Merge pull request #6166 from laujan/patch-1

Update azure-resources.md

Author: prmerger-automator[bot]

articles/ai-services/language-service/question-answering/concepts/azure-resources.md

@@ -1,24 +1,24 @@
 ---
 title: Azure resources - custom question answering
-description: Question answering uses several Azure sources, each with a different purpose. Understanding how they are used individually allows you to plan for and select the correct pricing tier or know when to change your pricing tier. Understanding how they are used in combination allows you to find and fix problems when they occur.
+description: Question answering uses several Azure sources, each with a different purpose. Understanding how they're used individually allows you to plan for and select the correct pricing tier or know when to change your pricing tier. Understanding how they're used in combination allows you to find and fix problems when they occur.
 ms.service: azure-ai-language
 ms.topic: conceptual
 author: laujan
 ms.author: lajanuar
-ms.date: 06/30/2025
+ms.date: 07/22/2025
 ms.custom: language-service-question-answering
 ---
 
 # Azure resources for custom question answering
 
-Custom question answering uses several Azure sources, each with a different purpose. Understanding how they are used individually allows you to plan for and select the correct pricing tier or know when to change your pricing tier. Understanding how resources are used _in combination_ allows you to find and fix problems when they occur.
+Custom question answering uses several Azure sources, each with a different purpose. Understanding how they're used individually allows you to plan for and select the correct pricing tier or know when to change your pricing tier. Understanding how resources are used _in combination_ allows you to find and fix problems when they occur.
 
 ## Resource planning
 
 > [!TIP]
 > "Knowledge base" and "project" are equivalent terms in custom question answering and can be used interchangeably.
 
-When you first develop a project, in the prototype phase, it is common to have a single resource for both testing and production.
+When you first develop a project, in the prototype phase, it's common to have a single resource for both testing and production.
 
 When you move into the development phase of the project, you should consider:
 
@@ -34,14 +34,15 @@ Typically there are three parameters you need to consider:
 
     * The throughput for custom question answering is currently capped at 10 text records per second for both management APIs and prediction APIs.
 
-    * This should also influence your **Azure AI Search** selection, see more details [here](/azure/search/search-sku-tier). Additionally, you might need to adjust Azure AI Search [capacity](/azure/search/search-capacity-planning) with replicas.
+    * The throughput cap should also influence your **Azure AI Search** selection. For more information, *see* [Azure AI Search](/azure/search/search-sku-tier). Additionally, you might need to adjust Azure AI Search [capacity](/azure/search/search-capacity-planning) with replicas.
 
 * **Size and the number of projects**: Choose the appropriate [Azure search SKU](https://azure.microsoft.com/pricing/details/search/) for your scenario. Typically, you decide the number of projects you need based on number of different subject domains. One subject domain (for a single language) should be in one project.
 
     With custom question answering, you have a choice to set up your language resource in a single language or multiple languages. You can make this selection when you create your first project in the [Language Studio](https://language.azure.com/).
 
     > [!IMPORTANT]
-    > You can publish N-1 projects of a single language or N/2 projects of different languages in a particular tier, where N is the maximum indexes allowed in the tier. Also check the maximum size and the number of documents allowed per tier.
+    > You can publish N-1 projects  with a single language resource or N-2 projects with multiple language resources in a single tier. The `N` notation is the maximum indexes allowed in the tier.
+    > Also, check the maximum size and the number of documents allowed per tier.
 
     For example, if your tier has 15 allowed indexes, you can publish 14 projects of the same language (one index per published project). The 15th index is used for all the projects for authoring and testing. If you choose to have projects in different languages, then you can only publish seven projects.
 
@@ -51,9 +52,9 @@ The following table gives you some high-level guidelines.
 
 |                            |Azure AI Search | Limitations                      |
 | -------------------------- |------------ | -------------------------------- |
-| **Experimentation**        |Free Tier    | Publish Up to 2 KBs, 50 MB size  |
-| **Dev/Test Environment**   |Basic        | Publish Up to 14 KBs, 2 GB size    |
-| **Production Environment** |Standard     | Publish Up to 49 KBs, 25 GB size |
+| **Experimentation**        |Free Tier    | Publish Up to 2-KBs, 50-MB size  |
+| **Dev/Test Environment**   |Basic        | Publish Up to 14-KBs, 2-GB size    |
+| **Production Environment** |Standard     | Publish Up to 49-KBs, 25-GB size |
 
 ## Recommended settings
 
@@ -63,14 +64,14 @@ The throughput for custom question answering is currently capped at 10 text reco
 
 ## Keys in custom question answering
 
-Your custom question answering feature deals with two kinds of keys: **authoring keys** and **Azure AI Search keys** used to access the service in the customer’s subscription.
+Your custom question answering feature deals with two kinds of keys: **authoring keys** and **Azure AI Search keys** used to access the service in the customer's subscription.
 
 Use these keys when making requests to the service through APIs.
 
 |Name|Location|Purpose|
 |--|--|--|
 |Authoring/Subscription key|[Azure portal](https://azure.microsoft.com/free/cognitive-services/)|These keys are used to access the Language service APIs). These APIs let you edit the questions and answers in your project, and publish your project. These keys are created when you create a new resource.<br><br>Find these keys on the **Azure AI services** resource on the **Keys and Endpoint** page.|
-|Azure AI Search Admin Key|[Azure portal](/azure/search/search-security-api-keys)|These keys are used to communicate with the Azure AI Search service deployed in the user’s Azure subscription. When you associate an Azure AI Search resource with the custom question answering feature, the admin key is automatically passed to custom question answering. <br><br>You can find these keys on the **Azure AI Search** resource on the **Keys** page.|
+|Azure AI Search Admin Key|[Azure portal](/azure/search/search-security-api-keys)|These keys are used to communicate with the Azure AI Search service deployed in the user's Azure subscription. When you associate an Azure AI Search resource with the custom question answering feature, the admin key is automatically passed to custom question answering. <br><br>You can find these keys on the **Azure AI Search** resource on the **Keys** page.|
 
 ### Find authoring keys in the Azure portal
 
@@ -94,12 +95,12 @@ In custom question answering, both the management and the prediction services ar
 
 Each Azure resource created with custom question answering feature has a specific purpose:
 
-* Language resource (Also referred to as a Text Analytics resource depending on the context of where you are evaluating the resource.)
+* Language resource (Also referred to as a Text Analytics resource depending on the context of where you're evaluating the resource.)
 * Azure AI Search resource
 
 ### Language resource
 
-The language resource with custom question answering feature provides access to the authoring and publishing APIs, hosts the ranking runtime as well as provides telemetry.
+The language resource with custom question answering feature provides access to the authoring and publishing APIs, hosts the ranking runtime and provides telemetry.
 
 ### Azure AI Search resource
 

articles/ai-services/language-service/question-answering/concepts/limits.md

@@ -1,16 +1,16 @@
 ---
 title: Limits and boundaries - custom question answering
-description: Custom question answering has meta-limits for parts of the knowledge base and service. It is important to keep your knowledge base within those limits in order to test and publish.
+description: Custom question answering has meta-limits for parts of the knowledge base and service. It's important to keep your knowledge base within those limits in order to test and publish.
 ms.service: azure-ai-language
 author: laujan
 ms.author: lajanuar
 ms.topic: conceptual
-ms.date: 06/21/2025
+ms.date: 07/22/2025
 ---
 
 # Project limits and boundaries
 
-Custom question answering limits provided below are a combination of the [Azure AI Search pricing tier limits](/azure/search/search-limits-quotas-capacity) and custom question answering limits. Both sets of limits affect how many projects you can create per resource and how large each project can grow.
+The following custom question answering limits are a combination of the [Azure AI Search pricing tier limits](/azure/search/search-limits-quotas-capacity) and custom question answering limits. Both sets of limits affect how many projects you can create per resource and how large each project can grow.
 
 ## Projects
 
@@ -21,7 +21,8 @@ Choose the appropriate [Azure search SKU](https://azure.microsoft.com/pricing/de
 With custom question answering, you have a choice to set up your language resource in a single language or multiple languages. You can make this selection when you create your first project in the [Language Studio](https://language.azure.com/).
 
   > [!IMPORTANT]
-  > You can publish N-1 projects of a single language or N/2 projects of different languages in a particular tier, where N is the maximum indexes allowed in the tier. Also check the maximum size and the number of documents allowed per tier.
+  > You can publish N-1 projects with a single language resource or N-2 projects with multiple language resources in a single tier. The `N` notation is the maximum indexes allowed in the tier.
+  > Also check the maximum size and the number of documents allowed per tier.
 
 For example, if your tier has 15 allowed indexes, you can publish 14 projects of the same language (one index per published project). The 15th index is used for all the projects for authoring and testing. If you choose to have projects in different languages, then you can only publish seven projects.
 
@@ -32,7 +33,7 @@ For example, if your tier has 15 allowed indexes, you can publish 14 projects of
 
 File names may not include the following characters:
 
-|Do not use character|
+|Don't use character|
 |--|
 |Single quote `'`|
 |Double quote `"`|
@@ -51,17 +52,17 @@ File names may not include the following characters:
 
 > [!NOTE]
 > Custom question answering currently has no limits on the number of sources that can be added. Throughput is currently capped at 10 text records per second for both management APIs and prediction APIs.
-> When using the F0 tier, upload is limited to 3 files.
+> If you use the F0 tier, upload is limited to three files.
 
 ### Maximum number of deep-links from URL
 
 The maximum number of deep-links that can be crawled for extraction of question answer pairs from a URL page is **20**.
 
 ## Metadata limits
 
-Metadata is presented as a text-based `key:value` pair, such as `product:windows 10`. It is stored and compared in lower case. Maximum number of metadata fields is based on your **[Azure AI Search tier limits](/azure/search/search-limits-quotas-capacity)**.
+Metadata is presented as a text-based `key:value` pair, such as `product:windows 10`. Metadata is stored and compared in lower case. The maximum number of metadata fields is based on your **[Azure AI Search tier limits](/azure/search/search-limits-quotas-capacity)**.
 
-If you choose to projects with multiple languages in a single language resource, there is a dedicated test index per project. So the limit is applied per project in the language service.
+If you choose to projects with multiple languages in a single language resource, there's a dedicated test index per project. So the limit is applied per project in the language service.
 
 |**Azure AI Search tier** | **Free** | **Basic** |**S1** | **S2**| **S3** |**S3 HD**|
 |---|---|---|---|---|---|----|
@@ -99,7 +100,7 @@ Overall limits on the content in the project:
 
 ## Create project call limits:
 
-These represent the limits for each create project action; that is, selecting *Create new project* or calling the REST API to create a project.
+The limits for each create project action, that is, selecting *Create new project* or calling the REST API to create a project are as follows:
 
 * Recommended maximum number of alternate questions per answer: 300
 * Maximum number of URLs: 10
@@ -108,7 +109,8 @@ These represent the limits for each create project action; that is, selecting *C
 
 ## Update project call limits
 
-These represent the limits for each update action; that is, selecting *Save* or calling the REST API with an update request.
+The limits for each update action, that is, selecting *Save* or calling the REST API with an update request are as follows:
+
 * Length of each source name: 300
 * Recommended maximum number of alternate questions added or deleted: 300
 * Maximum number of metadata fields added or deleted: 10
@@ -118,19 +120,21 @@ These represent the limits for each update action; that is, selecting *Save* or
 ## Add unstructured file limits
 
 > [!NOTE]
-> * If you need to use larger files than the limit allows, you can break the file into smaller files before sending them to the API. 
+> * If you need to use larger files than the limit allows, you can break the file into smaller files before sending them to the API.
+
+The limits when unstructured files are used to *Create new project* or call the REST API to create a project are as follows:
 
-These represent the limits when unstructured files are used to *Create new project* or call the REST API to create a project:
-* Length of file: We will extract first 32000 characters
+* Length of file: The service extracts the first 32,000 characters.
 * Maximum three responses per file.
 
 ## Prebuilt custom question answering limits
 
 > [!NOTE]
-> * If you need to use larger documents than the limit allows, you can break the text into smaller chunks of text before sending them to the API. 
-> * A document is a single string of text characters.  
+> * A document is a single string of text characters.
+> * To use larger documents than the limit allows, you can break the text into smaller chunks before sending them to the API.
+
+The limits when the REST API is used to answer a question without having to create a project is as follows:
 
-These represent the limits when REST API is used to answer a question based without having to create a project:
 * Number of documents: 5
 * Maximum size of a single document:  5,120 characters
 * Maximum three responses per document.