edit pass: azure-openai-on-your-data

Author: ShawnJackson

articles/ai-services/openai/concepts/use-your-image-data.md

@@ -157,11 +157,11 @@ After you have a Blob Storage container that's populated with image files and at
 
 1. Review the details, and then select **Save and close**.
 
-## Using your ingested data with your GPT-4 Turbo with Vision model
+## Use your ingested data with your GPT-4 Turbo with Vision model
 
 After you connect your data source by using any of the three methods listed earlier, the data ingestion process takes some time to finish. An icon and a **Ingestion in progress** message appear as the process progresses.
 
-After the ingestion finishes, confirm that a data source is created. The details of your data source appear, along with the image search index name.
+After the ingestion finishes, confirm that a data source is created. The details of your data source appear, along with the name of your image search index.
 
 :::image type="content" source="../media/use-your-image-data/completed-data-source.png" alt-text="Screenshot that shows a completed data source ingestion." lightbox="../media/use-your-image-data/completed-data-source.png":::
 

articles/ai-services/openai/how-to/azure-developer-cli.md

@@ -13,7 +13,7 @@ recommendations: false
 
 # Use the Azure Developer CLI to deploy resources for Azure OpenAI On Your Data 
 
-Use this article to learn how to automate resource deployment for Azure OpenAI Service On Your Data. The Azure Developer CLI (`azd`) is an open-source command-line tool that streamlines provisioning and deploying resources to Azure by using a template system. The template contains infrastructure files to provision the necessary Azure OpenAI resources and configurations, and it includes the completed sample app code.
+Use this article to learn how to automate resource deployment for Azure OpenAI Service On Your Data. The Azure Developer CLI (`azd`) is an open-source command-line tool that streamlines provisioning and deploying resources to Azure by using a template system. The template contains infrastructure files to provision the necessary Azure OpenAI resources and configurations. It also includes the completed sample app code.
 
 ## Prerequisites
 
@@ -52,15 +52,15 @@ Use this article to learn how to automate resource deployment for Azure OpenAI S
     azd up
     ```
 
-1. `azd` prompts you for the following information:
+1. The Azure Developer CLI prompts you for the following information:
 
     - `Subscription`: The Azure subscription that your resources are deployed to.
     - `Location`: The Azure region where your resources are deployed.
 
     > [!NOTE]
     > The sample `azd` template uses the `gpt-35-turbo-16k` model. A recommended region for this template is East US, because different Azure regions support different OpenAI models. For more details about model support by region, go to the [Azure OpenAI Service Models](/azure/ai-services/openai/concepts/models) support page.
 
-    The provisioning process might take several minutes to complete. Wait for the task to finish before you proceed to the next steps.
+    The provisioning process might take several minutes. Wait for the task to finish before you proceed to the next steps.
 
 1. Select the link in the `azd` outputs to go to the new resource group in the Azure portal. The following top-level resources should appear:
 
@@ -83,4 +83,4 @@ The `azd` template provisioned all of the required resources for you to chat wit
 
 ## Connect or create an application
 
-After you run the `azd` template and upload your data, you're ready to start using Azure OpenAI On Your Data. See the [quickstart article](../use-your-data-quickstart.md) for code samples that you can use to build your applications.
+After you run the `azd` template and upload your data, you're ready to start using Azure OpenAI On Your Data. For code samples that you can use to build your applications, see the [quickstart article](../use-your-data-quickstart.md).

articles/ai-services/openai/how-to/on-your-data-best-practices.md

@@ -14,7 +14,7 @@ recommendations: false
 
 # Troubleshooting and best practices for Azure OpenAI On Your Data
 
-This article can help guide you through the common problems in developing a solution by using Azure OpenAI Service On Your Data, a feature that allows you to use the power of OpenAI models with your own data. By following the best practices and tips in this article, you can optimize your output with Azure OpenAI On Your Data and achieve the best AI quality possible.
+This article can help guide you through common problems in developing a solution by using Azure OpenAI Service On Your Data, a feature that allows you to use the power of OpenAI models with your own data. By following the best practices and tips in this article, you can optimize your output with Azure OpenAI On Your Data and achieve the best AI quality possible.
 
 ## Azure OpenAI On Your Data: Workflow
 
@@ -24,22 +24,22 @@ The workflow for Azure OpenAI On Your Data has two major parts:
 
   Also in this stage, you can choose an embedding model to use for creation of embeddings or preferred search type. Embeddings are representations of values or objects (like text, images, and audio) that are designed to be consumed by machine learning models and semantic search algorithms.
 
-  The output of this process is an index that will later be used for retrieving documents during inference.
+  The output of this process is an index that will later be used for retrieving documents during inferencing.
 
 * **Inferencing**: This is the stage where users chat with their data by using a studio, a deployed web app, or direct API calls. In this stage, users can set various model parameters (such as `temperature` and `top_P` ) and system parameters (such as `strictness` and `topNDocuments`).
 
 Think of ingestion as a separate process before inferencing. After the index is created, Azure OpenAI On Your Data goes through the following steps to generate a good response to user questions:
 
-1. **Intent generation**: Azure OpenAI On Your Data generates multiple search intents by using user questions and conversation history. It generates multiple search intents to address any ambiguity in the users' questions, add more context by using the conversation history to retrieve holistic information in the retrieval stage, and provide any additional information to make the final response thorough and useful.
+1. **Intent generation**: Azure OpenAI On Your Data generates multiple search intents by using user questions and conversation history. It generates multiple search intents to address any ambiguity in users' questions, add more context by using the conversation history to retrieve holistic information in the retrieval stage, and provide any additional information to make the final response thorough and useful.
 2. **Retrieval**: By using the search type provided during the ingestion, Azure OpenAI On Your Data retrieves a list of relevant document chunks that correspond to each of the search intents.
 3. **Filtration**: Azure OpenAI On Your Data uses the strictness setting to filter out the retrieved documents that are considered irrelevant according to the strictness threshold. The `strictness` parameter controls how aggressive the filtration is.
-4. **Re-ranking**: Azure OpenAI On Your Data re-ranks the remaining document chunks retrieved for each of the search intents. The purpose of re-ranking is to produce a combined list of the most relevant documents retrieved for all search intents.
-5. **Parameter inclusion**: The `topNDocuments` parameter from the re-ranked list is included in the prompt sent to the model, along with the question, the conversation history, and the role information or system message.
+4. **Reranking**: Azure OpenAI On Your Data reranks the remaining document chunks retrieved for each of the search intents. The purpose of reranking is to produce a combined list of the most relevant documents retrieved for all search intents.
+5. **Parameter inclusion**: The `topNDocuments` parameter from the reranked list is included in the prompt sent to the model, along with the question, the conversation history, and the role information or system message.
 6. **Response generation**: The model uses the provided context to generate the final response along with citations.
 
 ## How to structure debugging investigation
 
-When you see an unfavorable response to a query, it might be the result of different outputs from various components not working as expected. You can debug the outputs of each component by using the following steps.
+When you see an unfavorable response to a query, it might be the result of outputs from various components not working as expected. You can debug the outputs of each component by using the following steps.
 
 ### Step 1: Check for retrieval problems
 
@@ -111,7 +111,7 @@ See the preceding debugging process, starting at [step 1](#step-1-check-for-retr
 
 ### Intents are empty or wrong
 
-* Refer to [Step 3](#step-3-check-the-rest-of-the-funnel) in the preceding debugging process.
+* See [Step 3](#step-3-check-the-rest-of-the-funnel) in the preceding debugging process.
 
 * If intents are irrelevant, the problem might be that the intent generation step lacks context. Intent generation considers only the user question and conversation history. It doesn't consider the role information or the document chunks. You might consider adding a prefix to each user question with a short context string to help the intent generation step.
 

articles/ai-services/openai/how-to/use-web-app.md

@@ -23,7 +23,7 @@ Along with Azure OpenAI Studio, APIs, and SDKs, you can use the available standa
 - Publishing creates an Azure App Service instance in your subscription. It might incur costs depending on the [pricing plan](https://azure.microsoft.com/pricing/details/app-service/windows/) that you select. When you're done with your app, you can delete it from the Azure portal.
 - GPT-4 Turbo with Vision models are not supported.
 - By default, the app is deployed with the Microsoft identity provider already configured. The identity provider restricts access to the app to members of your Azure tenant. To add or modify authentication:
-    1. Go to the [Azure portal](https://portal.azure.com/#home) and search for the app name that you specified during publishing. Select the web app, and then select **Authentication** on the left menu. Then select **Add an identity provider**.
+    1. Go to the [Azure portal](https://portal.azure.com/#home) and search for the app name that you specified during publishing. Select the web app, and then select **Authentication** on the left menu. Then select **Add identity provider**.
 
         :::image type="content" source="../media/quickstarts/web-app-authentication.png" alt-text="Screenshot of the authentication pane in the Azure portal." lightbox="../media/quickstarts/web-app-authentication.png":::
 
@@ -55,7 +55,7 @@ We recommend pulling changes from the `main` branch for the web app's source cod
 If you haven't customized the web app, you can use these steps to synchronize it:
 
 1. Go to your web app in the [Azure portal](https://portal.azure.com/).
-1. On the left menu, under **Deployment**, select **Deployment center**.
+1. On the left menu, under **Deployment**, select **Deployment Center**.
 1. Select **Sync** at the top of the pane, and confirm that the app will be redeployed.
 
     :::image type="content" source="../media/use-your-data/sync-app.png" alt-text="A screenshot of the web app synchronization button on the Azure portal." lightbox="../media/use-your-data/sync-app.png":::
@@ -74,9 +74,9 @@ To turn on chat history, deploy or redeploy your model as a web app by using [Az
 :::image type="content" source="../media/use-your-data/enable-chat-history.png" alt-text="Screenshot of the checkbox for enabling chat history in Azure OpenAI Studio." lightbox="../media/use-your-data/enable-chat-history.png":::
 
 > [!IMPORTANT]
-> Turning on chat history creates a [Cosmos DB](/azure/cosmos-db/introduction) instance in your resource group, and it incurs [additional charges](https://azure.microsoft.com/pricing/details/cosmos-db/autoscale-provisioned/) for the storage that you use.
+> Turning on chat history creates an [Azure Cosmos DB](/azure/cosmos-db/introduction) instance in your resource group, and it incurs [additional charges](https://azure.microsoft.com/pricing/details/cosmos-db/autoscale-provisioned/) for the storage that you use.
 
-After you turn on chat history, your users can show and hide it in the upper-right corner of the app. When users show chat history, they can rename or delete conversations. Because they're signed in to the app, conversations are automatically ordered from newest to oldest. Conversations are named based on the first query in the conversation.
+After you turn on chat history, your users can show and hide it in the upper-right corner of the app. When users show chat history, they can rename or delete conversations. Because the users are signed in to the app, conversations are automatically ordered from newest to oldest. Conversations are named based on the first query in the conversation.
 
 :::image type="content" source="../media/use-your-data/web-app-chat-history.png" alt-text="Screenshot of the chat history in the web app." lightbox="../media/use-your-data/web-app-chat-history.png":::