Merge pull request #1039 from eric-urban/eur/ai-studio-scrub

v-dirichards · web-flow · commit 56d7978221cf · 2024-10-25T13:52:17.000-05:00
AI Studio refresh
diff --git a/articles/search/index.yml b/articles/search/index.yml
@@ -68,7 +68,7 @@ landingContent:
         links:
           - text: Create a vector index in AI Studio
             url: /azure/ai-studio/how-to/index-add
-          - text: Chat with your data in Azure OpenAI Studio
+          - text: Chat with your data using Azure OpenAI
             url: /azure/ai-services/openai/use-your-data-quickstart
           - text: Build a question and answer copilot
             url: /azure/ai-studio/tutorials/deploy-copilot-ai-studio
diff --git a/articles/search/retrieval-augmented-generation-overview.md b/articles/search/retrieval-augmented-generation-overview.md
@@ -37,7 +37,7 @@ Azure AI Search is a [proven solution for information retrieval](/azure/develope
 Microsoft has several built-in implementations for using Azure AI Search in a RAG solution.
 
 + Azure AI Studio, [use a vector index and retrieval augmentation](/azure/ai-studio/concepts/retrieval-augmented-generation). 
-+ Azure OpenAI Studio, [use a search index with or without vectors](/azure/ai-services/openai/concepts/use-your-data).
++ Azure OpenAI, [use a search index with or without vectors](/azure/ai-services/openai/concepts/use-your-data).
 + Azure Machine Learning, [use a search index as a vector store in a prompt flow](/azure/machine-learning/how-to-create-vector-index).
 
 Curated approaches make it simple to get started, but for more control over the architecture, you need a custom solution. These templates create end-to-end solutions in:
@@ -77,7 +77,7 @@ The information retrieval system provides the searchable index, query logic, and
 
 The LLM receives the original prompt, plus the results from Azure AI Search. The LLM analyzes the results and formulates a response. If the LLM is ChatGPT, the user interaction might be a back and forth conversation. If you're using Davinci, the prompt might be a fully composed answer. An Azure solution most likely uses Azure OpenAI, but there's no hard dependency on this specific service.
 
-Azure AI Search doesn't provide native LLM integration for prompt flows or chat preservation, so you need to write code that handles orchestration and state. You can review demo source ([Azure-Samples/azure-search-openai-demo](https://github.com/Azure-Samples/azure-search-openai-demo)) for a blueprint of what a full solution entails. We also recommend Azure AI Studio or [Azure OpenAI Studio](/azure/ai-services/openai/use-your-data-quickstart) to create RAG-based Azure AI Search solutions that integrate with LLMs.
+Azure AI Search doesn't provide native LLM integration for prompt flows or chat preservation, so you need to write code that handles orchestration and state. You can review demo source ([Azure-Samples/azure-search-openai-demo](https://github.com/Azure-Samples/azure-search-openai-demo)) for a blueprint of what a full solution entails. We also recommend [Azure AI Studio](/azure/ai-studio/concepts/retrieval-augmented-generation) to create RAG-based Azure AI Search solutions that integrate with LLMs.
 
 ## Searchable content in Azure AI Search
 
diff --git a/articles/search/search-try-for-free.md b/articles/search/search-try-for-free.md
@@ -122,9 +122,9 @@ Try the portal quickstarts for Azure AI Search or quickstarts that use Visual St
 - [Quickstart: Generative search (RAG) using a Python client](search-get-started-rag.md)
 - [Quickstart: Vector search using a REST client](search-get-started-vector.md)
 
-Azure AI Studio and Azure OpenAI Studio support connecting to content in Azure AI Search
+Azure AI Studio supports connecting to content in Azure AI Search.
 
-- [Quickstart: Chat using your own data in Azure OpenAI Studio](/azure/ai-services/openai/use-your-data-quickstart)
+- [Quickstart: Chat using your own data with Azure OpenAI](/azure/ai-services/openai/use-your-data-quickstart)
 - [Tutorial: Build a custom chat app with the prompt flow SDK](/azure/ai-studio/tutorials/copilot-sdk-create-resources)
 
 Developers should review [azure-search-vector-samples](https://github.com/Azure/azure-search-vector-samples) repository or the solution accelerators. You can deploy and run any of these samples using the Azure trial subscription. 
diff --git a/articles/search/service-configure-firewall.md b/articles/search/service-configure-firewall.md
@@ -133,7 +133,7 @@ The trusted service list for Azure AI Search includes:
 + `Microsoft.CognitiveServices` for Azure OpenAI and Azure AI services
 + `Microsoft.MachineLearningServices` for Azure Machine Learning
 
-Workflows for this network exception are requests originating *from* Azure AI Studio, Azure OpenAI Studio, or other AML features *to* Azure AI Search, typically in [Azure OpenAI On Your Data](/azure/ai-services/openai/concepts/use-your-data) scenarios for retrieval augmented generation (RAG) and playground environments.
+Workflows for this network exception are requests originating from Azure AI Studio or other AML features to Azure AI Search. The trusted services exception is typically for [Azure OpenAI On Your Data](/azure/ai-services/openai/concepts/use-your-data) scenarios for retrieval augmented generation (RAG) and playground environments.
 
 ### Trusted resources must have a managed identity
 
diff --git a/articles/search/service-create-private-endpoint.md b/articles/search/service-create-private-endpoint.md
@@ -21,7 +21,7 @@ This article explains how to configure a private connection to Azure AI Search s
 + [Create an Azure virtual machine in the same virtual network](#create-a-virtual-machine)
 + [Test using a browser session on the virtual machine](#connect-to-the-vm)
 
-Other Azure resources that might privately connect to Azure AI Search include Azure OpenAI for "use your own data" scenarios. Azure OpenAI Studio doesn't run in a virtual network, but it can be configured on the backend to send requests over the Microsoft backbone network. Configuration for this traffic pattern is enabled by Microsoft when your request is submitted and approved. For this scenario:
+Other Azure resources that might privately connect to Azure AI Search include Azure OpenAI for "use your own data" scenarios. Azure AI Studio doesn't run in a virtual network, but it can be configured on the backend to send requests over the Microsoft backbone network. Configuration for this traffic pattern is enabled by Microsoft when your request is submitted and approved. For this scenario:
 
 + Follow the instructions in this article to set up the private endpoint.
 + [Enable trusted service](/azure/ai-services/openai/how-to/use-your-data-securely#enable-trusted-service-1) of your search resource from the Azure portal.
diff --git a/articles/search/tutorial-rag-build-solution-models.md b/articles/search/tutorial-rag-build-solution-models.md
@@ -2,14 +2,13 @@
 title: 'RAG tutorial: Set up models'
 titleSuffix: Azure AI Search
 description: Set up an embedding model and chat model for generative search (RAG).
-
 manager: nitinme
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
 ms.topic: tutorial
 ms.custom: references_regions
-ms.date: 10/04/2024
+ms.date: 10/25/2024
 
 ---
 
@@ -34,7 +33,7 @@ If you don't have an Azure subscription, create a [free account](https://azure.m
 
 - An **Owner** or **User Access Administrator** role on your Azure subscription, necessary for creating role assignments. You use at least three Azure resources in this tutorial. The connections are authenticated using Microsoft Entra ID, which requires the ability to create roles. Role assignments for connecting to models are documented in this article. If you can't create roles, you can use [API keys](search-security-api-keys.md) instead.
 
-- A model provider, such as [Azure OpenAI](/azure/ai-services/openai/how-to/create-resource), Azure AI Vision via an [Azure AI multi-service account](/azure/ai-services/multi-service-resource), or [Azure AI Studio](https://ai.azure.com/).
+- A model provider, such as [Azure OpenAI](/azure/ai-services/openai/how-to/create-resource), Azure AI Vision via an [Azure AI services multi-service resource](/azure/ai-services/multi-service-resource), or [Azure AI Studio](https://ai.azure.com/).
 
   We use Azure OpenAI in this tutorial. Other providers are listed so that you know your options for integrated vectorization.
 
@@ -103,7 +102,7 @@ This tutorial series uses the following models and model providers:
 
 You must have [**Cognitive Services OpenAI Contributor**]( /azure/ai-services/openai/how-to/role-based-access-control#cognitive-services-openai-contributor) or higher to deploy models in Azure OpenAI.
 
-1. Go to [Azure OpenAI Studio](https://oai.azure.com/).
+1. Go to [Azure AI Studio](https://ai.azure.com/).
 
 1. Select **Deployments** on the left menu.
 
diff --git a/articles/search/vector-search-integrated-vectorization.md b/articles/search/vector-search-integrated-vectorization.md
@@ -63,7 +63,7 @@ For text-to-vector conversion during queries, you take a dependency on these com
     | [AzureOpenAIEmbedding skill](cognitive-search-skill-azure-openai-embedding.md) | [Azure OpenAI vectorizer](vector-search-vectorizer-azure-open-ai.md) |
     | [Custom skill](cognitive-search-custom-skill-web-api.md) | [Custom Web API vectorizer](vector-search-vectorizer-custom-web-api.md) |
     | [Azure AI Vision skill (preview)](cognitive-search-skill-vision-vectorize.md)  | [Azure AI Vision vectorizer](vector-search-vectorizer-ai-services-vision.md) |
-    | [AML skill pointing to the model catalog in Azure AI Studio (preview)](cognitive-search-aml-skill.md) | [Azure AI Studio model catalog vectorizer](vector-search-vectorizer-azure-machine-learning-ai-studio-catalog.md) |
+    | [AML skill pointing to the model catalog in Azure AI Studio](cognitive-search-aml-skill.md) | [Azure AI Studio model catalog vectorizer](vector-search-vectorizer-azure-machine-learning-ai-studio-catalog.md) |
 
 ## Component diagram
 
diff --git a/articles/search/vector-search-overview.md b/articles/search/vector-search-overview.md
@@ -74,7 +74,7 @@ Vector search is available in:
 + [Azure portal: Import and vectorize data wizard](search-get-started-portal-import-vectors.md)
 + [Azure REST APIs](/rest/api/searchservice/operation-groups)
 + [Azure SDKs for .NET](https://www.nuget.org/packages/Azure.Search.Documents), [Python](https://pypi.org/project/azure-search-documents), and [JavaScript](https://www.npmjs.com/package/@azure/search-documents)
-+ Other Azure offerings such as Azure AI Studio and Azure OpenAI Studio.
++ Other Azure offerings such as Azure AI Studio.
 
 > [!NOTE]
 > Some older search services created before January 1, 2019 are deployed on infrastructure that doesn't support vector workloads. If you try to add a vector field to a schema and get an error, it's a result of outdated services. In this situation, you must create a new search service to try out the vector feature.
@@ -85,7 +85,7 @@ Azure AI Search is deeply integrated across the Azure AI platform. The following
 
 | Product | Integration |
 |---------|-------------|
-| Azure OpenAI Studio | In the chat with your data playground, **Add your own data** uses Azure AI Search for grounding data and conversational search. This is the easiest and fastest approach for chatting with your data. |
+| Azure AI Studio | In the chat with your data playground, **Add your own data** uses Azure AI Search for grounding data and conversational search. This is the easiest and fastest approach for chatting with your data. |
 | Azure OpenAI | Azure OpenAI provides embedding models and chat models. Demos and samples target the [text-embedding-ada-002](/azure/ai-services/openai/concepts/models#embeddings-models). We recommend Azure OpenAI for generating embeddings for text. |
 | Azure AI Services | [Image Retrieval Vectorize Image API(Preview)](/azure/ai-services/computer-vision/how-to/image-retrieval#call-the-vectorize-image-api) supports vectorization of image content. We recommend this API for generating embeddings for images. |
 | Azure data platforms: Azure Blob Storage, Azure Cosmos DB | You can use [indexers](search-indexer-overview.md) to automate data ingestion, and then use [integrated vectorization](vector-search-integrated-vectorization.md) to generate embeddings. Azure AI Search can automatically index vector data from two data sources: [Azure blob indexers](search-howto-indexing-azure-blob-storage.md) and [Azure Cosmos DB for NoSQL indexers](search-howto-index-cosmosdb.md). For more information, see [Add vector fields to a search index.](vector-search-how-to-create-index.md). |
diff --git a/articles/search/vector-search-vectorizer-azure-machine-learning-ai-studio-catalog.md b/articles/search/vector-search-vectorizer-azure-machine-learning-ai-studio-catalog.md
@@ -18,7 +18,7 @@ ms.date: 08/05/2024
 
 The **Azure AI Studio model catalog** vectorizer connects to an embedding model that was deployed via [the Azure AI Studio model catalog](/azure/ai-studio/how-to/model-catalog) to an Azure Machine Learning endpoint. Your data is processed in the [Geo](https://azure.microsoft.com/explore/global-infrastructure/data-residency/) where your model is deployed. 
 
-If you used integrated vectorization to create the vector arrays, the skillset should include an [AML skill pointing to the model catalog in Azure AI Studio (preview)](cognitive-search-aml-skill.md).
+If you used integrated vectorization to create the vector arrays, the skillset should include an [AML skill pointing to the model catalog in Azure AI Studio](cognitive-search-aml-skill.md).
 
 ## Vectorizer parameters
 
