Merge pull request #845 from eric-urban/eur/ai-search-patch-10-16

clarify requirement for embedding skill integration

Author: prmerger-automator[bot]

articles/search/cognitive-search-skill-azure-openai-embedding.md

@@ -16,15 +16,16 @@ ms.date: 10/16/2024
 
 The **Azure OpenAI Embedding** skill connects to a deployed embedding model on your [Azure OpenAI](/azure/ai-services/openai/overview) resource to generate embeddings during indexing. Your data is processed in the [Geo](https://azure.microsoft.com/explore/global-infrastructure/data-residency/) where your model is deployed. 
 
+## Prerequisites
+
 Your Azure OpenAI Service must have an associated [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains). If the service was created through the Azure portal, this subdomain is automatically generated as part of your service setup. Ensure that your service includes a custom subdomain before using it with the Azure AI Search integration.
 
-Note that Azure OpenAI models created with an AI Studio service account are not supported. Only models from the Azure OpenAI Service are compatible with this integration. 
+Azure OpenAI Service resources (with access to embedding models) that were created in AI Studio aren't supported. Only the Azure OpenAI Service resources created in the Azure portal are compatible with the **Azure OpenAI Embedding** skill integration.
 
 The [Import and vectorize data wizard](search-get-started-portal-import-vectors.md) in the Azure portal uses the **Azure OpenAI Embedding** skill to vectorize content. You can run the wizard and review the generated skillset to see how the wizard builds the skill for embedding models. 
 
 > [!NOTE]
 > This skill is bound to Azure OpenAI and is charged at the existing [Azure OpenAI pay-as-you go price](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/#pricing).
->
 
 ## @odata.type  
 

articles/search/search-get-started-portal-import-vectors.md

@@ -2,7 +2,6 @@
 title: "Quickstart: Vectorize text and images by using the Azure portal"
 titleSuffix: Azure AI Search
 description: Use a wizard to automate data chunking and vectorization in a search index.
-
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
@@ -49,7 +48,7 @@ Key points about the wizard:
 
 If using the Azure OpenAI Service, it must have an associated [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains). If the service was created through the Azure portal, this subdomain is automatically generated as part of your service setup. Ensure that your service includes a custom subdomain before using it with the Azure AI Search integration.
 
-Note that Azure OpenAI models created with an AI Studio service account are not supported. Only models from the Azure OpenAI Service are compatible with the Azure OpenAI integration. 
+Azure OpenAI Service resources (with access to embedding models) that were created in AI Studio aren't supported. Only the Azure OpenAI Service resources created in the Azure portal are compatible with the **Azure OpenAI Embedding** skill integration.
 
 ### Public endpoint requirements
 

articles/search/vector-search-vectorizer-azure-open-ai.md

@@ -2,8 +2,9 @@
 title: Azure OpenAI vectorizer
 titleSuffix: Azure AI Search
 description: Connects to a deployed model on your Azure OpenAI resource at query time.
-author: careyjmac
-ms.author: chalton
+author: HeidiSteen
+ms.author: heidist
+ms.reviewer: chalton
 ms.service: azure-ai-search
 ms.custom:
   - build-2024
@@ -15,10 +16,6 @@ ms.date: 10/16/2024
 
 The **Azure OpenAI** vectorizer connects to a deployed embedding model on your [Azure OpenAI](/azure/ai-services/openai/overview) resource to generate embeddings at query time. Your data is processed in the [Geo](https://azure.microsoft.com/explore/global-infrastructure/data-residency/) where your model is deployed. 
 
-Your Azure OpenAI Service must have an associated [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains). If the service was created through the Azure portal, this subdomain is automatically generated as part of your service setup. Ensure that your service includes a custom subdomain before using it with the Azure AI Search integration.
-
-Note that Azure OpenAI models created with an AI Studio service account are not supported. Only models from the Azure OpenAI Service are compatible with this integration. 
-
 Vectorizers are used at query time, but specified in index definitions, and referenced on vector fields through a vector profile. The Azure OpenAI vectorizer is called `AzureOpenAIVectorizer` in the API. 
 
 + Use the [**2024-07-01**](/rest/api/searchservice/indexes/create) REST API or an Azure SDK package that's been updated to provide the feature.
@@ -27,7 +24,12 @@ Vectorizers are used at query time, but specified in index definitions, and refe
 
 > [!NOTE]
 > This vectorizer is bound to Azure OpenAI and is charged at the existing [Azure OpenAI pay-as-you go price](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/#pricing).
->
+
+## Prerequisites
+
+Your Azure OpenAI Service must have an associated [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains). If the service was created through the Azure portal, this subdomain is automatically generated as part of your service setup. Ensure that your service includes a custom subdomain before using it with the Azure AI Search integration.
+
+Azure OpenAI Service resources (with access to embedding models) that were created in AI Studio aren't supported. Only the Azure OpenAI Service resources created in the Azure portal are compatible with the **Azure OpenAI Embedding** skill integration. 
 
 ## Vectorizer parameters