Merge pull request #6959 from haileytap/quickstarts

v-shils · web-flow · commit 83ad51c30538 · 2025-09-05T12:14:15.000-07:00
[Azure Search] Refactor Python pivot for AR quickstart
diff --git a/articles/search/includes/quickstarts/agentic-retrieval-csharp.md b/articles/search/includes/quickstarts/agentic-retrieval-csharp.md
@@ -16,7 +16,7 @@ Although you can provide your own data, this quickstart uses [sample JSON docume
 To get started with a Jupyter notebook instead, see the [Azure-Samples/azure-search-dotnet-samples](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-agentic-retrieval) repository on GitHub.
 
 > [!TIP]
-> The C# version of this quickstart uses the 2025-05-01-preview REST API version, which doesn't support knowledge sources and other agentic retrieval features introduced in the 2025-08-01-preview. To use these features, see the REST version of this quickstart.
+> The C# version of this quickstart uses the 2025-05-01-preview REST API version, which doesn't support knowledge sources and other agentic retrieval features introduced in the 2025-08-01-preview. To use these features, see the REST or Python version.
 
 ## Prerequisites
 
diff --git a/articles/search/includes/quickstarts/agentic-retrieval-java.md b/articles/search/includes/quickstarts/agentic-retrieval-java.md
@@ -14,7 +14,7 @@ In this quickstart, you use [agentic retrieval](../../search-agentic-retrieval-c
 Although you can provide your own data, this quickstart uses [sample JSON documents](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/nasa-e-book/earth-at-night-json) from NASA's Earth at Night e-book. The documents describe general science topics and images of Earth at night as observed from space.
 
 > [!TIP]
-> The Java version of this quickstart uses the 2025-05-01-preview REST API version, which doesn't support knowledge sources and other agentic retrieval features introduced in the 2025-08-01-preview. To use these features, see the REST version of this quickstart.
+> The Java version of this quickstart uses the 2025-05-01-preview REST API version, which doesn't support knowledge sources and other agentic retrieval features introduced in the 2025-08-01-preview. To use these features, see the REST or Python version.
 
 ## Prerequisites
 
diff --git a/articles/search/includes/quickstarts/agentic-retrieval-javascript.md b/articles/search/includes/quickstarts/agentic-retrieval-javascript.md
@@ -14,7 +14,7 @@ In this quickstart, you use [agentic retrieval](../../search-agentic-retrieval-c
 Although you can provide your own data, this quickstart uses [sample JSON documents](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/nasa-e-book/earth-at-night-json) from NASA's Earth at Night e-book. The documents describe general science topics and images of Earth at night as observed from space.
 
 > [!TIP]
-> The JavaScript version of this quickstart uses the 2025-05-01-preview REST API version, which doesn't support knowledge sources and other agentic retrieval features introduced in the 2025-08-01-preview. To use these features, see the REST version of this quickstart.
+> The JavaScript version of this quickstart uses the 2025-05-01-preview REST API version, which doesn't support knowledge sources and other agentic retrieval features introduced in the 2025-08-01-preview. To use these features, see the REST or Python version.
 
 ## Prerequisites
 
diff --git a/articles/search/includes/quickstarts/agentic-retrieval-python.md b/articles/search/includes/quickstarts/agentic-retrieval-python.md
diff --git a/articles/search/includes/quickstarts/agentic-retrieval-rest.md b/articles/search/includes/quickstarts/agentic-retrieval-rest.md
@@ -9,9 +9,9 @@ ms.date: 08/26/2025
 
 [!INCLUDE [Feature preview](../previews/preview-generic.md)]
 
-In this quickstart, you use [agentic retrieval](../../search-agentic-retrieval-concept.md) to create a conversational search experience powered by documents indexed in Azure AI Search and large language models (LLMs) from Azure AI Foundry Models.
+In this quickstart, you use [agentic retrieval](../../search-agentic-retrieval-concept.md) to create a conversational search experience powered by documents indexed in Azure AI Search and large language models (LLMs) from Azure OpenAI in Azure AI Foundry Models.
 
-A *knowledge agent* orchestrates agentic retrieval by decomposing complex queries into subqueries, running the subqueries against one or more *knowledge sources*, and returning results with metadata. By default, the agent outputs raw content from your sources, but this quickstart passes the output to an LLM for natural-language answer generation.
+A *knowledge agent* orchestrates agentic retrieval by decomposing complex queries into subqueries, running the subqueries against one or more *knowledge sources*, and returning results with metadata. By default, the agent outputs raw content from your sources, but this quickstart uses the answer synthesis modality for natural-language answer generation.
 
 Although you can provide your own data, this quickstart uses [sample JSON documents](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/nasa-e-book/earth-at-night-json) from NASA's Earth at Night e-book. The documents describe general science topics and images of Earth at night as observed from space.
 
@@ -34,7 +34,7 @@ Although you can provide your own data, this quickstart uses [sample JSON docume
 
 ## Connect from your local system
 
-You configured role-based access to interact with Azure AI Search and Azure AI Foundry. From the command line, use the Azure CLI to sign in to the same subscription and tenant for both resources. For more information, see [Quickstart: Connect without keys](../../search-get-started-rbac.md).
+You configured role-based access to interact with Azure AI Search and Azure OpenAI in Azure AI Foundry. From the command line, use the Azure CLI to sign in to the same subscription and tenant for both resources. For more information, see [Quickstart: Connect without keys](../../search-get-started-rbac.md).
 
 To connect from your local system:
 
@@ -56,7 +56,7 @@ To connect from your local system:
 
 ## Load connections
 
-Before you send any requests, define endpoints, credentials, and deployment details for connections to Azure AI Search and Azure AI Foundry. These values are used in the following sections.
+Before you send any requests, define endpoints, credentials, and deployment details for connections to Azure AI Search and Azure OpenAI in Azure AI Foundry. These values are used in the following sections.
 
 To load the connections:
 
@@ -95,7 +95,7 @@ To load the connections:
 
 In Azure AI Search, an index is a structured collection of data. Use [Indexes - Create (REST API)](/rest/api/searchservice/indexes/create) to define an index named `earth-at-night`, which you previously specified using the `@index-name` variable.
 
-The index schema contains fields for document identification and page content, embeddings, and numbers. The schema also includes configurations for semantic ranking and vector search, which uses your `text-embedding-3-large` deployment to vectorize text and match documents based on semantic or conceptual similarity.
+The index schema contains fields for document identification and page content, embeddings, and numbers. The schema also includes configurations for semantic ranking and vector search, which uses your `text-embedding-3-large` deployment to vectorize text and match documents based on semantic similarity.
 
 ```HTTP
 ### Create an index
@@ -299,7 +299,7 @@ POST {{search-url}}/agents('{{knowledge-agent-name}}')/retrieve?api-version={{ap
 
 The output should be similar to the following JSON, where:
 
-+ `response` provides a synthesized, LLM-generated answer to the query based on the retrieved documents. When answer synthesis isn't enabled, this section contains content extracted directly from the documents.
++ `response` provides a synthesized, LLM-generated answer to the query that cites the retrieved documents. When answer synthesis isn't enabled, this section contains content extracted directly from the documents.
 
 + `activity` tracks the steps that were taken during the retrieval process, including the subqueries generated by your `gpt-4.1-mini` deployment and the tokens used for semantic ranking, query planning, and answer synthesis.
 
@@ -399,7 +399,9 @@ The output should be similar to the following JSON, where:
 
 When you work in your own subscription, it's a good idea to finish a project by determining whether you still need the resources you created. Resources that are left running can cost you money.
 
-Run the following code to delete the objects you created in this quickstart.
+In the [Azure portal](https://portal.azure.com/), you can manage your Azure AI Search and Azure AI Foundry resources by selecting **All resources** or **Resource groups** from the left pane.
+
+Otherwise, run the following code to delete the objects you created in this quickstart.
 
 <!-- You can delete resources individually or delete the entire resource group.
 
diff --git a/articles/search/includes/quickstarts/agentic-retrieval-typescript.md b/articles/search/includes/quickstarts/agentic-retrieval-typescript.md
@@ -14,7 +14,7 @@ In this quickstart, you use [agentic retrieval](../../search-agentic-retrieval-c
 Although you can provide your own data, this quickstart uses [sample JSON documents](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/nasa-e-book/earth-at-night-json) from NASA's Earth at Night e-book. The documents describe general science topics and images of Earth at night as observed from space.
 
 > [!TIP]
-> The TypeScript version of this quickstart uses the 2025-05-01-preview REST API version, which doesn't support knowledge sources and other agentic retrieval features introduced in the 2025-08-01-preview. To use these features, see the REST version of this quickstart.
+> The TypeScript version of this quickstart uses the 2025-05-01-preview REST API version, which doesn't support knowledge sources and other agentic retrieval features introduced in the 2025-08-01-preview. To use these features, see the REST or Python version.
 
 ## Prerequisites
 
diff --git a/articles/search/includes/quickstarts/search-get-started-rbac-python.md b/articles/search/includes/quickstarts/search-get-started-rbac-python.md
@@ -42,7 +42,7 @@ To sign in:
 ## Connect to Azure AI Search
 
 > [!NOTE]
-> This section illustrates the basic Python pattern for keyless connections. For comprehensive guidance, see a specific quickstart or tutorial, such as [Quickstart: Run agentic retrieval in Azure AI Search](../../search-get-started-agentic-retrieval.md).
+> This section illustrates the basic Python pattern for keyless connections. For comprehensive guidance, see a specific quickstart or tutorial, such as [Quickstart: Use agentic retrieval in Azure AI Search](../../search-get-started-agentic-retrieval.md).
 
 You can use Python notebooks in Visual Studio Code to send requests to your Azure AI Search service. For request authentication, use the `DefaultAzureCredential` class from the Azure Identity library.
 
diff --git a/articles/search/includes/quickstarts/search-get-started-rbac-rest.md b/articles/search/includes/quickstarts/search-get-started-rbac-rest.md
@@ -58,7 +58,7 @@ To get your token:
 ## Connect to Azure AI Search
 
 > [!NOTE]
-> This section illustrates the basic REST pattern for keyless connections. For comprehensive guidance, see a specific quickstart or tutorial, such as [Quickstart: Run agentic retrieval in Azure AI Search](../../search-get-started-agentic-retrieval.md).
+> This section illustrates the basic REST pattern for keyless connections. For comprehensive guidance, see a specific quickstart or tutorial, such as [Quickstart: Use agentic retrieval in Azure AI Search](../../search-get-started-agentic-retrieval.md).
 
 You can use the REST Client extension in Visual Studio Code to send requests to your Azure AI Search service. For request authentication, include an `Authorization` header with the Microsoft Entra ID token you previously generated.
 
diff --git a/articles/search/samples-dotnet.md b/articles/search/samples-dotnet.md
@@ -52,7 +52,7 @@ Code samples from the Azure AI Search team demonstrate features and workflows. A
 |-------------|------------------|---------|
 | [create-mvc-app](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/create-mvc-app) |  [Tutorial: Add search to an ASP.NET Core (MVC) app](tutorial-csharp-create-mvc-app.md) | While most samples are console applications, this MVC sample uses a web page to front the sample Hotels index, demonstrating basic search, pagination, and other server-side behaviors.|
 | [quickstart](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart/AzureSearchQuickstart) | [Quickstart: Full-text search](search-get-started-text.md) | Covers the basic workflow for creating, loading, and querying a search index in C# using sample data. |
-| [quickstart-agentic-retrieval](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-agentic-retrieval) | [Quickstart: Run agentic retrieval in Azure AI Search](search-get-started-agentic-retrieval.md) | Creates a knowledge agent in Azure AI Search to integrate LLM reasoning into query planning. |
+| [quickstart-agentic-retrieval](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-agentic-retrieval) | [Quickstart: Run agentic retrieval in Azure AI Search](search-get-started-agentic-retrieval.md) | Creates a retrieval pipeline that integrates semantic ranking in Azure AI Search with LLM-powered query planning and answer generation. |
 | [quickstart-rag](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-rag) | [Quickstart: Generative search (RAG)](search-get-started-rag.md) | Uses grounding data from Azure AI Search with a chat completion model from Azure OpenAI. |
 | [quickstart-semantic-search](https://github.com/Azure-Samples/azure-search-dotnet-samples/blob/main/quickstart-semantic-search/) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Shows the index schema and query request for invoking semantic ranker. |
 | [quickstart-vector-search](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-vector-search) | [Quickstart: Vector search](search-get-started-vector.md) | Covers the basic workflow for indexing and querying vector data. |
diff --git a/articles/search/samples-python.md b/articles/search/samples-python.md
@@ -37,7 +37,7 @@ Code samples from the Azure AI Search team demonstrate features and workflows. M
 | Samples | Article |
 |---------|---------|
 | [Quickstart](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart) | Source code for the Python portion of [Quickstart: Full-text search](search-get-started-text.md). This sample covers the basic workflow for creating, loading, and querying a search index using sample data. |
-| [Quickstart-Agentic-Retrieval](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Agentic-Retrieval) | Source code for the Python portion of [Quickstart: Run agentic retrieval in Azure AI Search](search-get-started-agentic-retrieval.md). |
+| [Quickstart-Agentic-Retrieval](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Agentic-Retrieval) | Source code for the Python portion of [Quickstart: Run agentic retrieval in Azure AI Search](search-get-started-agentic-retrieval.md). This sample creates a retrieval pipeline that integrates semantic ranking in Azure AI Search with LLM-powered query planning and answer generation. |
 | [Quickstart-RAG](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-RAG) | Source code for the Python portion of [Quickstart: Generative search (RAG) with grounding data from Azure AI Search](search-get-started-rag.md). |
 | [Quickstart-Semantic-Search](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Semantic-Search) | Source code for the Python portion of [Quickstart: Semantic ranking](search-get-started-semantic.md). This sample shows the index schema and query request for invoking semantic ranker. |
 | [Quickstart-Vector-Search](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Vector-Search) | Source code for the Python portion of [Quickstart: Vector search](search-get-started-vector.md). Covers the basic workflow for indexing and querying vector data. |
diff --git a/articles/search/samples-rest.md b/articles/search/samples-rest.md
@@ -28,7 +28,7 @@ Code samples from the Azure AI Search team demonstrate features and workflows. M
 |---------|---------|
 | [quickstart](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart) | Source code for the REST portion of [Quickstart: Full-text search](search-get-started-text.md). This sample covers the basic workflow for creating, loading, and querying a search index using sample data. |
 | [quickstart-vectors](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-vectors) | Source code for [Quickstart: Vector search using REST APIs](search-get-started-vector.md). This sample covers the basic workflow for indexing and querying vector data. |
-| [quickstart-agentic-retrieval](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-agentic-retrieval) | Source code for the REST portion of [Quickstart: Run agentic retrieval in Azure AI Search](search-get-started-agentic-retrieval.md). This sample shows you how to create a knowledge agent in Azure AI Search to integrate LLM reasoning into query planning. |
+| [quickstart-agentic-retrieval](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Quickstart-agentic-retrieval) | Source code for the REST portion of [Quickstart: Run agentic retrieval in Azure AI Search](search-get-started-agentic-retrieval.md). This sample creates a retrieval pipeline that integrates semantic ranking in Azure AI Search with LLM-powered query planning and answer generation. |
 | [skillset-tutorial](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/skillset-tutorial) | Source code for [Tutorial: Use REST and AI to generate searchable content from Azure blobs](tutorial-skillset.md). This sample shows you how to create a skillset that iterates over Azure blobs to extract information and infer structure.|
 | [skill examples](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/skill-examples) | Skillset examples in indexer pipelines that include indexes and indexers so that you can follow field mappings, output field mappings, and source paths. |
 | [debug-sessions](https://github.com/Azure-Samples/azure-search-rest-samples/tree/main/Debug-sessions) | Source code for [Tutorial: Diagnose, repair, and commit changes to your skillset](cognitive-search-tutorial-debug-sessions.md). This sample shows you how to use a skillset debug session in the Azure portal. REST is used to create the objects used during debug.|
