@@ -111,7 +111,7 @@ To create custom models, start with configuring your project:
 
 :::image type="content" source="../media/studio/create-project.gif" alt-text="Animation showing create a custom project in Document Intelligence Studio.":::
 
-While creating your custom models, you may need to extract data collections from your documents. The collections may appear one of two formats. Using tables as the visual pattern:
+While creating your custom models, you might need to extract data collections from your documents. The collections may appear one of two formats. Using tables as the visual pattern:
 
 * Dynamic or variable count of values (rows) for a given set of fields (columns)
 
@@ -474,7 +474,7 @@ Using the programming language of your choice to analyze a form or document with
 
 ---
 
-Test your newly trained models by [analyzing forms](build-a-custom-model.md?view=doc-intel-2.1.0&preserve-view=true#test-the-model) that weren't part of the training dataset. Depending on the reported accuracy, you may want to do further training to improve the model. You can continue further training to [improve results](../label-tool.md#improve-results).
+Test your newly trained models by [analyzing forms](build-a-custom-model.md?view=doc-intel-2.1.0&preserve-view=true#test-the-model) that weren't part of the training dataset. Depending on the reported accuracy, you might want to do further training to improve the model. You can continue further training to [improve results](../label-tool.md#improve-results).
 
 ## Manage your custom models
 

@@ -106,7 +106,7 @@ After you create your web app, you can enable the continuous deployment option:
 > When creating your web app, you can also configure authorization/authentication. This is not necessary to get started.
 
 > [!IMPORTANT]
-> You may need to enable TLS for your web app in order to view it at its `https` address. Follow the instructions in [Enable a TLS endpoint](/azure/container-instances/container-instances-container-group-ssl) to set up a sidecar container than enables TLS/SSL for your web app.
+> You might need to enable TLS for your web app in order to view it at its `https` address. Follow the instructions in [Enable a TLS endpoint](/azure/container-instances/container-instances-container-group-ssl) to set up a sidecar container than enables TLS/SSL for your web app.
 <!-- markdownlint-disable MD001 -->
 ### Azure CLI
 

@@ -288,7 +288,7 @@ To test your model, select the `Analyze` icon from the navigation bar. Select so
 
 ## Improve results
 
-Depending on the reported accuracy, you may want to do further training to improve the model. After you complete a prediction, examine the confidence values for each of the applied tags. If the average accuracy training value is high, but the confidence scores are low (or the results are inaccurate), add the prediction file to the training set, label it, and train again.
+Depending on the reported accuracy, you might want to do further training to improve the model. After you complete a prediction, examine the confidence values for each of the applied tags. If the average accuracy training value is high, but the confidence scores are low (or the results are inaccurate), add the prediction file to the training set, label it, and train again.
 
 The reported average accuracy, confidence scores, and actual accuracy can be inconsistent when the analyzed documents differ from documents used in training. Keep in mind that some documents look similar when viewed by people but can look distinct to the AI model. For example, you might train with a form type that has two variations, where the training set consists of 20% variation A and 80% variation B. During prediction, the confidence scores for documents of variation A are likely to be lower.
 

@@ -24,9 +24,9 @@ The schema defines the classes that you need your model to classify your text in
 
     For example, if you are classifying support tickets, you might need the following classes: *login issue*, *hardware issue*, *connectivity issue*, and *new equipment request*.
 
-* **Avoid ambiguity in classes**: Ambiguity arises when the classes you specify share similar meaning to one another. The more ambiguous your schema is, the more labeled data you may need to differentiate between different classes.
+* **Avoid ambiguity in classes**: Ambiguity arises when the classes you specify share similar meaning to one another. The more ambiguous your schema is, the more labeled data you might need to differentiate between different classes.
 
-    For example, if you are classifying food recipes, they may be similar to an extent. To differentiate between *dessert recipe* and *main dish recipe*, you may need to label more examples to help your model distinguish between the two classes. Avoiding ambiguity saves time and yields better results. 
+    For example, if you are classifying food recipes, they may be similar to an extent. To differentiate between *dessert recipe* and *main dish recipe*, you might need to label more examples to help your model distinguish between the two classes. Avoiding ambiguity saves time and yields better results. 
 
 * **Out of scope data**: When using your model in production, consider adding an *out of scope* class to your schema if you expect documents that don't belong to any of your classes. Then add a few documents to your dataset to be labeled as *out of scope*. The model can learn to recognize irrelevant documents, and predict their labels accordingly.
 

@@ -32,7 +32,7 @@ setx LANGUAGE_ENDPOINT your-endpoint
 > [!NOTE]
 > If you only need to access the environment variables in the current running console, you can set the environment variable with `set` instead of `setx`.
 
-After you add the environment variables, you may need to restart any running programs that will need to read the environment variables, including the console window. For example, if you are using Visual Studio as your editor, restart Visual Studio before running the example.
+After you add the environment variables, you might need to restart any running programs that will need to read the environment variables, including the console window. For example, if you are using Visual Studio as your editor, restart Visual Studio before running the example.
 
 #### [Linux](#tab/linux)
 

@@ -56,7 +56,7 @@ To see the loaded data, click the **Data View** button on the left edge of the P
 
 ## Prepare the data
 
-You may need to transform your data in Power BI Desktop before it's ready to be processed by Key Phrase Extraction.
+You might need to transform your data in Power BI Desktop before it's ready to be processed by Key Phrase Extraction.
 
 The sample data contains a `subject` column and a `comment` column. With the Merge Columns function in Power BI Desktop, you can extract key phrases from the data in both these columns, rather than just the `comment` column.
 
@@ -66,7 +66,7 @@ In Power BI Desktop, select the **Home** ribbon. In the **External data** group,
 
 Select `FabrikamComments` in the **Queries** list at the left side of the window if it isn't already selected.
 
-Now select both the `subject` and `comment` columns in the table. You may need to scroll horizontally to see these columns. First click the `subject` column header, then hold down the Control key and click the `comment` column header.
+Now select both the `subject` and `comment` columns in the table. You might need to scroll horizontally to see these columns. First click the `subject` column header, then hold down the Control key and click the `comment` column header.
 
 ![Selecting fields to be merged](../media/tutorials/power-bi/select-columns.png)
 
@@ -140,7 +140,7 @@ A new field appears in the dialog, **text (optional)**. This field is asking whi
 
 Finally, select **OK.**
 
-If everything is ready, Power BI calls your custom function once for each row in the table. It sends the queries to the Key Phrases API and adds a new column to the table to store the results. But before that happens, you may need to specify authentication and privacy settings.
+If everything is ready, Power BI calls your custom function once for each row in the table. It sends the queries to the Key Phrases API and adds a new column to the table to store the results. But before that happens, you might need to specify authentication and privacy settings.
 
 ## Authentication and privacy
 
@@ -156,7 +156,7 @@ Select **Edit Credentials,** make sure `Anonymous` is selected in the dialog, th
 > [!div class="mx-imgBorder"]
 > ![setting authentication to anonymous](../media/tutorials/power-bi/access-web-content.png)
 
-If you see the Edit Credentials banner even after choosing anonymous access, you may have forgotten to paste your Language resource key into the code in the `KeyPhrases` [custom function](#create-a-custom-function).
+If you see the Edit Credentials banner even after choosing anonymous access, you might have forgotten to paste your Language resource key into the code in the `KeyPhrases` [custom function](#create-a-custom-function).
 
 Next, a banner may appear asking you to provide information about your data sources' privacy. 
 

@@ -34,7 +34,7 @@ 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** SKU selection, see more details [here](/azure/search/search-sku-tier). Additionally, you may need to adjust Azure AI Search [capacity](/azure/search/search-capacity-planning) with replicas.
+    * This should also influence your **Azure AI Search** SKU 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.
 
 * **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.
 

@@ -1,6 +1,6 @@
 ---
 title: Get default answer - custom question answering
-description: The default answer is returned when there is no match to the question. You may want to change the default answer from the standard default answer in custom question answering.
+description: The default answer is returned when there is no match to the question. You might want to change the default answer from the standard default answer in custom question answering.
 ms.service: azure-ai-language
 ms.topic: how-to
 ms.date: 11/21/2024

@@ -38,7 +38,7 @@ You can create a custom question answering project from your own content, such a
     > [!div class="mx-imgBorder"]
     > ![Enable custom question answering](../media/create-test-deploy/enable-custom-question-answering.png)
 
-5. Return to the Language Studio tab. You may need to refresh this page for it to register the change to your resource. Select **Create new project**.
+5. Return to the Language Studio tab. You might need to refresh this page for it to register the change to your resource. Select **Create new project**.
 
 6. Choose the option **I want to set the language for all projects created in this resource** > select **English** > Select **Next**.
 

@@ -11,7 +11,7 @@ ms.date: 11/21/2024
 ---
 # Export-import-refresh in custom question answering
 
-You may want to create a copy of your custom question answering project or related question and answer pairs for several reasons:
+You might want to create a copy of your custom question answering project or related question and answer pairs for several reasons:
 
 * To implement a backup and restore process
 * To integrate with your CI/CD pipeline

@@ -14,7 +14,7 @@ ms.custom: language-service-question-answering
 
 > This article deals with the process to export and move projects and sources from one Language resource to another.
 
-You may want to create copies of your projects or sources for several reasons:
+You might want to create copies of your projects or sources for several reasons:
 
 * To implement a backup and restore process
 * Integrate with your CI/CD pipeline

@@ -26,7 +26,7 @@ This functionality is provided to support scenarios where the content in the sou
 If you have a project with a URL source that has changed, you can trigger a smart URL refresh to keep your project up to date. The service will scan the URL for updated content and generate QnA pairs. It will add any new QnA pairs to your project and also delete any pairs that have disappeared from the source (with exceptions—see below). It also merges old and new QnA pairs in some situations (see below).
 
 > [!IMPORTANT]
-> Because smart URL refresh can involve deleting old content from your project, you may want to [create a backup](./export-import-refresh.md) of your project before you do any refresh operations.
+> Because smart URL refresh can involve deleting old content from your project, you might want to [create a backup](./export-import-refresh.md) of your project before you do any refresh operations.
 
 You can trigger a URL refresh in Language Studio by opening your project, selecting the source in the **Manage sources** list, and selecting **Refresh URL**.
 
@@ -64,14 +64,14 @@ See the following example of a merge operation with differing questions and prom
 
 |Source iteration|Question  |Answer  |Prompts  |
 |---------|---------|---------|--|
-|old |"What is the new HR policy?"     |  "You may have to choose among the following options:"       | P1, P2        |
-|new |"What is the new payroll policy?"    |  "You may have to choose among the following options:"    |  P3, P4   |
+|old |"What is the new HR policy?"     |  "You might have to choose among the following options:"       | P1, P2        |
+|new |"What is the new payroll policy?"    |  "You might have to choose among the following options:"    |  P3, P4   |
 
-The prompts P1 and P2 come from the original source and are different from prompts P3 and P4 of the new QnA pair. They both have the same answer, `You may have to choose among the following options:`, but it leads to different prompts. In this case, the resulting QnA pair would look like this:
+The prompts P1 and P2 come from the original source and are different from prompts P3 and P4 of the new QnA pair. They both have the same answer, `You might have to choose among the following options:`, but it leads to different prompts. In this case, the resulting QnA pair would look like this:
 
 |Question  |Answer  |Prompts  |
 |---------|---------|--|
-|"What is the new HR policy?" </br>(alternate question: "What is the new payroll policy?")    |  "You may have to choose among the following options:"       | P3, P4  |
+|"What is the new HR policy?" </br>(alternate question: "What is the new payroll policy?")    |  "You might have to choose among the following options:"       | P3, P4  |
 
 #### Duplicate answers scenario
 

@@ -36,7 +36,7 @@ You can create a custom question answering project from your own content, such a
     > [!div class="mx-imgBorder"]
     > ![Enable custom question answering](../media/create-test-deploy/enable-custom-question-answering.png)
 
-5. Return to the Language Studio tab. You may need to refresh this page for it to register the change to your resource. Select **Create new project**.
+5. Return to the Language Studio tab. You might need to refresh this page for it to register the change to your resource. Select **Create new project**.
 
 6. Choose the option **I want to set the language for all projects created in this resource** > select **English** > Select **Next**.
 

@@ -28,7 +28,7 @@ You can also use [https://ai.azure.com/resource](https://ai.azure.com/resource)
 
 ## Focus on Azure OpenAI Service
 
-If you've been using Azure OpenAI Studio, all your work, such as your deployments, content filters, batch jobs or fine-tuned models, is still available. All the features and functionality are still here, though the look and feel of some features are updated.
+If you've been using Azure OpenAI Studio, all your work, such as your deployments, content filters, batch jobs or fine-tuned models, is still available in Azure AI Foundry portal. All the features and functionality are still here, though the look and feel of some features are updated.
 
 :::image type="content" source="media/azure-openai-in-ai-studio/studio-home.png" alt-text="Screenshot shows the new Azure OpenAI in Azure AI Foundry portal." lightbox="media/azure-openai-in-ai-studio/studio-home.png":::
 

@@ -38,10 +38,6 @@ sections:
           Can I use models other than ChatGPT in Azure AI Foundry portal? 
         answer: |
           Yes. Azure AI Foundry includes a robust and growing catalog of frontier and open-source models from OpenAI, Hugging Face, Meta and more that can be applied over your data. You can even compare models by task using open-source datasets and evaluate the model with your own test data to see how the pre-trained model would perform to fit your own use case.
-      - question: |
-          How is the playground in Azure AI Foundry portal different from the Azure OpenAI Studio playground? 
-        answer: |
-          The playground experiences in both Azure AI Foundry and Azure OpenAI Studio are similar; however, Azure AI Foundry provides playground experience for models in addition to those provisioned via Azure OpenAI Studio.
       - question: |
           Will there be multiple varying model benchmarks in Azure AI Foundry portal based on individual projects and data sources? 
         answer: |

@@ -740,7 +740,7 @@ result = evaluate(
 
 ## Cloud evaluation on test datasets
 
-After local evaluations of your generative AI applications, you may want to run evaluations in the cloud for pre-deployment testing, and [continuously evaluate](https://aka.ms/GenAIMonitoringDoc) your applications for post-deployment monitoring. Azure AI Projects SDK offers such capabilities via a Python API and supports almost all of the features available in local evaluations. Follow the steps below to submit your evaluation to the cloud on your data using built-in or custom evaluators.
+After local evaluations of your generative AI applications, you might want to run evaluations in the cloud for pre-deployment testing, and [continuously evaluate](https://aka.ms/GenAIMonitoringDoc) your applications for post-deployment monitoring. Azure AI Projects SDK offers such capabilities via a Python API and supports almost all of the features available in local evaluations. Follow the steps below to submit your evaluation to the cloud on your data using built-in or custom evaluators.
 
 ### Prerequisites
 

@@ -307,7 +307,7 @@ for doc in results:
 
 ## Using Azure OpenAI models
 
-If you are using Azure OpenAI service or Azure AI model inference service with OpenAI models with `langchain-azure-ai` package, you may need to use `api_version` parameter to select a specific API version. The following example shows how to connect to an Azure OpenAI model deployment in Azure OpenAI service:
+If you are using Azure OpenAI service or Azure AI model inference service with OpenAI models with `langchain-azure-ai` package, you might need to use `api_version` parameter to select a specific API version. The following example shows how to connect to an Azure OpenAI model deployment in Azure OpenAI service:
 
 ```python
 from langchain_azure_ai.chat_models import AzureAIChatCompletionsModel
@@ -423,7 +423,7 @@ You can configure your application to send telemetry to Azure Application Insigh
 
 ### Configure tracing for Azure AI Foundry
 
-The following code creates a tracer connected to the Azure Application Insights behind a project in Azure AI Foundry. Notice that the parameter `enable_content_recording` is set to `True`. This enables the capture of the inputs and outputs of the entire application as well as the intermediate steps. Such is helpful when debugging and building applications, but you may want to disable it on production environments. It defaults to the environment variable `AZURE_TRACING_GEN_AI_CONTENT_RECORDING_ENABLED`:
+The following code creates a tracer connected to the Azure Application Insights behind a project in Azure AI Foundry. Notice that the parameter `enable_content_recording` is set to `True`. This enables the capture of the inputs and outputs of the entire application as well as the intermediate steps. Such is helpful when debugging and building applications, but you might want to disable it on production environments. It defaults to the environment variable `AZURE_TRACING_GEN_AI_CONTENT_RECORDING_ENABLED`:
 
 ```python
 from langchain_azure_ai.callbacks.tracers import AzureAIInferenceTracer

@@ -166,7 +166,7 @@ You can view the trace of the request along with feedback in Application Insight
 
 ## Advanced usage: export trace to custom OpenTelemetry collector service
 
-In some cases, you may want to export the trace data to your deployed OTel collector service, enabled by setting "OTEL_EXPORTER_OTLP_ENDPOINT". Use this exporter when you want to customize your own span processing logic and your own trace persistent target.
+In some cases, you might want to export the trace data to your deployed OTel collector service, enabled by setting "OTEL_EXPORTER_OTLP_ENDPOINT". Use this exporter when you want to customize your own span processing logic and your own trace persistent target.
 
 ## Related content
 

@@ -86,7 +86,7 @@ To provision an entirely new set of resources, including a new hub and project,
 
 ## Use network isolation
 
-If your Azure AI Foundry project is configured for network isolation you may need to open ports to the internet, For more information, visit [How to configure network isolation](../configure-managed-network.md#scenario-use-visual-studio-code).
+If your Azure AI Foundry project is configured for network isolation you might need to open ports to the internet, For more information, visit [How to configure network isolation](../configure-managed-network.md#scenario-use-visual-studio-code).
 
 ## Remarks
 

@@ -204,12 +204,12 @@ For more information on assigning roles, see [Tutorial: Grant a user access to r
 
 | Resource | Role | Assignee | Description |
 |----------|------|----------|-------------|
-| Azure AI Search | Search Services Contributor | Developer's Microsoft Entra ID | List API-Keys to list indexes from Azure OpenAI Studio. |
+| Azure AI Search | Search Services Contributor | Developer's Microsoft Entra ID | List API-Keys to list indexes from Azure AI Foundry portal. |
 | Azure AI Search | Search Index Data Contributor | Developer's Microsoft Entra ID | Required for the indexing scenario. |
-| Azure AI services/OpenAI | Cognitive Services OpenAI Contributor | Developer's Microsoft Entra ID | Call public ingestion API from Azure OpenAI Studio. |
-| Azure AI services/OpenAI | Cognitive Services Contributor | Developer's Microsoft Entra ID | List API-Keys from Azure OpenAI Studio. |
+| Azure AI services/OpenAI | Cognitive Services OpenAI Contributor | Developer's Microsoft Entra ID | Call public ingestion API from Azure AI Foundry portal. |
+| Azure AI services/OpenAI | Cognitive Services Contributor | Developer's Microsoft Entra ID | List API-Keys from Azure AI Foundry portal. |
 | Azure AI services/OpenAI | Contributor | Developer's Microsoft Entra ID | Allows for calls to the control plane. |
-| Azure Storage Account | Contributor | Developer's Microsoft Entra ID | List Account SAS to upload files from Azure OpenAI Studio. |
+| Azure Storage Account | Contributor | Developer's Microsoft Entra ID | List Account SAS to upload files from Azure AI Foundry portal. |
 | Azure Storage Account | Storage Blob Data Contributor | Developer's Microsoft Entra ID | Needed for developers to read and write to blob storage. |
 | Azure Storage Account | Storage File Data Privileged Contributor | Developer's Microsoft Entra ID | Needed to Access File Share in Storage for Promptflow data. |
 | The resource group or Azure subscription where the developer need to deploy the web app to | Contributor | Developer's Microsoft Entra ID | Deploy web app to the developer's Azure subscription. |

@@ -96,7 +96,7 @@ Recommended System Message Framework:
     - **Define the scope and limitations** of the model's performance by providing clear instructions.
     - **Define the posture and tone** the model should exhibit in its responses.
 - Define the model's output format.
-    - **Define the language and syntax** of the output format. For example, if you want the output to be machine parse-able, you may want tot structure the output to be in JSON, XSON orXML.
+    - **Define the language and syntax** of the output format. For example, if you want the output to be machine parse-able, you might want tot structure the output to be in JSON, XSON orXML.
     - **Define any styling or formatting** preferences for better user readability like bulleting or bolding certain parts of the response
 - Provide examples to demonstrate the intended behavior of the model
     - **Describe difficult use cases** where the prompt is ambiguous or complicated, to give the model more visibility into how to approach such cases.