments agents with knowledge from outside its model, such as proprietary product information or documents provided by your users.        | ✔️ | ✔️ | File upload only | File upload and using blob storage | 
-| [Azure AI Search](./azure-ai-search.md) | Uses an existing Azure AI Search index as a knowledge base. | ✔️ | ✔️ | | ✔️ |
+| [Azure AI Search](./azure-ai-search.md) | Uses an existing Azure AI Search index as a knowledge base. | ✔️ | ✔️ | ✔️ | ✔️ |
 
 ## Action tools
 

articles/ai-services/agents/includes/azure-search/setup.md

@@ -13,15 +13,8 @@ ms.date: 12/10/2024
 A prerequisite of using the Azure AI Search tool is to have an existing Azure AI Search index. If you don't have an existing index, you can create one in the Azure portal using the import and vectorize data wizard.
 -  [Quickstart: Create a vector index with the import and vectorize data wizard in the Azure portal](../../../../search/search-get-started-portal-import-vectors.md)
 
-
-#### Complete the agent setup
-- **Option 1: Standard Agent Setup using an existing AI Search resource** If you want your agent to use an existing AI Search resource to create new indexes or bring existing ones you should use the [standard agent setup and add your AI Search resource ID](../../quickstart.md). 
-    - You can provide your Azure AI Search resource ID in the bicep file. Your resource ID should be in the format: `/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.Search/searchServices/{searchServiceName}`.
-- **Option 2: Standard Agent Setup** If you want to create a new Azure AI Search resource for your agents to use when creating new indexes follow the [standard agent setup](../../quickstart.md).
-
-
 #### Create a project connection to the Azure AI Search resource with the index you want to use
-Once you have completed the standard agent setup, you must create a project connection to the Azure AI Search resource that contains the index you want to use. 
+Once you have completed the agent setup, you must create a project connection to the Azure AI Search resource that contains the index you want to use. 
 
 If you already connected the AI Search resource that contains the index you want to use to your project, skip this step. 
 

articles/ai-services/commitment-tier.md

@@ -74,8 +74,6 @@ If you use the resource above the quota provided, you're charged for the additio
 
 The commitment plans have a calendar month commitment period. You can purchase a commitment plan at any time from the default pay-as-you-go pricing model. When you purchase a plan, you're charged a pro-rated price for the remaining month. During the commitment period, you can't change the commitment plan for the current month. However, you can choose a different commitment plan for the next calendar month. The billing for the next month would happen on the first day of the next month.
 
-If you need a larger commitment plan than any of the ones offered, contact `[email protected]`.
-
 ## End a commitment plan
 
 If you decide that you don't want to continue purchasing a commitment plan, you can set your resource's autorenewal to **Do not auto-renew**. Your commitment plan expires on the displayed commitment end date. After this date, you won't be charged for the commitment plan. You're able to continue using the Azure resource to make API calls, charged at pay-as-you-go pricing. You have until midnight (UTC) on the last day of each month to end a commitment plan, and not be charged for the following month.

articles/ai-services/document-intelligence/concept/add-on-capabilities.md

@@ -55,9 +55,9 @@ Document Intelligence supports more sophisticated and modular analysis capabilit
 
 > [!NOTE]
 >
-> * Not all add-on capabilities are supported by all models. For more information, *see* [model data extraction](../model-overview.md#model-analysis-features).
+> Not all models or Microsoft Office file types support add-on capabilities. For more information, *see* [model data extraction](../model-overview.md#model-analysis-features).
 >
-> * Add-on capabilities are currently not supported for Microsoft Office file types.
+
 :::moniker-end
 
 ## Version availability
@@ -73,7 +73,7 @@ Document Intelligence supports more sophisticated and modular analysis capabilit
 |High resolution extraction|**Add-On**| ✔️| ✔️| n/a| n/a|
 |Query fields|**Add-On**| ✔️|n/a|n/a| n/a|
 
-✱ Add-On - Query fields are priced differently than the other add-on features. See [pricing](https://azure.microsoft.com/pricing/details/ai-document-intelligence/) for details. </br>
+✱ Add-On - Query fields are priced differently than the other add-on features. See [pricing](https://azure.microsoft.com/pricing/details/ai-document-intelligence/) for details.</br>
 ** Add-On - Searchable pdf is available only with Read model as an add-on feature. 
 
 ## Supported file formats
@@ -759,7 +759,7 @@ The `ocr.barcode` capability extracts all identified barcodes in the `barcodes`
 | `Databar` |:::image type="content" source="../media/barcodes/databar.png" alt-text="Screenshot of the Data bar.":::|
 | `Databar` Expanded |:::image type="content" source="../media/barcodes/databar-expanded.gif" alt-text="Screenshot of the Data bar Expanded.":::|
 | `ITF` |:::image type="content" source="../media/barcodes/interleaved-two-five.png" alt-text="Screenshot of the interleaved-two-of-five barcode (ITF).":::|
-| `Data Matrix` |:::image type="content" source="../media/barcodes/datamatrix.gif" alt-text="Screenshot of the Data Matrix.":::|
+| `Data Matrix` |:::image type="content" source="../media/barcodes/data-matrix.png" alt-text="Screenshot of the Data Matrix.":::|
 
 ::: moniker range="doc-intel-4.0.0"
 
@@ -983,8 +983,8 @@ The searchable PDF capability enables you to convert an analog PDF, such as scan
 
   > [!IMPORTANT]
   >
-  > * Currently, the searchable PDF capability is only supported by Read OCR model `prebuilt-read`. When using this feature, please specify the `modelId` as `prebuilt-read`.
-  > * Searchable PDF is included with the 2024-11-30 (GA) `prebuilt-read` model with no usage cost for general PDF consumption.
+  > * Currently, only the Read model `prebuilt-read` supports the searchable PDF capability. When using this feature, specify the `modelId` as `prebuilt-read`.
+  > * Searchable PDF is included with the `2024-11-30` (GA) `prebuilt-read` model with no usage cost for general PDF consumption.
 
 ### Use searchable PDF
 
@@ -1044,7 +1044,7 @@ Query fields are an add-on capability to extend the schema extracted from any pr
 
 > [!NOTE]
 >
-> Document Intelligence Studio query field extraction is currently available with the Layout and Prebuilt models `2024-11-30 (GA) API with the exception of the `US tax` models (W2, 1098s, and 1099s models).
+> Document Intelligence Studio query field extraction is currently available with the Layout and Prebuilt models `2024-11-30` (GA) API except for US tax models W2, 1098, and 1099.
 
 ### Query field extraction
 

articles/ai-services/document-intelligence/faq.yml

@@ -383,7 +383,8 @@ sections:
         answer: |
           **Yes,** briefly.
 
-          For all features, Document Intelligence temporarily stores data and results in Azure Storage in the same region as the request. Your data is then deleted within 24 hours from the time that you submit an analyze request.
+          For all features, Document Intelligence temporarily stores data and results in Azure Storage in the same region as the request. Your data is then deleted 24 hours from the time that you submit an analyze request. If you would like the data deleted sooner, you can call the [delete analyze response](https://learn.microsoft.com/rest/api/aiservices/document-models/delete-analyze-result?view=rest-aiservices-v4.0%20(2024-11-30)&tabs=HTTP). This API marks the results for deletion and is available in the v4.0 API.
+    
 
           Learn more about [data, privacy, and security for Document Intelligence](/legal/cognitive-services/document-intelligence/data-privacy-security?toc=/azure/ai-services/document-intelligence/toc.json&bc=/azure/ai-services/document-intelligence/breadcrumb/toc.json).
 

articles/ai-services/document-intelligence/media/barcodes/codabar.png

@@ -76,6 +76,9 @@ For more information, *see* client libraries for the following supported program
 *  [🆕 US Tax model](prebuilt/tax-document.md)
    *  New prebuilt tax models added for 1095A, 1095C, 1099SSA, and W4.
 
+* [Delete analyze response](https://learn.microsoft.com/rest/api/aiservices/document-models/delete-analyze-result?view=rest-aiservices-v4.0%20(2024-11-30)&tabs=HTTP)
+  * Analyze response is stored for 24 hours from when the operation completes for retrieval. For scenarios where you want to delete the response sooner, use the delete analyze response API to delete the response.  
+
 * The v4.0 API includes cumulative updates from preview releases as listed:
   * [August 2024](#august-2024)
   * [May 2024](#may-2024)