@@ -30,7 +30,7 @@
             "redirect_url": "/azure/search/search-get-started-skillset",
             "redirect_document_id": true
         },
-                {
+        {
             "source_path_from_root": "/articles/search/cognitive-search-tutorial-blob.md",
             "redirect_url": "/azure/search/tutorial-skillset",
             "redirect_document_id": true
@@ -595,6 +595,51 @@
             "source_path_from_root": "/articles/search/search-how-to-index-logic-apps-indexers.md",
             "redirect_url": "/azure/search/search-how-to-index-logic-apps",
             "redirect_document_id": true
+        },
+        {
+            "source_path_from_root": "/articles/search/tutorial-rag-build-solution.md",
+            "redirect_url": "https://github.com/Azure-Samples/azure-search-classic-rag",
+            "redirect_document_id": false
+        },
+        {
+            "source_path_from_root": "/articles/search/tutorial-rag-build-solution-models.md",
+            "redirect_url": "https://github.com/Azure-Samples/azure-search-classic-rag",
+            "redirect_document_id": false
+        },
+        {
+            "source_path_from_root": "/articles/search/tutorial-rag-build-solution-index-schema.md",
+            "redirect_url": "https://github.com/Azure-Samples/azure-search-classic-rag",
+            "redirect_document_id": false
+        },
+        {
+            "source_path_from_root": "/articles/search/tutorial-rag-build-solution-pipeline.md",
+            "redirect_url": "https://github.com/Azure-Samples/azure-search-classic-rag",
+            "redirect_document_id": false
+        },
+        {
+            "source_path_from_root": "/articles/search/tutorial-rag-build-solution-query.md",
+            "redirect_url": "https://github.com/Azure-Samples/azure-search-classic-rag",
+            "redirect_document_id": false
+        },
+        {
+            "source_path_from_root": "/articles/search/tutorial-rag-build-solution-maximize-relevance.md",
+            "redirect_url": "https://github.com/Azure-Samples/azure-search-classic-rag",
+            "redirect_document_id": false
+        },
+        {
+            "source_path_from_root": "/articles/search/tutorial-rag-build-solution-minimize-storage.md",
+            "redirect_url": "https://github.com/Azure-Samples/azure-search-classic-rag",
+            "redirect_document_id": false
+        },
+        {
+            "source_path_from_root": "/articles/search/search-howto-powerapps.md",
+            "redirect_url": "/azure/search/search-what-is-azure-search",
+            "redirect_document_id": false
+        },
+        {
+            "source_path_from_root": "/articles/search/tutorial-csharp-create-mvc-app.md",
+            "redirect_url": "/azure/search/tutorial-csharp-overview",
+            "redirect_document_id": false
         }
     ]
   }
\ No newline at end of file

@@ -43,9 +43,9 @@ We recommend using the [**Import data (new)** wizard](search-get-started-portal-
 
 ## Prerequisites
 
-+ A [Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects) or an [AML workspace](../machine-learning/concept-workspace.md) for a custom model that you create.
++ A [Microsoft Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects) or an [AML workspace](../machine-learning/concept-workspace.md) for a custom model that you create.
 
-+ For hub-based projects only, a [serverless deployment](/azure/ai-foundry/how-to/deploy-models-serverless) of a [supported model](#skill-parameters) from the Foundry model catalog.
++ For hub-based projects only, a serverless deployment of a [supported model](#skill-parameters) from the Microsoft Foundry model catalog. You can use an [ARM/Bicep template](https://github.com/Azure-Samples/azure-ai-search-multimodal-sample/blob/42b4d07f2dd9f7720fdc0b0788bf107bdac5eecb/infra/ai/modules/project.bicep#L37C1-L38C1) to provision the serverless deployment.
 
 ## @odata.type
 
@@ -57,7 +57,7 @@ Parameters are case sensitive. The parameters you use depend on what [authentica
 
 | Parameter name | Description |
 |--------------------|-------------|
-| `uri` | (Required for [key authentication](#WhatSkillParametersToUse)) The target URI of the serverless deployment from the Foundry model catalog or the [scoring URI of the AML online endpoint](../machine-learning/how-to-authenticate-online-endpoint.md). Only the HTTPS URI scheme is allowed. Supported models from the model catalog are:<ul><li>Cohere-embed-v3-english</li><li>Cohere-embed-v3-multilingual</li><li>Cohere-embed-v4</li></ul> |
+| `uri` | (Required for [key authentication](#WhatSkillParametersToUse)) The target URI of the serverless deployment from the Microsoft Foundry model catalog or the [scoring URI of the AML online endpoint](../machine-learning/how-to-authenticate-online-endpoint.md). Only the HTTPS URI scheme is allowed. Supported models from the model catalog (serverless deployments only) are:<ul><li>Cohere-embed-v3-english</li><li>Cohere-embed-v3-multilingual</li><li>Cohere-embed-v4</li></ul> |
 | `key` | (Required for [key authentication](#WhatSkillParametersToUse)) The API key of the model provider. |
 | `resourceId` | (Required for [token authentication](#WhatSkillParametersToUse)) The Azure Resource Manager resource ID of the model provider. For an AML online endpoint, use the `subscriptions/{guid}/resourceGroups/{resource-group-name}/Microsoft.MachineLearningServices/workspaces/{workspace-name}/onlineendpoints/{endpoint_name}` format. |
 | `region` | (Optional for [token authentication](#WhatSkillParametersToUse)) The region in which the model provider is deployed. Required if the region is different from the region of the search service. |

@@ -1,208 +0,0 @@
----
-manager: nitinme
-author: haileytap
-ms.author: haileytapia
-ms.service: azure-ai-search
-ms.topic: include
-ms.date: 09/16/2025
----
-
-> [!IMPORTANT]
-> The **Import data (new)** wizard now supports keyword search, which was previously only available in the **Import data** wizard. We recommend the new wizard for an improved search experience. For more information about how we're consolidating the wizards, see [Import data wizards in the Azure portal](../../search-import-data-portal.md).
-
-In this quickstart, you learn how a skillset in Azure AI Search adds optical character recognition (OCR), image analysis, language detection, text merging, and entity recognition to generate text-searchable content in an index.
-
-You can run the **Import data (new)** wizard in the Azure portal to apply skills that create and transform textual content during indexing. The input is your raw data, usually blobs in Azure Storage. The output is a searchable index containing AI-generated image text, captions, and entities. You can then query generated content in the Azure portal using [**Search explorer**](../../search-explorer.md).
-
-Before you run the wizard, you create a few resources and upload sample files.
-
-## Prerequisites
-
-+ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
-
-+ An Azure AI Search service. [Create a service](../../search-create-service-portal.md) or [find an existing service](https://portal.azure.com/#blade/HubsExtension/BrowseResourceBlade/resourceType/Microsoft.Search%2FsearchServices) in your current subscription. You can use a free service for this quickstart.
-
-+ An [Azure Storage account](/azure/storage/common/storage-account-create). Use Azure Blob Storage on a standard performance (general-purpose v2) account. To avoid bandwidth charges, use the same region as Azure AI Search.
-
-> [!NOTE]
-> This quickstart uses [Foundry Tools](https://azure.microsoft.com/services/cognitive-services/) for AI enrichment. Because the workload is small, Foundry Tools is tapped behind the scenes for free processing up to 20 transactions. Therefore, you don't need to create a Microsoft Foundry resource.
-
-## Prepare sample data
-
-In this section, you create an Azure Storage container to store sample data consisting of various file types, including images and application files that aren't full-text searchable in their native formats.
-
-To prepare the sample data for this quickstart:
-
-1. Sign in to the [Azure portal](https://portal.azure.com/) and select your Azure Storage account.
-
-1. From the left pane, select **Data storage** > **Containers**.
-
-1. Create a container, and then upload the [sample data](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/ai-enrichment-mixed-media) to the container.
-
-## Run the wizard
-
-To run the wizard:
-
-1. Sign in to the [Azure portal](https://portal.azure.com/) and select your search service.
-
-1. On the **Overview** page, select **Import data (new)**.
-
-   :::image type="content" source="../../media/search-import-data-portal/import-data-new-button.png" alt-text="Screenshot that shows how to open the new import wizard in the Azure portal.":::
-
-1. Select **Azure Blob Storage** for the data source.
-
-   :::image type="content" source="../../media/search-get-started-skillset/choose-data-source.png" alt-text="Screenshot of the Azure Blob Storage data source option in the Azure portal." border="true" lightbox="../../media/search-get-started-skillset/choose-data-source.png":::
-
-1. Select **Keyword search**.
-
-   :::image type="content" source="../../media/search-get-started-portal/keyword-search-tile.png" alt-text="Screenshot of the keyword search tile in the Azure portal." border="true" lightbox="../../media/search-get-started-portal/keyword-search-tile.png":::
-
-### Step 1: Create a data source
-
-Azure AI Search requires a connection to a data source for content ingestion and indexing. In this case, the data source is your Azure Storage account.
-
-To create the data source:
-
-1. On the **Connect to your data** page, select your Azure subscription.
-
-1. Select your storage account, and then select the container you created.
-
-   :::image type="content" source="../../media/search-get-started-skillset/connect-to-your-data.png" alt-text="Screenshot of the Connect to your data page in the Azure portal." border="true" lightbox="../../media/search-get-started-skillset/connect-to-your-data.png":::
-
-1. Select **Next**.
-
-If you get `Error detecting index schema from data source`, the indexer that powers the wizard can't connect to your data source. The data source most likely has security protections. Try the following solutions, and then rerun the wizard.
-
-| Security feature | Solution |
-|--------------------|----------|
-| Resource requires Azure roles, or its access keys are disabled. | [Connect as a trusted service](../../search-indexer-howto-access-trusted-service-exception.md) or [connect using a managed identity](../../search-how-to-managed-identities.md). |
-| Resource is behind an IP firewall. | [Create an inbound rule for Azure AI Search and the Azure portal](../../search-indexer-howto-access-ip-restricted.md). |
-| Resource requires a private endpoint connection. | [Connect over a private endpoint](../../search-indexer-howto-access-private.md). |
-
-### Step 2: Add cognitive skills
-
-The next step is to configure AI enrichment to invoke OCR, image analysis, and entity recognition.
-
-OCR and image analysis are available for blobs in Azure Blob Storage and Azure Data Lake Storage (ADLS) Gen2 and for image content in Microsoft OneLake. Images can be standalone files or embedded images in a PDF or other files.
-
-To add the skills:
-
-1. Select **Extract entities**, and then select the gear icon.
-
-1. Select and save the following checkboxes:
-
-   + **Persons**
-
-   + **Locations**
-
-   + **Organizations**
-
-   :::image type="content" source="../../media/search-get-started-skillset/extract-entities.png" alt-text="Screenshot of the Extract entities options in the Azure portal." lightbox="../../media/search-get-started-skillset/extract-entities.png":::
-
-1. Select **Extract text from images**, and then select the gear icon.
-
-1. Select and save the following checkboxes:
-
-   + **Generate tags**
-
-   + **Categorize content**
-
-   :::image type="content" source="../../media/search-get-started-skillset/extract-text.png" alt-text="Screenshot of the Extract text from images options in the Azure portal." lightbox="../../media/search-get-started-skillset/extract-text.png":::
-
-1. Leave the **Use a free AI service (limited enrichments)** checkbox selected.
-
-   The sample data consists of 14 files, so the free allotment of 20 transactions on Foundry Tools is sufficient.
-
-1. Select **Next**.
-
-### Step 3: Configure the index
-
-An index contains your searchable content. The wizard can usually create the schema by sampling the data source. In this step, you review the generated schema and potentially revise any settings.
-
-For this quickstart, the wizard sets reasonable defaults:  
-
-+ Default fields are based on metadata properties of existing blobs and new fields for the enrichment output, such as `persons`, `locations`, and `organizations`. Data types are inferred from metadata and by data sampling.
-
-  :::image type="content" source="../../media/search-get-started-skillset/index-fields-new-wizard.png" alt-text="Screenshot of the index definition page." border="true" lightbox="../../media/search-get-started-skillset/index-fields-new-wizard.png":::
-
-+ Default document key is `metadata_storage_path`, which is selected because the field contains unique values.
-
-+ Default field attributes are based on the skills you selected. For example, fields created by the Entity Recognition skill (`persons`, `locations`, and `organizations`) are **Retrievable**, **Filterable**, **Facetable**, and **Searchable**. To view and change these attributes, select a field, and then select **Configure field**.
-
-  **Retrievable** fields can be returned in results, while **Searchable** fields support full-text search. Use **Filterable** if you want to use fields in a filter expression.
-  
-  Marking a field as **Retrievable** doesn't mean that the field *must* appear in search results. You can control which fields are returned by using the `select` query parameter.
-
-After you review the index schema, select **Next**.
-
-### Step 4: Skip advanced settings
-
-The wizard offers advanced settings for semantic ranking and index scheduling, which are beyond the scope of this quickstart. Skip this step by selecting **Next**.
-
-### Step 5: Review and create objects
-
-The last step is to review your configuration and create the index, indexer, and data source on your search service. The indexer automates the process of extracting content from your data source, loading the index, and driving skillset execution.
-
-To review and create the objects:
-
-1. Accept the default **Objects name prefix**.
-
-1. Review the object configurations.
-
-   :::image type="content" source="../../media/search-get-started-skillset/review-and-create.png" alt-text="Screenshot of the object configuration page in the Azure portal." border="true" lightbox="../../media/search-get-started-skillset/review-and-create.png":::
-
-   AI enrichment, semantic ranker, and indexer scheduling are either disabled or set to their default values because you skipped their wizard steps.
-
-1. Select **Create** to simultaneously create the objects and run the indexer.
-
-## Monitor status
-
-You can monitor the creation of the indexer in the Azure portal. Skills-based indexing takes longer than text-based indexing, especially OCR and image analysis.
-
-To monitor the progress of the indexer:
-
-1. From the left pane, select **Indexers**.
-
-1. Select your indexer from the list.
-
-1. Select **Success** (or **Failed**) to view execution details.
-
-   :::image type="content" source="../../media/search-get-started-skillset/indexer-notification.png" alt-text="Screenshot of the indexer status page." border="true" lightbox="../../media/search-get-started-skillset/indexer-notification.png":::
-
-  In this quickstart, there are a few warnings, including `Could not execute skill because one or more skill input was invalid.` This warning tells you that a PNG file in the data source doesn't provide a text input to Entity Recognition. It occurs because the upstream OCR skill didn't recognize any text in the image and couldn't provide a text input to the downstream Entity Recognition skill.
-
-  Warnings are common in skillset execution. As you become familiar with how skills iterate over your data, you might begin to notice patterns and learn which warnings are safe to ignore.
-
-## Query in Search explorer
-
-To query your index:
-
-1. From the left pane, select **Indexes**.
-
-1. Select your index from the list. If the index has zero documents or storage, wait for the Azure portal to refresh.
-
-1. On the **Search explorer** tab, enter a search string, such as `satya nadella`.
-
-The search bar accepts keywords, quote-enclosed phrases, and operators. For example: `"Satya Nadella" +"Bill Gates" +"Steve Ballmer"`
-
-Results are returned as verbose JSON, which can be hard to read, especially in large documents. Here are tips for searching in this tool:
-    
-   + Switch to the JSON view to specify parameters that shape results.
-   + Add `select` to limit the fields in results.
-   + Add `count` to show the number of matches.
-   + Use Ctrl-F to search within the JSON for specific properties or terms.
-
-:::image type="content" source="../../media/search-get-started-skillset/search-explorer-new-wizard.png" alt-text="Screenshot of the Search explorer page." border="true" lightbox="../../media/search-get-started-skillset/search-explorer-new-wizard.png":::
-
-Here's some JSON you can paste into the view:
-    
-```json
-{
-"search": "\"Satya Nadella\" +\"Bill Gates\" +\"Steve Ballmer\"",
-"count": true,
-"select": "merged_content, persons"
-}
-```
-
-> [!TIP]
-> Query strings are case sensitive, so if you get an "unknown field" message, check **Fields** or **Index Definition (JSON)** to verify the name and case.
\ No newline at end of file

@@ -1,196 +0,0 @@
----
-manager: nitinme
-author: haileytap
-ms.author: haileytapia
-ms.service: azure-ai-search
-ms.topic: include
-ms.date: 09/16/2025
----
-
-> [!IMPORTANT]
-> The **Import data** wizard will eventually be deprecated. Most of its functionality is available in the **Import data (new)** wizard, which we recommend for most search scenarios. For more information, see [Import data wizards in the Azure portal](../../search-import-data-portal.md).
-
-In this quickstart, you learn how a skillset in Azure AI Search adds optical character recognition (OCR), image analysis, language detection, text merging, and entity recognition to generate text-searchable content in an index.
-
-You can run the **Import data** wizard in the Azure portal to apply skills that create and transform textual content during indexing. The input is your raw data, usually blobs in Azure Storage. The output is a searchable index containing AI-generated image text, captions, and entities. You can then query generated content in the Azure portal using [**Search explorer**](../../search-explorer.md).
-
-Before you run the wizard, you create a few resources and upload sample files.
-
-## Prerequisites
-
-+ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
-
-+ An Azure AI Search service. [Create a service](../../search-create-service-portal.md) or [find an existing service](https://portal.azure.com/#blade/HubsExtension/BrowseResourceBlade/resourceType/Microsoft.Search%2FsearchServices) in your current subscription. You can use a free service for this quickstart.
-
-+ An [Azure Storage account](/azure/storage/common/storage-account-create). Use Azure Blob Storage on a standard performance (general-purpose v2) account. To avoid bandwidth charges, use the same region as Azure AI Search.
-
-> [!NOTE]
-> This quickstart uses [Foundry Tools](https://azure.microsoft.com/services/cognitive-services/) for AI enrichment. Because the workload is small, Foundry Tools is tapped behind the scenes for free processing up to 20 transactions. Therefore, you don't need to create a Microsoft Foundry resource.
-
-## Prepare sample data
-
-In this section, you create an Azure Storage container to store sample data consisting of various file types, including images and application files that aren't full-text searchable in their native formats.
-
-To prepare the sample data for this quickstart:
-
-1. Sign in to the [Azure portal](https://portal.azure.com/) and select your Azure Storage account.
-
-1. From the left pane, select **Data storage** > **Containers**.
-
-1. Create a container, and then upload the [sample data](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/ai-enrichment-mixed-media) to the container.
-
-## Run the wizard
-
-To run the wizard:
-
-1. Sign in to the [Azure portal](https://portal.azure.com/) and select your search service.
-
-1. On the **Overview** page, select **Import data**.
-
-   :::image type="content" source="../../media/search-import-data-portal/import-data-button.png" alt-text="Screenshot of the Import data command." border="true":::
-
-### Step 1: Create a data source
-
-Azure AI Search requires a connection to a data source for content ingestion and indexing. In this case, the data source is your Azure Storage account.
-
-To create the data source:
-
-1. On the **Connect to your data** page, select the **Data Source** dropdown list, and then select **Azure Blob Storage**.
-
-1. Choose an existing connection string for your storage account, and then select the container you created.
-
-1. Enter a name for the data source.
-
-   :::image type="content" source="../../media/search-get-started-skillset/blob-datasource.png" alt-text="Screenshot of the data source definition page." border="true" lightbox="../../media/search-get-started-skillset/blob-datasource.png":::
-
-1. Select **Next: Add cognitive skills (Optional)**.
-
-If you get `Error detecting index schema from data source`, the indexer that powers the wizard can't connect to your data source. The data source most likely has security protections. Try the following solutions, and then rerun the wizard.
-
-| Security feature | Solution |
-|--------------------|----------|
-| Resource requires Azure roles, or its access keys are disabled. | [Connect as a trusted service](../../search-indexer-howto-access-trusted-service-exception.md) or [connect using a managed identity](../../search-how-to-managed-identities.md). |
-| Resource is behind an IP firewall. | [Create an inbound rule for Azure AI Search and the Azure portal](../../search-indexer-howto-access-ip-restricted.md). |
-| Resource requires a private endpoint connection. | [Connect over a private endpoint](../../search-indexer-howto-access-private.md). |
-
-### Step 2: Add cognitive skills
-
-The next step is to configure AI enrichment to invoke OCR, image analysis, and natural-language processing. 
-
-OCR and image analysis are available for blobs in Azure Blob Storage and Azure Data Lake Storage (ADLS) Gen2 and for image content in Microsoft OneLake. Images can be standalone files or embedded images in a PDF or other files.
-
-To add the skills:
-
-1. Expand the **Attach Cognitive Services** section.
-
-1. Select **Free (Limited enrichments)** to use a free Foundry resource.
-
-   :::image type="content" source="../../media/search-get-started-skillset/cog-search-attach.png" alt-text="Screenshot of the Attach Foundry tab." border="true" lightbox="../../media/search-get-started-skillset/cog-search-attach.png":::
-
-   The sample data consists of 14 files, so the free allotment of 20 transactions on Foundry is sufficient.
-
-1. Expand the **Add enrichments** section.
-
-1. Select the **Enable OCR and merge all text into merged_content field** checkbox.
-
-1. Under **Text Cognitive Skills**, select the following checkboxes:
-
-    + **Extract people names**
-    
-    + **Extract organization names**
-    
-    + **Extract location names**
-
-1. Under **Image Cognitive Skills**, select the following checkboxes: 
-
-    + **Generate tags from images**
-    
-    + **Generate captions from images**
-
-   :::image type="content" source="../../media/search-get-started-skillset/skillset.png" alt-text="Screenshot of the skillset definition page." border="true" lightbox="../../media/search-get-started-skillset/skillset.png":::
-
-1. Select **Next: Customer target index**.
-
-### Step 3: Configure the index
-
-An index contains your searchable content. The wizard can usually create the schema by sampling the data source. In this step, you review the generated schema and potentially revise any settings. 
-
-For this quickstart, the wizard sets reasonable defaults:  
-
-+ Default fields are based on metadata properties of existing blobs and new fields for the enrichment output, such as `people`, `organizations`, and `locations`. Data types are inferred from metadata and by data sampling.
-
-+ Default document key is `metadata_storage_path`, which is selected because the field contains unique values.
-
-+ Default attributes are **Retrievable** and **Searchable**. **Retrievable** fields can be returned in results, while **Searchable** fields support full-text search. The wizard assumes you want these fields to be retrievable and searchable because you created them via a skillset. Select **Filterable** if you want to use fields in a filter expression.
-
-  :::image type="content" source="../../media/search-get-started-skillset/index-fields-old-wizard.png" alt-text="Screenshot of the index definition page." border="true" lightbox="../../media/search-get-started-skillset/index-fields-old-wizard.png":::
-
-  Marking a field as **Retrievable** doesn't mean that the field *must* appear in search results. You can control which fields are returned by using the `select` query parameter.
-      
-After you review the index schema, select **Next: Create an indexer**.
-
-### Step 4: Configure the indexer
-
-The indexer drives the indexing process and specifies the data source name, a target index, and frequency of execution. In this step, the wizard creates several objects, including an indexer that you can reset and run repeatedly.
-
-To configure the indexer:
-
-1. On the **Create an indexer** page, accept the default name.
-
-1. Select **Once** for the schedule.
-
-   :::image type="content" source="../../media/search-get-started-skillset/indexer-def.png" alt-text="Screenshot of the indexer definition page." border="true" lightbox="../../media/search-get-started-skillset/indexer-def.png":::
-
-1. Select **Submit** to simultaneously create and run the indexer.
-
-## Monitor status
-
-You can monitor the creation of the indexer in the Azure portal. Skills-based indexing takes longer than text-based indexing, especially OCR and image analysis.
-
-To monitor the progress of the indexer:
-
-1. From the left pane, select **Indexers**.
-
-1. Select your indexer from the list.
-
-1. Select **Success** (or **Failed**) to view execution details.
-
-   :::image type="content" source="../../media/search-get-started-skillset/indexer-notification.png" alt-text="Screenshot of the indexer status page." border="true" lightbox="../../media/search-get-started-skillset/indexer-notification.png":::
-
-  In this quickstart, there are a few warnings, including `Could not execute skill because one or more skill input was invalid.` This warning tells you that a PNG file in the data source doesn't provide a text input to Entity Recognition. It occurs because the upstream OCR skill didn't recognize any text in the image and couldn't provide a text input to the downstream Entity Recognition skill.
-
-  Warnings are common in skillset execution. As you become familiar with how skills iterate over your data, you might begin to notice patterns and learn which warnings are safe to ignore.
-
-## Query in Search explorer
-
-To query your index:
-
-1. From the left pane, select **Indexes**.
-
-1. Select your index from the list. If the index has zero documents or storage, wait for the Azure portal to refresh.
-
-1. On the **Search explorer** tab, enter a search string, such as `satya nadella`.
-
-The search bar accepts keywords, quote-enclosed phrases, and operators. For example: `"Satya Nadella" +"Bill Gates" +"Steve Ballmer"`
-
-Results are returned as verbose JSON, which can be hard to read, especially in large documents. Here are tips for searching in this tool:
-    
-   + Switch to the JSON view to specify parameters that shape results.
-   + Add `select` to limit the fields in results.
-   + Add `count` to show the number of matches.
-   + Use Ctrl-F to search within the JSON for specific properties or terms.
-
-:::image type="content" source="../../media/search-get-started-skillset/search-explorer-old-wizard.png" alt-text="Screenshot of the Search explorer page." border="true" lightbox="../../media/search-get-started-skillset/search-explorer-old-wizard.png":::
-
-Here's some JSON you can paste into the view:
-    
-```json
-{
-"search": "\"Satya Nadella\" +\"Bill Gates\" +\"Steve Ballmer\"",
-"count": true,
-"select": "content, people"
-}
-```
-
-> [!TIP]
-> Query strings are case sensitive, so if you get an "unknown field" message, check **Fields** or **Index Definition (JSON)** to verify the name and case.
\ No newline at end of file

@@ -5,9 +5,9 @@ description: Learn how generative AI and retrieval augmented generation (RAG) pa
 author: HeidiSteen
 ms.author: heidist
 manager: nitinme
-ms.date: 10/14/2025
+ms.date: 12/10/2025
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: article
 ms.custom:
   - ignite-2023
   - ignite-2024
@@ -153,70 +153,6 @@ Here are some tips for maximizing relevance and recall:
 
 In comparison and benchmark testing, hybrid queries with text and vector fields, supplemented with semantic ranking, produce the most relevant results.
 
-<!-- ### Example code for a classic RAG workflow
-
-The following Python code demonstrates the essential components of a basic RAG workflow in Azure AI Search. You need to set up the clients, define a system prompt, and provide a query. The prompt tells the LLM to use just the results from the query, and how to return the results. For more steps based on this example, see this [RAG quickstart](search-get-started-rag.md).
-
-> [!NOTE]
-> For the Azure Government cloud, modify the API endpoint on the token provider to `"https://cognitiveservices.azure.us/.default"`.
-
-```python
-# Set up the query for generating responses
-from azure.identity import DefaultAzureCredential
-from azure.identity import get_bearer_token_provider
-from azure.search.documents import SearchClient
-from openai import AzureOpenAI
-
-credential = DefaultAzureCredential()
-token_provider = get_bearer_token_provider(credential, "https://cognitiveservices.azure.com/.default")
-openai_client = AzureOpenAI(
-    api_version="2024-06-01",
-    azure_endpoint=AZURE_OPENAI_ACCOUNT,
-    azure_ad_token_provider=token_provider
-)
-
-search_client = SearchClient(
-    endpoint=AZURE_SEARCH_SERVICE,
-    index_name="hotels-sample-index",
-    credential=credential
-)
-
-# This prompt provides instructions to the model. 
-# The prompt includes the query and the source, which are specified further down in the code.
-GROUNDED_PROMPT="""
-You are a friendly assistant that recommends hotels based on activities and amenities.
-Answer the query using only the sources provided below in a friendly and concise bulleted manner.
-Answer ONLY with the facts listed in the list of sources below.
-If there isn't enough information below, say you don't know.
-Do not generate answers that don't use the sources below.
-Query: {query}
-Sources:\n{sources}
-"""
-
-# The query is sent to the search engine, but it's also passed in the prompt
-query="Can you recommend a few hotels near the ocean with beach access and good views"
-
-# Retrieve the selected fields from the search index related to the question
-search_results = search_client.search(
-    search_text=query,
-    top=5,
-    select="Description,HotelName,Tags"
-)
-sources_formatted = "\n".join([f'{document["HotelName"]}:{document["Description"]}:{document["Tags"]}' for document in search_results])
-
-response = openai_client.chat.completions.create(
-    messages=[
-        {
-            "role": "user",
-            "content": GROUNDED_PROMPT.format(query=query, sources=sources_formatted)
-        }
-    ],
-    model="gpt-4.1-mini"
-)
-
-print(response.choices[0].message.content)
-``` -->
-
 ## Integration code and LLMs
 
 A RAG solution that includes Azure AI Search can leverage [built-in data chunking and vectorization capabilities](vector-search-integrated-vectorization.md), or you can build your own using platforms like Semantic Kernel, LangChain, or LlamaIndex.
@@ -227,13 +163,11 @@ We recommend the [Azure OpenAI demo](https://github.com/Azure-Samples/azure-sear
 
 There are many ways to get started, including code-first solutions and demos.
 
-For help with choosing between agentic retrieval and classic RAG, try a few quickstarts using your own data to understand the development effort and compare outcomes.
-
 ### [**Docs**](#tab/docs)
 
-+ [Try this agentic retrieval quickstart](search-get-started-rag.md) to walk through the new and recommended approach for RAG.
++ [Try this agentic retrieval quickstart](search-get-started-agentic-retrieval.md) to walk through the new and recommended approach for RAG.
 
-+ [Try this classic RAG quickstart](search-get-started-rag.md) for a demonstration of query integration with chat models over a search index.
++ [Try this tutorial](agentic-retrieval-how-to-create-pipeline.md) for a more comprehensive approach that includes an agent.
 
 + [Review indexing concepts and strategies](search-what-is-an-index.md) to determine how you want to ingest and refresh data. Decide whether to use vector search, keyword search, or hybrid search. The kind of content you need to search over, and the type of queries you want to run, determines index design.
 
@@ -246,7 +180,11 @@ For help with choosing between agentic retrieval and classic RAG, try a few quic
 
 Check out the following GitHub repositories for code, documentation, and video demonstrations where applicable.
 
-+ [RAG Time Journeys](https://github.com/microsoft/rag-time)
++ [RAG chat app with Azure OpenAI and Azure AI Search (Python)](https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/README.md)
+
++ [Classic RAG Time Journeys](https://github.com/microsoft/rag-time)
+
++ [azure-search-classic-rag](https://github.com/Azure-Samples/azure-search-classic-rag/blob/main/README.md)
 
 + [azure-search-vector-samples](https://github.com/Azure/azure-search-vector-samples)
 
@@ -279,8 +217,4 @@ Check out the following GitHub repositories for code, documentation, and video d
 
 ## See also
 
-+ [RAG Experiment Accelerator](https://github.com/microsoft/rag-experiment-accelerator)
-
-+ [Retrieval Augmented Generation: Streamlining the creation of intelligent natural language processing models](https://ai.meta.com/blog/retrieval-augmented-generation-streamlining-the-creation-of-intelligent-natural-language-processing-models/)
-
-+ [Azure Cognitive Search and LangChain: A Seamless Integration for Enhanced Vector Search Capabilities](https://techcommunity.microsoft.com/t5/azure-ai-services-blog/azure-cognitive-search-and-langchain-a-seamless-integration-for/ba-p/3901448)
++ [Retrieval augmented generation and indexes (Foundry)](/azure/ai-foundry/concepts/retrieval-augmented-generation)

@@ -10,7 +10,7 @@ ms.custom:
   - devx-track-dotnet
   - ignite-2023
 ms.topic: concept-article
-ms.date: 09/23/2025
+ms.date: 12/10/2025
 ---
 
 # C# samples for Azure AI Search
@@ -52,7 +52,6 @@ Code samples from the Azure AI Search team demonstrate features and workflows. T
 | [quickstart-rag](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/quickstart-rag) | [Quickstart: Generative search (RAG)](search-get-started-rag.md) | Use 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) | Add semantic ranking to an index schema and run semantic queries. |
 | [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) | Index and query vector content. |
-| [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) | Add basic search, pagination, and other server-side behaviors to an MVC web app, unlike the console applications used in most samples. |
 | [search-website](https://github.com/Azure-Samples/azure-search-static-web-app) | [Tutorial: Add search to web apps](tutorial-csharp-overview.md) | Build an end-to-end search app that uses the push API for bulk upload and a rich client for hosting the app and handling search requests. |
 | [tutorial-ai-enrichment](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/tutorial-ai-enrichment) | [Tutorial: AI-generated searchable content from Azure blobs](tutorial-skillset.md) | Create a skillset that iterates over Azure blobs to extract information and infer structure. |
 | [multiple-data-sources](https://github.com/Azure-Samples/azure-search-dotnet-scale/tree/main/multiple-data-sources) | [Tutorial: Index from multiple data sources](tutorial-multiple-data-sources.md) | Merge content from two data sources into one index. |
@@ -61,14 +60,6 @@ Code samples from the Azure AI Search team demonstrate features and workflows. T
 | [DotNetToIndexers](https://github.com/Azure-Samples/search-dotnet-getting-started/tree/master/DotNetHowToIndexers) | [Tutorial: Index Azure SQL data](search-indexer-tutorial.md) | Configure an Azure SQL indexer with a schedule, field mappings, and parameters. |
 | [DotNetHowToEncryptionUsingCMK](https://github.com/Azure-Samples/search-dotnet-getting-started/tree/master/DotNetHowToEncryptionUsingCMK) | [Configure customer-managed keys for data encryption](search-security-manage-encryption-keys.md) | Create objects that are encrypted with a customer-managed key. |
 
-## Accelerators
-
-An accelerator is an end-to-end solution that includes code and documentation you can adapt for your own implementation of a specific scenario.
-
-| Sample | Description |
-|--|--|
-| [search-qna-maker-accelerator](https://github.com/Azure-Samples/search-qna-maker-accelerator) | [Solution](https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/qna-with-azure-cognitive-search/2081381) that combines Azure AI Search and QnA Maker. See the live [demo site](https://aka.ms/qnaWithAzureSearchDemo). |
-
 ## Demos
 
 A demo repo provides proof-of-concept source code for examples or scenarios shown in demonstrations. Unlike accelerators, demo solutions aren't designed for adaptation.

@@ -41,7 +41,6 @@ Code samples from the Azure AI Search team demonstrate features and workflows. T
 | [Quickstart-RAG](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-RAG) | [Quickstart: Generative search (RAG)](search-get-started-rag.md) | Use grounding data from Azure AI Search with a chat completion model from Azure OpenAI. |
 | [Quickstart-Semantic-Search](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Semantic-Search) | [Quickstart: Semantic ranking](search-get-started-semantic.md) | Add semantic ranking to an index schema and run semantic queries. |
 | [Quickstart-Vector-Search](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Vector-Search) | [Quickstart: Vector search](search-get-started-vector.md) | Index and query vector content. |
-| [Tutorial-RAG](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Tutorial-RAG) | [Build a RAG solution using Azure AI Search](tutorial-rag-build-solution.md) | Create an indexing pipeline that loads, chunks, embeds, and ingests searchable content for RAG. |
 | [agentic-retrieval-pipeline-example](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/agentic-retrieval-pipeline-example) | [Tutorial: Build an end-to-end agentic retrieval solution](agentic-retrieval-how-to-create-pipeline.md) | Unlike [Quickstart-Agentic-Retrieval](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Agentic-Retrieval), this sample incorporates Foundry Agent Service for request orchestration. |
 
 ## Accelerators
@@ -68,6 +67,7 @@ The following samples are also published by the Azure AI Search team but aren't
 
 | Sample | Description |
 |--|--|
+| [Classic RAG pattern](https://github.com/Azure-Samples/azure-search-classic-rag/blob/main/README.md) | Create an indexing pipeline that uses the [classic search engine](search-what-is-azure-search.md#what-is-classic-search) to load, chunk, embed, and ingest searchable content. |
 | [Quickstart-Document-Permissions-Pull-API](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Document-Permissions-Pull-API) | Using an indexer "pull API" approach, flow access control lists from a data source to search results and apply permission filters that restrict access to authorized content. |
 | [Quickstart-Document-Permissions-Push-API](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-Document-Permissions-Push-API) | Using the push APIs for indexing a JSON payload, flow embedded permission metadata to indexed documents and search results that are filtered based on user access to authorized content. |
 | [azure-function-search](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/azure-function-search) | Use an Azure function to send queries to a search service. You can substitute this Python version for the `api` code used in [Add search to web sites with .NET](tutorial-csharp-overview.md). |

@@ -6,7 +6,7 @@ manager: nitinme
 author: HeidiSteen
 ms.author: heidist
 ms.service: azure-ai-search
-ms.topic: conceptual
+ms.topic: article
 ms.date: 10/06/2025
 ms.update-cycle: 365-days
 ms.custom:
@@ -137,7 +137,7 @@ The output of an indexer is a search index, used for interactive exploration usi
 + [Full query syntax](query-lucene-syntax.md)
 + [Filter expression syntax](query-odata-filter-orderby-syntax.md)
 
-A more permanent solution is to gather query inputs and present the response as search results in a client application. The following C# tutorial explains how to build a search application: [Add search to an ASP.NET Core (MVC) application](tutorial-csharp-create-mvc-app.md).
+A more permanent solution is to gather query inputs and present the response as search results in a client application.
 
 ## Next steps
 

@@ -52,20 +52,20 @@ For content embedding, choose one of the following methods:
 
 + **Multimodal embeddings:** Uses an embedding model to directly vectorize both text and images.
 
-The following table lists the supported providers and models for each method. Deployment instructions for the models are provided in a [later section](#deploy-models).
+The portal supports the following models for each method. Deployment instructions are provided in a [later section](#deploy-models).
 
 | Provider | Models for image verbalization | Models for multimodal embeddings |
 |--|--|--|
-| [Azure OpenAI in Foundry Models resource](/azure/ai-services/openai/how-to/create-resource) <sup>1, 2</sup> | LLMs:<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large | |
-| [Foundry project](/azure/ai-foundry/how-to/create-projects) | LLMs:<br>phi-4<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large | |
-| [Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects) | LLMs:<br>phi-4<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large<br>Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> | Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> |
-| [Foundry resource](/azure/ai-services/multi-service-resource) <sup>4</sup> | Embedding model: [Azure Vision in Foundry Tools multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>5</sup> | [Azure Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>5</sup> |
+| [Azure OpenAI resource](/azure/ai-foundry/openai/how-to/create-resource?view=foundry-classic&pivots=web-portal&preserve-view=true) <sup>1, 2</sup> | LLMs:<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large | |
+| [Microsoft Foundry project](/azure/ai-foundry/how-to/create-projects?view=foundry-classic&pivots=web-portal&preserve-view=true) | LLMs:<br>phi-4<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large | |
+| [Microsoft Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects?view=foundry-classic&pivots=web-portal&preserve-view=true) | LLMs:<br>phi-4<br>gpt-4o<br>gpt-4o-mini<br>gpt-5<br>gpt-5-mini<br>gpt-5-nano<br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large<br>Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> | Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> |
+| [Microsoft Foundry resource](/azure/ai-services/multi-service-resource) <sup>4</sup> | Embedding model: [Azure Vision in Foundry Tools multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>5</sup> | [Azure Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>5</sup> |
 
 <sup>1</sup> The endpoint of your Azure OpenAI resource must have a [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains), such as `https://my-unique-name.openai.azure.com`. If you created your resource in the [Azure portal](https://portal.azure.com/), this subdomain was automatically generated during resource setup.
 
 <sup>2</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Foundry portal](https://ai.azure.com/?cid=learnDocs) aren't supported. You must create an Azure OpenAI resource in the Azure portal.
 
-<sup>3</sup> To use this model in the wizard, you must [deploy it as a serverless API deployment](/azure/ai-foundry/how-to/deploy-models-serverless).
+<sup>3</sup> To use this model in the wizard, you must provision it as a serverless API deployment. You can use an [ARM/Bicep template](https://github.com/Azure-Samples/azure-ai-search-multimodal-sample/blob/42b4d07f2dd9f7720fdc0b0788bf107bdac5eecb/infra/ai/modules/project.bicep#L37C1-L38C1) for this task.
 
 <sup>4</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
 

@@ -42,20 +42,20 @@ The wizard [supports a wide range of Azure data sources](search-import-data-port
 
 ### Supported embedding models
 
-For integrated vectorization, use one of the following embedding models. Deployment instructions are provided in a [later section](#prepare-embedding-model).
+The portal supports the following embedding models for integrated vectorization. Deployment instructions are provided in a [later section](#prepare-embedding-model).
 
 | Provider | Supported models |
 |--|--|
-| [Azure OpenAI in Foundry Models resource](/azure/ai-services/openai/how-to/create-resource) <sup>1, 2</sup> | For text:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
+| [Azure OpenAI resource](/azure/ai-services/openai/how-to/create-resource) <sup>1, 2</sup> | For text:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
 | [Microsoft Foundry project](/azure/ai-foundry/how-to/create-projects) | For text:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
-| [Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects) | For text:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large<br><br>For text and images:<br>Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> |
-| [Foundry resource](/azure/ai-services/multi-service-resource) <sup>4</sup> | For text and images: [Azure Vision in Foundry Tools multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>5</sup></li> |
+| [Microsoft Foundry hub-based project](/azure/ai-foundry/how-to/hub-create-projects) | For text:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large<br><br>For text and images:<br>Cohere-embed-v3-english <sup>3</sup><br>Cohere-embed-v3-multilingual <sup>3</sup> |
+| [Microsoft Foundry resource](/azure/ai-services/multi-service-resource) <sup>4</sup> | For text and images: [Azure Vision in Foundry Tools multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>5</sup></li> |
 
 <sup>1</sup> The endpoint of your Azure OpenAI resource must have a [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains), such as `https://my-unique-name.openai.azure.com`. If you created your resource in the [Azure portal](https://portal.azure.com/), this subdomain was automatically generated during resource setup.
 
 <sup>2</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Foundry portal](https://ai.azure.com/?cid=learnDocs) aren't supported. You must create an Azure OpenAI resource in the Azure portal.
 
-<sup>3</sup> To use this model in the wizard, you must [deploy it as a serverless API deployment](/azure/ai-foundry/how-to/deploy-models-serverless).
+<sup>3</sup> To use this model in the wizard, you must provision it as a serverless API deployment. You can use an [ARM/Bicep template](https://github.com/Azure-Samples/azure-ai-search-multimodal-sample/blob/42b4d07f2dd9f7720fdc0b0788bf107bdac5eecb/infra/ai/modules/project.bicep#L37C1-L38C1) for this task.
 
 <sup>4</sup> For billing purposes, you must [attach your Foundry resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
 

@@ -53,8 +53,4 @@ In this quickstart, you send queries to a chat completion model for a conversati
 
 [!INCLUDE [TypeScript quickstart](includes/quickstarts/search-get-started-rag-typescript.md)]
 
-::: zone-end
-
-## Related content
-
-- [Tutorial: Build a RAG solution in Azure AI Search](tutorial-rag-build-solution.md)
\ No newline at end of file
+::: zone-end
\ No newline at end of file

@@ -10,19 +10,210 @@ ms.update-cycle: 180-days
 ms.custom:
   - ignite-2023
 ms.topic: quickstart
-ms.date: 09/16/2025
-zone_pivot_groups: azure-portal-wizards
+ms.date: 12/11/2025
 ---
 
 # Quickstart: Create a skillset in the Azure portal
 
-::: zone pivot="import-data-new"
-[!INCLUDE [Import data (new) instructions](includes/quickstarts/search-get-started-skillset-new-wizard.md)]
-::: zone-end
+> [!IMPORTANT]
+> The **Import data (new)** wizard now supports keyword search, which was previously only available in the **Import data** wizard. We recommend the new wizard for an improved search experience. For more information about how we're consolidating the wizards, see [Import data wizards in the Azure portal](search-import-data-portal.md).
 
-::: zone pivot="import-data"
-[!INCLUDE [Import data instructions](includes/quickstarts/search-get-started-skillset-old-wizard.md)]
-::: zone-end
+In this quickstart, you learn how a skillset in Azure AI Search adds optical character recognition (OCR), image analysis, language detection, text merging, and entity recognition to generate text-searchable content in an index.
+
+You can run the **Import data (new)** wizard in the Azure portal to apply skills that create and transform textual content during indexing. The input is your raw data, usually blobs in Azure Storage. The output is a searchable index containing AI-generated image text, captions, and entities. You can then query generated content in the Azure portal using [**Search explorer**](search-explorer.md).
+
+Before you run the wizard, you create a few resources and upload sample files.
+
+## Prerequisites
+
++ An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
+
++ An Azure AI Search service. [Create a service](search-create-service-portal.md) or [find an existing service](https://portal.azure.com/#blade/HubsExtension/BrowseResourceBlade/resourceType/Microsoft.Search%2FsearchServices) in your current subscription. You can use a free service for this quickstart.
+
++ An [Azure Storage account](/azure/storage/common/storage-account-create). Use Azure Blob Storage on a standard performance (general-purpose v2) account. To avoid bandwidth charges, use the same region as Azure AI Search.
+
+> [!NOTE]
+> This quickstart uses [Foundry Tools](https://azure.microsoft.com/services/cognitive-services/) for AI enrichment. Because the workload is small, Foundry Tools is tapped behind the scenes for free processing up to 20 transactions. Therefore, you don't need to create a Microsoft Foundry resource.
+
+## Prepare sample data
+
+In this section, you create an Azure Storage container to store sample data consisting of various file types, including images and application files that aren't full-text searchable in their native formats.
+
+To prepare the sample data for this quickstart:
+
+1. Sign in to the [Azure portal](https://portal.azure.com/) and select your Azure Storage account.
+
+1. From the left pane, select **Data storage** > **Containers**.
+
+1. Create a container, and then upload the [sample data](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/ai-enrichment-mixed-media) to the container.
+
+## Run the wizard
+
+To run the wizard:
+
+1. Sign in to the [Azure portal](https://portal.azure.com/) and select your search service.
+
+1. On the **Overview** page, select **Import data (new)**.
+
+   :::image type="content" source="media/search-import-data-portal/import-data-new-button.png" alt-text="Screenshot that shows how to open the new import wizard in the Azure portal.":::
+
+1. Select **Azure Blob Storage** for the data source.
+
+   :::image type="content" source="media/search-get-started-skillset/choose-data-source.png" alt-text="Screenshot of the Azure Blob Storage data source option in the Azure portal." border="true" lightbox="media/search-get-started-skillset/choose-data-source.png":::
+
+1. Select **Keyword search**.
+
+   :::image type="content" source="media/search-get-started-portal/keyword-search-tile.png" alt-text="Screenshot of the keyword search tile in the Azure portal." border="true" lightbox="media/search-get-started-portal/keyword-search-tile.png":::
+
+### Step 1: Create a data source
+
+Azure AI Search requires a connection to a data source for content ingestion and indexing. In this case, the data source is your Azure Storage account.
+
+To create the data source:
+
+1. On the **Connect to your data** page, select your Azure subscription.
+
+1. Select your storage account, and then select the container you created.
+
+   :::image type="content" source="media/search-get-started-skillset/connect-to-your-data.png" alt-text="Screenshot of the Connect to your data page in the Azure portal." border="true" lightbox="media/search-get-started-skillset/connect-to-your-data.png":::
+
+1. Select **Next**.
+
+If you get `Error detecting index schema from data source`, the indexer that powers the wizard can't connect to your data source. The data source most likely has security protections. Try the following solutions, and then rerun the wizard.
+
+| Security feature | Solution |
+|--------------------|----------|
+| Resource requires Azure roles, or its access keys are disabled. | [Connect as a trusted service](search-indexer-howto-access-trusted-service-exception.md) or [connect using a managed identity](search-how-to-managed-identities.md). |
+| Resource is behind an IP firewall. | [Create an inbound rule for Azure AI Search and the Azure portal](search-indexer-howto-access-ip-restricted.md). |
+| Resource requires a private endpoint connection. | [Connect over a private endpoint](search-indexer-howto-access-private.md). |
+
+### Step 2: Add cognitive skills
+
+The next step is to configure AI enrichment to invoke OCR, image analysis, and entity recognition.
+
+OCR and image analysis are available for blobs in Azure Blob Storage and Azure Data Lake Storage (ADLS) Gen2 and for image content in Microsoft OneLake. Images can be standalone files or embedded images in a PDF or other files.
+
+To add the skills:
+
+1. Select **Extract entities**, and then select the gear icon.
+
+1. Select and save the following checkboxes:
+
+   + **Persons**
+
+   + **Locations**
+
+   + **Organizations**
+
+   :::image type="content" source="media/search-get-started-skillset/extract-entities.png" alt-text="Screenshot of the Extract entities options in the Azure portal." lightbox="media/search-get-started-skillset/extract-entities.png":::
+
+1. Select **Extract text from images**, and then select the gear icon.
+
+1. Select and save the following checkboxes:
+
+   + **Generate tags**
+
+   + **Categorize content**
+
+   :::image type="content" source="media/search-get-started-skillset/extract-text.png" alt-text="Screenshot of the Extract text from images options in the Azure portal." lightbox="media/search-get-started-skillset/extract-text.png":::
+
+1. Leave the **Use a free AI service (limited enrichments)** checkbox selected.
+
+   The sample data consists of 14 files, so the free allotment of 20 transactions on Foundry Tools is sufficient.
+
+1. Select **Next**.
+
+### Step 3: Configure the index
+
+An index contains your searchable content. The wizard can usually create the schema by sampling the data source. In this step, you review the generated schema and potentially revise any settings.
+
+For this quickstart, the wizard sets reasonable defaults:  
+
++ Default fields are based on metadata properties of existing blobs and new fields for the enrichment output, such as `persons`, `locations`, and `organizations`. Data types are inferred from metadata and by data sampling.
+
+  :::image type="content" source="media/search-get-started-skillset/index-fields-new-wizard.png" alt-text="Screenshot of the index definition page." border="true" lightbox="media/search-get-started-skillset/index-fields-new-wizard.png":::
+
++ Default document key is `metadata_storage_path`, which is selected because the field contains unique values.
+
++ Default field attributes are based on the skills you selected. For example, fields created by the Entity Recognition skill (`persons`, `locations`, and `organizations`) are **Retrievable**, **Filterable**, **Facetable**, and **Searchable**. To view and change these attributes, select a field, and then select **Configure field**.
+
+  **Retrievable** fields can be returned in results, while **Searchable** fields support full-text search. Use **Filterable** if you want to use fields in a filter expression.
+  
+  Marking a field as **Retrievable** doesn't mean that the field *must* appear in search results. You can control which fields are returned by using the `select` query parameter.
+
+After you review the index schema, select **Next**.
+
+### Step 4: Skip advanced settings
+
+The wizard offers advanced settings for semantic ranking and index scheduling, which are beyond the scope of this quickstart. Skip this step by selecting **Next**.
+
+### Step 5: Review and create objects
+
+The last step is to review your configuration and create the index, indexer, and data source on your search service. The indexer automates the process of extracting content from your data source, loading the index, and driving skillset execution.
+
+To review and create the objects:
+
+1. Accept the default **Objects name prefix**.
+
+1. Review the object configurations.
+
+   :::image type="content" source="media/search-get-started-skillset/review-and-create.png" alt-text="Screenshot of the object configuration page in the Azure portal." border="true" lightbox="media/search-get-started-skillset/review-and-create.png":::
+
+   AI enrichment, semantic ranker, and indexer scheduling are either disabled or set to their default values because you skipped their wizard steps.
+
+1. Select **Create** to simultaneously create the objects and run the indexer.
+
+## Monitor status
+
+You can monitor the creation of the indexer in the Azure portal. Skills-based indexing takes longer than text-based indexing, especially OCR and image analysis.
+
+To monitor the progress of the indexer:
+
+1. From the left pane, select **Indexers**.
+
+1. Select your indexer from the list.
+
+1. Select **Success** (or **Failed**) to view execution details.
+
+   :::image type="content" source="media/search-get-started-skillset/indexer-notification.png" alt-text="Screenshot of the indexer status page." border="true" lightbox="media/search-get-started-skillset/indexer-notification.png":::
+
+  In this quickstart, there are a few warnings, including `Could not execute skill because one or more skill input was invalid.` This warning tells you that a PNG file in the data source doesn't provide a text input to Entity Recognition. It occurs because the upstream OCR skill didn't recognize any text in the image and couldn't provide a text input to the downstream Entity Recognition skill.
+
+  Warnings are common in skillset execution. As you become familiar with how skills iterate over your data, you might begin to notice patterns and learn which warnings are safe to ignore.
+
+## Query in Search explorer
+
+To query your index:
+
+1. From the left pane, select **Indexes**.
+
+1. Select your index from the list. If the index has zero documents or storage, wait for the Azure portal to refresh.
+
+1. On the **Search explorer** tab, enter a search string, such as `satya nadella`.
+
+The search bar accepts keywords, quote-enclosed phrases, and operators. For example: `"Satya Nadella" +"Bill Gates" +"Steve Ballmer"`
+
+Results are returned as verbose JSON, which can be hard to read, especially in large documents. Here are tips for searching in this tool:
+    
+   + Switch to the JSON view to specify parameters that shape results.
+   + Add `select` to limit the fields in results.
+   + Add `count` to show the number of matches.
+   + Use Ctrl-F to search within the JSON for specific properties or terms.
+
+:::image type="content" source="media/search-get-started-skillset/search-explorer-new-wizard.png" alt-text="Screenshot of the Search explorer page." border="true" lightbox="media/search-get-started-skillset/search-explorer-new-wizard.png":::
+
+Here's some JSON you can paste into the view:
+    
+```json
+{
+"search": "\"Satya Nadella\" +\"Bill Gates\" +\"Steve Ballmer\"",
+"count": true,
+"select": "merged_content, persons"
+}
+```
+
+> [!TIP]
+> Query strings are case sensitive, so if you get an "unknown field" message, check **Fields** or **Index Definition (JSON)** to verify the name and case.
 
 ## Takeaways
 

@@ -16,7 +16,7 @@ ms.update-cycle: 180-days
 
 For indexes containing chunked documents, an *index projection* specifies how parent-child content is mapped to fields in a search index for one-to-many indexing. Through an index projection, you can send content to:
 
-- A single index, where the parent fields repeat for each chunk, but the grain of the index is at the chunk level. The [RAG tutorial](tutorial-rag-build-solution-index-schema.md) is an example of this approach.
+- A single index, where the parent fields repeat for each chunk, but the grain of the index is at the chunk level. The [classic RAG example](https://github.com/Azure-Samples/azure-search-classic-rag/blob/main/README.md) shows this approach.
 
 - Two or more indexes, where the parent index has fields related to the parent document, and the child index is organized around chunks. The child index is the primary search corpus, but the parent index could be used for [lookup queries](/rest/api/searchservice/documents/get) when you want to retrieve the parent fields of a particular chunk, or for independent queries.
 
@@ -92,7 +92,7 @@ You can use the Azure portal, REST APIs, or an Azure SDK to [create an index](se
 
 #### [**Python**](#tab/python-create-index)
 
-This example is similar to the [RAG tutorial](tutorial-rag-build-solution-index-schema.md). It's an index schema designed for chunked content extracted from a parent document and combines all parent-child fields in the same index.
+This example is similar to the [classic RAG example](https://github.com/Azure-Samples/azure-search-classic-rag/blob/main/README.md). It's an index schema designed for chunked content extracted from a parent document and combines all parent-child fields in the same index.
 
 ```python
  # Create a search index  
@@ -406,7 +406,7 @@ The indexer definition specifies the components of the pipeline. In the indexer
 
 ## Next step
 
-Data chunking and one-to-many indexing are part of the RAG pattern in Azure AI Search. Continue on to the following tutorial and code sample to learn more about it.
+Data chunking and one-to-many indexing are part of the classic RAG pattern in Azure AI Search. Continue on to the following tutorial and code sample to learn more about it.
 
 > [!div class="nextstepaction"]
-> [How to build a RAG solution using Azure AI Search](tutorial-rag-build-solution.md)
+> [How to build a classic RAG solution using Azure AI Search](https://github.com/Azure-Samples/azure-search-classic-rag/blob/main/README.md)

@@ -46,9 +46,9 @@ For integrated vectorization, use one of the following embedding models on an Az
 
 | Provider | Supported models |
 |--|--|
-| [Azure OpenAI in Foundry Models](/azure/ai-services/openai/how-to/create-resource) <sup>1, 2</sup> | text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
+| [Azure OpenAI resource](/azure/ai-services/openai/how-to/create-resource) <sup>1, 2</sup> | text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
 | [Microsoft Foundry resource](/azure/ai-services/multi-service-resource) <sup>3</sup> | For text and images: [Azure Vision multimodal](/azure/ai-services/computer-vision/how-to/image-retrieval) <sup>4</sup></li> |
-<!--| [Foundry model catalog](/azure/ai-foundry/what-is-azure-ai-foundry) | For text:<br>Cohere-embed-v3-english<br>Cohere-embed-v3-multilingual<br><br>For images:<br>Facebook-DinoV2-Image-Embeddings-ViT-Base<br>Facebook-DinoV2-Image-Embeddings-ViT-Giant<br><br>For text and images:<br>Cohere-embed-v4 |-->
+<!--| [Foundry model catalog](/azure/ai-foundry/what-is-azure-ai-foundry) | For text:<br>Cohere-embed-v3-english<br>Cohere-embed-v3-multilingual<br><br><br>For text and images:<br>Cohere-embed-v4 |-->
 
 <sup>1</sup> The endpoint of your Azure OpenAI resource must have a [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains), such as `https://my-unique-name.openai.azure.com`. If you created your resource in the [Azure portal](https://portal.azure.com/), this subdomain was automatically generated during resource setup.
 

@@ -251,7 +251,7 @@ response = openai_client.chat.completions.create(
 print(response.choices[0].message.content)
 ```
 
-For the end-to-end example, see [Quickstart: Generative search (RAG) with grounding data from Azure AI Search](search-get-started-rag.md).
+For the end-to-end example, see [classic RAG in Azure AI Search](https://github.com/Azure-Samples/azure-search-classic-rag/blob/main/README.md).
 
 ## Select complex fields
 
@@ -365,7 +365,7 @@ var combinedCountryCategoryFilter = "(" + countryFilter + " and " + catgFilter +
 
 ```
 
-If you implement the workaround, be sure to test extentively.
+If you implement the workaround, be sure to test extensively.
 
 ## Next steps
 

@@ -1,269 +0,0 @@
----
-title: 'Tutorial: Query from Power Apps'
-titleSuffix: Azure AI Search
-description: Step-by-step guidance on how to build a Power App that connects to an Azure AI Search index, sends queries, and renders results.
-author: HeidiSteen
-ms.author: heidist
-ms.service: azure-ai-search
-ms.topic: tutorial
-ms.date: 04/14/2025
-ms.update-cycle: 365-days
-ms.custom:
-  - ignite-2023
-  - sfi-image-nochange
----
-
-# Tutorial: Query an Azure AI Search index from Power Apps
-
-Use the rapid application development environment of Power Apps to create a custom app for your searchable content in Azure AI Search.
-
-In this tutorial, you learn how to:
-
-> [!div class="checklist"]
-> * Connect to Azure AI Search
-> * Set up a query request
-> * Visualize results in a canvas app
-
-If you don't have an Azure subscription, open a [free account](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn) before you begin.
-
-## Prerequisites
-
-* [Power Apps account](https://make.powerapps.com) with a [premium license](/power-platform/admin/pricing-billing-skus#licenses), such as a Power Apps per apps plan or a Power Apps per user plan.  
-
-* [Hotels-sample index](search-get-started-portal.md) hosted on your search service.
-
-* [Query API key](search-security-api-keys.md#find-existing-keys).
-
-## 1 - Create a custom connector
-
-A connector in Power Apps is a data source connection. In this step, create a custom connector to connect to a search index in the cloud.
-
-1. [Sign in](https://make.powerapps.com) to Power Apps.
-
-1. On the left, select **Custom Connectors**.
-
-    :::image type="content" source="./media/search-howto-powerapps/1-2-custom-connector.png" alt-text="Custom connector menu" border="true":::
-
-1. Select  **+ New custom connector**, and then select **Create from blank**.
-
-    :::image type="content" source="./media/search-howto-powerapps/1-3-create-blank.png" alt-text="Create from blank menu" border="true":::
-
-1. Give your custom connector a name (for example, *AzureSearchQuery*), and then select **Continue**.
-
-1. Enter information in the General Page:
-
-   * Icon background color (for instance, #007ee5)
-   * Description (for instance, "A connector to Azure AI Search")
-   * In the Host, enter your search service URL (such as `<yourservicename>.search.windows.net`)
-   * For Base URL, enter "/"
-
-    :::image type="content" source="./media/search-howto-powerapps/1-5-general-info.png" alt-text="General information dialogue" border="true":::
-
-1. In the Security Page, set *API Key* as the **Authentication Type**, set both the parameter label and parameter name to *api-key*. For **Parameter location**, select *Header* as shown in the following screenshot.
-
-    :::image type="content" source="./media/search-howto-powerapps/1-6-authentication-type.png" alt-text="Authentication type option" border="true":::
-
-1. In the Definitions Page, select **+ New Action** to create an action that queries the index. Enter the value "Query" for the summary and the name of the operation ID. Enter a description like *"Queries the search index"*.
-
-    :::image type="content" source="./media/search-howto-powerapps/1-7-new-action.png" alt-text="New action options" border="true":::
-
-1. Scroll down. In Requests, select **+ Import from sample** button to configure a query request to your search service:
-
-   * Select the verb `GET`
-
-   * For the URL, enter a sample query for your search index (`search=*` returns all documents, `$select=` lets you choose fields). The API version is required. Fully specified, a URL might look like the following example. Notice that the `https://` prefix is omitted.
-
-     ```http
-     mydemo.search.windows.net/indexes/hotels-sample-index/docs?search=*&$select=HotelName,Description,Address/City&api-version=2025-09-01
-     ```
-
-   * For Headers, type `Content-Type application/json`.
-
-     **Power Apps** uses the syntax in the URL to extract parameters from the query: search, select, and api-version parameters become configurable as you progress through the wizard.
-
-       :::image type="content" source="./media/search-howto-powerapps/1-8-1-import-from-sample.png" alt-text="Import from sample" border="true":::
-
-1. Select **Import** to autofill the Request. Complete setting the parameter metadata by clicking the **...** symbol next to each of the parameters. Select **Back** to return to the Request page after each parameter update.
-
-   :::image type="content" source="./media/search-howto-powerapps/1-8-2-import-from-sample.png" alt-text="Import from sample dialogue" border="true":::
-
-1. For *search*: Set `*` as the **default value**, set **required** as *False* and set **visibility** to *none*. 
-
-    :::image type="content" source="./media/search-howto-powerapps/1-10-1-parameter-metadata-search.png" alt-text="Search parameter metadata" border="true":::
-
-1. For *select*: Set `HotelName,Description,Address/City` as the **default value**, set **required** to *False*, and set **visibility** to *none*.  
-
-    :::image type="content" source="./media/search-howto-powerapps/1-10-4-parameter-metadata-select.png" alt-text="Select parameter metadata" border="true":::
-
-1. For *api-version*: Set `2025-09-01` as the **default value**, set **required** to *True*, and set **visibility** as *internal*.  
-
-    :::image type="content" source="./media/search-howto-powerapps/1-10-2-parameter-metadata-version.png" alt-text="Version parameter metadata" border="true":::
-
-1. For *Content-Type*: Set to `application/json`.
-
-1. After making these changes, toggle to the **Swagger Editor** view. In the parameters section you should see the following configuration:
-
-    ```JSON
-    parameters:
-      - {name: search, in: query, required: false, type: string, default: '*'}
-      - {name: $select, in: query, required: false, type: string, default: 'HotelName,Description,Address/City'}
-      - {name: api-version, in: query, required: true, type: string, default: '2025-09-01',
-        x-ms-visibility: internal}
-      - {name: Content-Type, in: header, required: false, type: string}
-    ```
-
-1. Switch back to the wizard and return to the **3. Definition** step. Scroll down to the Response section. Select **"Add default response"**. This step is critical because it helps Power Apps understand the schema of the response. 
-
-1. Paste a sample response. An easy way to capture a sample response is through Search Explorer in the Azure portal. In Search Explorer, you should enter the same query as you did for the request, but add **$top=2** to constrain results to just two documents: `search=*&$select=HotelName,Description,Address/City&$top=2`. 
-
-   Power Apps only needs a few results to detect the schema. You can copy the following response into the wizard now, assuming you're using the hotels-sample-index.
-
-    ```JSON
-    {
-        "@odata.context": "https://mydemo.search.windows.net/indexes('hotels-sample-index')/$metadata#docs(*)",
-        "value": [
-            {
-                "@search.score": 1,
-                "HotelName": "Happy Lake Resort & Restaurant",
-                "Description": "The largest year-round resort in the area offering more of everything for your vacation – at the best value!  What can you enjoy while at the resort, aside from the mile-long sandy beaches of the lake? Check out our activities sure to excite both young and young-at-heart guests. We have it all, including being named “Property of the Year” and a “Top Ten Resort” by top publications.",
-                "Address": {
-                    "City": "Seattle"
-                }
-            },
-            {
-                "@search.score": 1,
-                "HotelName": "Grand Gaming Resort",
-                "Description": "The Best Gaming Resort in the area.  With elegant rooms & suites, pool, cabanas, spa, brewery & world-class gaming.  This is the best place to play, stay & dine.",
-                "Address": {
-                    "City": "Albuquerque"
-                }
-            }
-        ]
-    }
-    ```
-
-    > [!TIP] 
-    > There's a character limit to the JSON response you can enter, so you might want to simplify the JSON before pasting it. The schema and format of the response is more important than the values themselves. For example, the Description field could be simplified to just the first sentence.
-
-1. Select **Import** to add the default response.
-
-1. Select **Create connector** on the top right to save the definition.
-
-1. Select **Close** to close the connector.
-
-## 2 - Test the connection
-
-When the connector is first created, you need to reopen it from the Custom Connectors list in order to test it. Later, if you make more updates, you can test from within the wizard.
-
-Provide a [query API key](search-security-api-keys.md#find-existing-keys) for this task. Each time a connection is created, whether for a test run or inclusion in an app, the connector needs the query API key used for connecting to Azure AI Search.
-
-1. On the far left, select **Custom Connectors**.
-
-1. Find your connector in the list (in this tutorial, is "AzureSearchQuery").
-
-1. Select the connector, expand the actions list, and select **View Properties**.
-
-    :::image type="content" source="./media/search-howto-powerapps/1-11-1-test-connector.png" alt-text="View Properties" border="true":::
-
-1. In the drop-down list of operations, select **6. Test**.
-
-1. In **Test Operation**, select **+ New Connection**.
-
-1. Enter a query API key. This is an Azure AI Search query for read-only access to an index. You can [find the key](search-security-api-keys.md#find-existing-keys) in the Azure portal. 
-
-1. In Operations, select the **Test operation** button. If you're successful you should see a 200 status, and in the body of the response you should see JSON that describes the search results.
-
-    :::image type="content" source="./media/search-howto-powerapps/1-11-2-test-connector.png" alt-text="JSON response" border="true":::
-
-If the test fails, recheck the inputs. In particular, revisit the sample response and make sure it was created properly. The connector definition should show the expected items for the response.
-
-If you're blocked by a Data Loss Prevention (DLP) policy error, review the error message for guidance. You might be able to modify the policy or make your connector nonblockable.
-
-## 3 - Visualize results
-
-In this step, create a Power App with a search box, a search button, and a display area for the results. The Power App will connect to the recently created custom connector to get the data from Azure Search.
-
-1. On the left, expand **Apps** > **New app** > **Start with a page design**.
-
-1. Select a **Blank canvas** with the **Phone Layout**. Give the app a name, such as "Hotel Finder". Select **Create**. The **Power Apps Studio** appears.
-
-1. In the studio, select the **Data** tab, select **Add data**, and then find the new Connector you have just created. In this tutorial, it's called *AzureSearchQuery*. Select **Add a connection**.
-
-   Enter the query API key.
-
-    :::image type="content" source="./media/search-howto-powerapps/2-3-connect-connector.png" alt-text="connect connector" border="true":::
-
-    Now *AzureSearchQuery* is a data source that is available to be used from your application.
-
-1. On the **Insert tab**, add a few controls to the canvas.
-
-    :::image type="content" source="./media/search-howto-powerapps/2-4-add-controls.png" alt-text="Insert controls" border="true":::
-
-1. Insert the following elements:
-
-   * A Text Label with the value "Query:"
-   * A Text Input element (call it *txtQuery*, default value: "*")
-   * A button with the text "Search" 
-   * A Vertical Gallery called (call it *galleryResults*)
-
-    The canvas should look something like this:
-
-    :::image type="content" source="./media/search-howto-powerapps/2-5-controls-layout.png" alt-text="Controls layout" border="true":::
-
-1. To make the **Search button** issue a query, paste the following action into **OnSelect**:
-
-    ```
-    If(!IsBlank(txtQuery.Text),
-        ClearCollect(azResult, AzureSearchQuery.Query({search: txtQuery.Text}).value))
-    ```
-
-   The following screenshot shows the formula bar for the **OnSelect** action.
-
-    :::image type="content" source="./media/search-howto-powerapps/2-6-search-button-event.png" alt-text="Button OnSelect" border="true":::
-
-   This action causes the button to update a new collection called *azResult* with the result of the search query, using the text in the *txtQuery* text box as the query term.
-
-   > [!NOTE]
-   > Try this if you get a formula syntax error "The function 'ClearCollect' has some invalid functions":
-   > 
-   > * First, make sure the connector reference is correct. Clear the connector name and begin typing the name of your connector. Intellisense should suggest the right connector and verb.
-   > 
-   > * If the error persists, delete and recreate the connector. If there are multiple instances of a connector, the app might be using the wrong one.
-   > 
-
-1. Link the Vertical Gallery control to the *azResult* collection that was created when you completed the previous step. 
-
-   Select the gallery control, and perform the following actions in the properties pane.
-
-   * Set **DataSource** to *azResult*.
-   * Select a **Layout** that works for you based on the type of data in your index. In this case, we used the *Title, subtitle and body* layout.
-   * **Edit Fields**, and select the fields you would like to visualize.
-
-    Since we provided a sample result when we defined the connector, the app is aware of the fields available in your index.
-    
-    :::image type="content" source="./media/search-howto-powerapps/2-7-gallery-select-fields.png" alt-text="Gallery fields" border="true":::   
- 
-1. Press **F5** to preview the app.  
-
-    :::image type="content" source="./media/search-howto-powerapps/2-8-3-final.png" alt-text="Final app" border="true":::    
-
-<!--     Remember that the fields can be set to calculated values.
-
-    For the example, setting using the *"Image, Title and Subtitle"* layout and specifying the *Image* function as the concatenation of the root path for the data and the file name (for instance, `"https://mystore.blob.core.windows.net/multilang/" & ThisItem.metadata_storage_name`) will produce the result below.
-
-    :::image type="content" source="./media/search-howto-powerapps/2-8-2-final.png" alt-text="Final app" border="true":::         -->
-
-## Clean up resources
-
-When you're working in your own subscription, it's a good idea at the end of a project to identify whether you still need the resources you created. Resources left running can cost you money. You can delete resources individually or delete the resource group to delete the entire set of resources.
-
-You can find and manage resources in the Azure portal, using the **All resources** or **Resource groups** link in the left-navigation pane.
-
-Remember that a free search service is limited to three indexes, indexers, and data sources. You can delete individual items in the Azure portal to stay under the limit.
-
-## Next steps
-
-Power Apps enables the rapid application development of custom apps. Now that you know how to connect to a search index, learn more about creating a rich visualize experience in a custom Power App.
-
-> [!div class="nextstepaction"]
-> [Power Apps Learning Catalog](/powerapps/learning-catalog/bdm#get-started)

@@ -383,6 +383,4 @@ To quickly generate a search page for your client, consider these options:
 
 + [Create demo app](search-create-app-portal.md), in the Azure portal, creates an HTML page with a search bar, faceted navigation, and a thumbnail area if you have images.
 
-+ [Add search to an ASP.NET Core (MVC) app](tutorial-csharp-create-mvc-app.md) is a tutorial and code sample that builds a functional client.
-
 + [Add search to web apps](tutorial-csharp-overview.md) is a C# tutorial and code sample that uses the React JavaScript libraries for the user experience. The app is deployed using Azure Static Web Apps and it implements pagination.

@@ -7,7 +7,7 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.update-cycle: 180-days
-ms.topic: conceptual
+ms.topic: article
 ms.date: 11/06/2025
 ms.custom: references_regions
 ---
@@ -94,7 +94,7 @@ Try the Azure portal quickstarts for Azure AI Search or quickstarts that use Vis
 - [Quickstart: Vector search in the Azure portal](search-get-started-portal-import-vectors.md)
 - [Quickstart: Image search in the Azure portal](search-get-started-portal-image-search.md)
 - [Quickstart: Keyword in the Azure portal](search-get-started-portal.md)
-- [Quickstart: Generative search (RAG) using a Python client](search-get-started-rag.md)
+- [Quickstart: Agentic retrieval](search-get-started-agentic-retrieval.md)
 - [Quickstart: Vector search using a REST client](search-get-started-vector.md)
 
 Foundry supports connecting to content in Azure AI Search.

@@ -165,7 +165,7 @@ All indexing and query requests target an index. Endpoints are usually one of th
 
    + [Quickstart: REST](search-get-started-text.md)
    + [Quickstart: Full-text search](search-get-started-text.md)
-   + [Quickstart: RAG (using Visual Studio Code and a Jupyter notebook)](search-get-started-rag.md)
+   + [Quickstart: Agentic retrieval](search-get-started-agentic-retrieval.md)
 
 ## Next steps
 

@@ -108,8 +108,6 @@ items:
   items:
   - name: Dev tutorials
     items:
-    - name: Add search to ASP.NET Core (MVC)
-      href: tutorial-csharp-create-mvc-app.md
     - name: Add search to static web apps
       items:
       - name: Overview
@@ -120,8 +118,6 @@ items:
         href: tutorial-csharp-deploy-static-web-app.md
       - name: Explore the code
         href: tutorial-csharp-search-query-integration.md
-    - name: Query from Power Apps
-      href: search-howto-powerapps.md
   - name: Indexing tutorials
     items:
     - name: Index any data
@@ -156,22 +152,6 @@ items:
       href: tutorial-document-layout-image-verbalization.md
   - name: Agentic retrieval tutorial
     href: agentic-retrieval-how-to-create-pipeline.md
-  - name: Classic RAG tutorials
-    items:
-    - name: Build a classic RAG solution
-      href: tutorial-rag-build-solution.md
-    - name: Choose models
-      href: tutorial-rag-build-solution-models.md
-    - name: Design an index
-      href: tutorial-rag-build-solution-index-schema.md
-    - name: Build an indexing pipeline
-      href: tutorial-rag-build-solution-pipeline.md
-    - name: Search and generate answers
-      href: tutorial-rag-build-solution-query.md
-    - name: Maximize relevance
-      href: tutorial-rag-build-solution-maximize-relevance.md
-    - name: Minimize storage and costs
-      href: tutorial-rag-build-solution-minimize-storage.md
   - name: Skills tutorials
     items:
     - name: Create a skillset

@@ -1,482 +0,0 @@
----
-title: Add search to ASP.NET Core MVC
-titleSuffix: Azure AI Search
-description: In this Azure AI Search tutorial, learn how to add search to an ASP.NET Core (Model-View-Controller) application.
-manager: nitinme
-author: HeidiSteen
-ms.author: heidist
-ms.service: azure-ai-search
-ms.update-cycle: 180-days
-ms.devlang: csharp
-ms.custom:
-  - ignite-2023
-ms.topic: tutorial
-ms.date: 12/05/2025
----
-
-# Create a search app in ASP.NET Core
-
-In this tutorial, you create a basic ASP.NET Core (Model-View-Controller) app that runs in localhost and connects to the [hotels-sample-index](search-get-started-portal.md) on your search service. You learn how to:
-
-> [!div class="checklist"]
-> + Create a basic search page
-> + Filter results
-> + Sort results
-
-This tutorial focuses on server-side operations called through the [Search APIs](/dotnet/api/overview/azure/search.documents-readme). Although it's common to sort and filter in client-side script, knowing how to invoke these operations on the server gives you more options when designing the search experience.
-
-You can find sample code for this tutorial in the [azure-search-dotnet-samples](https://github.com/Azure-Samples/azure-search-dotnet-samples/tree/main/create-mvc-app) repository on GitHub. 
-
-## Prerequisites
-
-+ [Visual Studio](https://visualstudio.microsoft.com/downloads/)
-+ [Azure.Search.Documents NuGet package](https://www.nuget.org/packages/Azure.Search.Documents/)
-+ [Azure AI Search](search-create-service-portal.md), any tier, but it must have public network access. 
-+ [Hotel samples index](search-get-started-portal.md)
-
-[Step through the Import data wizard](search-get-started-portal.md) to create the hotels-sample-index on your search service. Or, change the index name in the `HomeController.cs` file.
-
-## Create the project
-
-1. Start Visual Studio and select **Create a new project**.
-
-1. Select **ASP.NET Core Web App (Model-View-Controller)**, and then select **Next**.
-
-1. Enter a project name, and then select **Next**.
-
-1. On the next page, select **.NET 9.0**.
-
-1. Accept the default settings.
-
-1. Select **Create**.
-
-### Add NuGet packages
-
-1. On the **Tools** menu, select **NuGet Package Manager** > **Manage NuGet Packages for the solution**.
-
-1. Browse for `Azure.Search.Documents` and install the latest stable version.
-
-1. Browse for and install the `Microsoft.Spatial` package. The sample index includes a `GeographyPoint` data type. Installing this package avoids run time errors. Alternatively, remove the "Location" field from the `Hotels` class if you don't want to install the package. That field isn't used in this tutorial.
-
-### Add service information
-
-For the connection, the app presents a query API key to your fully qualified search URL. Both are specified in the `appsettings.json` file.
-
-Modify `appsettings.json` to specify your search service and [query API key](search-security-api-keys.md).
-
-```json
-{
-    "SearchServiceUri": "<YOUR-SEARCH-SERVICE-URL>",
-    "SearchServiceQueryApiKey": "<YOUR-SEARCH-SERVICE-QUERY-API-KEY>"
-}
-```
-
-You can get the service URL and API key from the Azure portal. Because this code is querying an index and not creating one, you can use a query key instead of an admin key.
-
-Make sure to specify a search service that has the `hotels-sample-index`.
-
-## Add models
-
-In this step, you create models that represent the schema of the hotels-sample-index.
-
-1. In Solution Explorer, right-select **Models** and add a new class named "Hotel" for the following code:
-
-   ```csharp
-    using Azure.Search.Documents.Indexes.Models;
-    using Azure.Search.Documents.Indexes;
-    using Microsoft.Spatial;
-    using System.Text.Json.Serialization;
-    
-    namespace HotelDemoApp.Models
-    {
-        public partial class Hotel
-        {
-            [SimpleField(IsFilterable = true, IsKey = true)]
-            public string HotelId { get; set; }
-    
-            [SearchableField(IsSortable = true)]
-            public string HotelName { get; set; }
-    
-            [SearchableField(AnalyzerName = LexicalAnalyzerName.Values.EnLucene)]
-            public string Description { get; set; }
-    
-            [SearchableField(AnalyzerName = LexicalAnalyzerName.Values.FrLucene)]
-            [JsonPropertyName("Description_fr")]
-            public string DescriptionFr { get; set; }
-    
-            [SearchableField(IsFilterable = true, IsSortable = true, IsFacetable = true)]
-            public string Category { get; set; }
-    
-            [SearchableField(IsFilterable = true, IsFacetable = true)]
-            public string[] Tags { get; set; }
-    
-            [SimpleField(IsFilterable = true, IsSortable = true, IsFacetable = true)]
-            public bool? ParkingIncluded { get; set; }
-    
-            [SimpleField(IsFilterable = true, IsSortable = true, IsFacetable = true)]
-            public DateTimeOffset? LastRenovationDate { get; set; }
-    
-            [SimpleField(IsFilterable = true, IsSortable = true, IsFacetable = true)]
-            public double? Rating { get; set; }
-    
-            public Address Address { get; set; }
-    
-            [SimpleField(IsFilterable = true, IsSortable = true)]
-            public GeographyPoint Location { get; set; }
-    
-            public Rooms[] Rooms { get; set; }
-        }
-    }
-   ```
-
-1. Add a class named "Address" and replace it with the following code:
-
-   ```csharp
-    using Azure.Search.Documents.Indexes;
-
-    namespace HotelDemoApp.Models
-    {
-        public partial class Address
-        {
-            [SearchableField]
-            public string StreetAddress { get; set; }
-    
-            [SearchableField(IsFilterable = true, IsSortable = true, IsFacetable = true)]
-            public string City { get; set; }
-    
-            [SearchableField(IsFilterable = true, IsSortable = true, IsFacetable = true)]
-            public string StateProvince { get; set; }
-    
-            [SearchableField(IsFilterable = true, IsSortable = true, IsFacetable = true)]
-            public string PostalCode { get; set; }
-    
-            [SearchableField(IsFilterable = true, IsSortable = true, IsFacetable = true)]
-            public string Country { get; set; }
-        }
-    }
-   ```
-
-1. Add a class named "Rooms" and replace it with the following code:
-
-   ```csharp
-    using Azure.Search.Documents.Indexes.Models;
-    using Azure.Search.Documents.Indexes;
-    using System.Text.Json.Serialization;
-    
-    namespace HotelDemoApp.Models
-    {
-        public partial class Rooms
-        {
-            [SearchableField(AnalyzerName = LexicalAnalyzerName.Values.EnMicrosoft)]
-            public string Description { get; set; }
-    
-            [SearchableField(AnalyzerName = LexicalAnalyzerName.Values.FrMicrosoft)]
-            [JsonPropertyName("Description_fr")]
-            public string DescriptionFr { get; set; }
-    
-            [SearchableField(IsFilterable = true, IsFacetable = true)]
-            public string Type { get; set; }
-    
-            [SimpleField(IsFilterable = true, IsFacetable = true)]
-            public double? BaseRate { get; set; }
-    
-            [SearchableField(IsFilterable = true, IsFacetable = true)]
-            public string BedOptions { get; set; }
-    
-            [SimpleField(IsFilterable = true, IsFacetable = true)]
-            public int SleepsCount { get; set; }
-    
-            [SimpleField(IsFilterable = true, IsFacetable = true)]
-            public bool? SmokingAllowed { get; set; }
-    
-            [SearchableField(IsFilterable = true, IsFacetable = true)]
-            public string[] Tags { get; set; }
-        }
-    }
-   ```
-
-1. Add a class named "SearchData" and replace it with the following code:
-
-   ```csharp
-    using Azure.Search.Documents.Models;
-
-    namespace HotelDemoApp.Models
-    {
-        public class SearchData
-        {
-            // The text to search for.
-            public string searchText { get; set; }
-    
-            // The list of results.
-            public SearchResults<Hotel> resultList;
-        }
-    }
-   ```
-
-## Modify the controller
-
-For this tutorial, modify the default `HomeController` to contain methods that execute on your search service.
-
-1. In Solution Explorer under **Models**, open `HomeController`.
-
-1. Replace the default content with the following code:
-
-   ```csharp
-   using Azure;
-    using Azure.Search.Documents;
-    using Azure.Search.Documents.Indexes;
-    using HotelDemoApp.Models;
-    using Microsoft.AspNetCore.Mvc;
-    using System.Diagnostics;
-    
-    namespace HotelDemoApp.Controllers
-    {
-        public class HomeController : Controller
-        {
-            public IActionResult Index()
-            {
-                return View();
-            }
-    
-            [HttpPost]
-            public async Task<ActionResult> Index(SearchData model)
-            {
-                try
-                {
-                    // Check for a search string
-                    if (model.searchText == null)
-                    {
-                        model.searchText = "";
-                    }
-    
-                    // Send the query to Search.
-                    await RunQueryAsync(model);
-                }
-    
-                catch
-                {
-                    return View("Error", new ErrorViewModel { RequestId = "1" });
-                }
-                return View(model);
-            }
-    
-            [ResponseCache(Duration = 0, Location = ResponseCacheLocation.None, NoStore = true)]
-            public IActionResult Error()
-            {
-                return View(new ErrorViewModel { RequestId = Activity.Current?.Id ?? HttpContext.TraceIdentifier });
-            }
-    
-            private static SearchClient _searchClient;
-            private static SearchIndexClient _indexClient;
-            private static IConfigurationBuilder _builder;
-            private static IConfigurationRoot _configuration;
-    
-            private void InitSearch()
-            {
-                // Create a configuration using appsettings.json
-                _builder = new ConfigurationBuilder().AddJsonFile("appsettings.json");
-                _configuration = _builder.Build();
-    
-                // Read the values from appsettings.json
-                string searchServiceUri = _configuration["SearchServiceUri"];
-                string queryApiKey = _configuration["SearchServiceQueryApiKey"];
-    
-                // Create a service and index client.
-                _indexClient = new SearchIndexClient(new Uri(searchServiceUri), new AzureKeyCredential(queryApiKey));
-                _searchClient = _indexClient.GetSearchClient("hotels-sample-index");
-            }
-    
-            private async Task<ActionResult> RunQueryAsync(SearchData model)
-            {
-                InitSearch();
-    
-                var options = new SearchOptions()
-                {
-                    IncludeTotalCount = true
-                };
-    
-                // Enter Hotel property names to specify which fields are returned.
-                // If Select is empty, all "retrievable" fields are returned.
-                options.Select.Add("HotelName");
-                options.Select.Add("Category");
-                options.Select.Add("Rating");
-                options.Select.Add("Tags");
-                options.Select.Add("Address/City");
-                options.Select.Add("Address/StateProvince");
-                options.Select.Add("Description");
-    
-                // For efficiency, the search call should be asynchronous, so use SearchAsync rather than Search.
-                model.resultList = await _searchClient.SearchAsync<Hotel>(model.searchText, options).ConfigureAwait(false);
-    
-                // Display the results.
-                return View("Index", model);
-            }
-            public IActionResult Privacy()
-            {
-                return View();
-            }
-        }
-    }
-   ```
-
-## Modify the view
-
-1. In Solution explorer, under **Views** > **Home**, open `index.cshtml`.
-
-1. Replace the default content with the following code:
-
-    ```razor
-    @model HotelDemoApp.Models.SearchData;
-    
-    @{
-        ViewData["Title"] = "Index";
-    }
-    
-    <div>
-        <h2>Search for Hotels</h2>
-    
-        <p>Use this demo app to test server-side sorting and filtering. Modify the RunQueryAsync method to change the operation. The app uses the default search configuration (simple search syntax, with searchMode=Any).</p>
-    
-        <form asp-controller="Home" asp-action="Index">
-            <p>
-                <input type="text" name="searchText" />
-                <input type="submit" value="Search" />
-            </p>
-        </form>
-    </div>
-    
-    <div>
-        @using (Html.BeginForm("Index", "Home", FormMethod.Post))
-        {
-            @if (Model != null)
-            {
-                // Show the result count.
-                <p>@Model.resultList.TotalCount Results</p>
-    
-                // Get search results.
-                var results = Model.resultList.GetResults().ToList();
-    
-                {
-                    <table class="table">
-                        <thead>
-                            <tr>
-                                <th>Name</th>
-                                <th>Category</th>
-                                <th>Rating</th>
-                                <th>Tags</th>
-                                <th>City</th>
-                                <th>State</th>
-                                <th>Description</th>
-                            </tr>
-                        </thead>
-                        <tbody>
-                            @foreach (var d in results)
-                            {
-                                <tr>
-                                    <td>@d.Document.HotelName</td>
-                                    <td>@d.Document.Category</td>
-                                    <td>@d.Document.Rating</td>
-                                    <td>@d.Document.Tags[0]</td>
-                                    <td>@d.Document.Address.City</td>
-                                    <td>@d.Document.Address.StateProvince</td>
-                                    <td>@d.Document.Description</td>
-                                </tr>
-                            }
-                        </tbody>
-                      </table>
-                }
-            }
-        }
-    </div>
-    ```
-
-## Run the sample
-
-1. Press **F5** to compile and run the project. The app runs on localhost and opens in your default browser.
-
-1. Select **Search** to return all results.
-
-1. This code uses the default search configuration, supporting the [simple syntax](query-simple-syntax.md) and `searchMode=Any`. You can enter keywords, augment with Boolean operators, or run a prefix search (`pool*`).
-
-In the next several sections, modify the **RunQueryAsync** method in the `HomeController` to add filters and sorting.
-
-## Filter results
-
-Index field attributes determine which fields are searchable, filterable, sortable, facetable, and retrievable. In the hotels-sample-index, filterable fields include Category, Address/City, and Address/StateProvince. This example adds a [$Filter](search-query-odata-filter.md) expression on Category.
-
-A filter always executes first, followed by a query, assuming you specify one.
-
-1. Open the `HomeController` and find the **RunQueryAsync** method. Add [Filter](/dotnet/api/azure.search.documents.searchoptions.filter) to `var options = new SearchOptions()`:
-
-   ```csharp
-    private async Task<ActionResult> RunQueryAsync(SearchData model)
-    {
-        InitSearch();
-
-        var options = new SearchOptions()
-        {
-            IncludeTotalCount = true,
-            Filter = "search.in(Category,'Budget,Suite')"
-        };
-
-        options.Select.Add("HotelName");
-        options.Select.Add("Category");
-        options.Select.Add("Rating");
-        options.Select.Add("Tags");
-        options.Select.Add("Address/City");
-        options.Select.Add("Address/StateProvince");
-        options.Select.Add("Description");
-
-        model.resultList = await _searchClient.SearchAsync<Hotel>(model.searchText, options).ConfigureAwait(false);
-
-        return View("Index", model);
-    }
-   ```
-
-1. Run the application.
-
-1. Select **Search** to run an empty query. The filter returns 18 documents instead of the original 50.
-
-For more information about filter expressions, see [Filters in Azure AI Search](search-filters.md) and [OData $filter syntax in Azure AI Search](search-query-odata-filter.md).
-
-## Sort results
-
-In the hotels-sample-index, sortable fields include Rating and LastRenovated. This example adds an [$OrderBy](/dotnet/api/azure.search.documents.searchoptions.orderby) expression to the Rating field.
-
-1. Open the `HomeController` and replace the **RunQueryAsync** method with the following version:
-
-   ```csharp
-    private async Task<ActionResult> RunQueryAsync(SearchData model)
-    {
-        InitSearch();
-    
-        var options = new SearchOptions()
-        {
-            IncludeTotalCount = true,
-        };
-    
-        options.OrderBy.Add("Rating desc");
-    
-        options.Select.Add("HotelName");
-        options.Select.Add("Category");
-        options.Select.Add("Rating");
-        options.Select.Add("Tags");
-        options.Select.Add("Address/City");
-        options.Select.Add("Address/StateProvince");
-        options.Select.Add("Description");
-
-        model.resultList = await _searchClient.SearchAsync<Hotel>(model.searchText, options).ConfigureAwait(false);
-    
-        return View("Index", model);
-    }
-   ```
-
-1. Run the application. Results are sorted by Rating in descending order.
-
-For more information about sorting, see [OData $orderby syntax in Azure AI Search](search-query-odata-orderby.md).
-
-## Next step
-
-In this tutorial, you created an ASP.NET Core (MVC) project that connects to a search service and calls Search APIs for server-side filtering and sorting.
-
-To add client-side code that responds to user actions, use a React template in your solution: [C# Tutorial: Add search to a website with .NET](tutorial-csharp-overview.md).

@@ -1,215 +0,0 @@
----
-title: 'Classic RAG tutorial: Design an index'
-titleSuffix: Azure AI Search
-description: Design an index for RAG patterns in Azure AI Search.
-manager: nitinme
-author: HeidiSteen
-ms.author: heidist
-ms.service: azure-ai-search
-ms.update-cycle: 180-days
-ms.topic: tutorial
-ms.date: 10/14/2025
-
----
-
-# Tutorial: Design an index for classic RAG in Azure AI Search
-
-An index contains searchable text and vector content, plus configurations. In a RAG pattern that uses a chat model for responses, you want an index designed around chunks of content that can be passed to an LLM at query time. 
-
-> [!NOTE]
-> We now recommend [agentic retrieval](agentic-retrieval-overview.md) for RAG workflows, but classic RAG is simpler. If it meets your application requirements, it's still a good choice.
-
-In this tutorial, you:
-
-> [!div class="checklist"]
-> - Learn the characteristics of an index schema built for RAG
-> - Create an index that accommodates vector and hybrid queries
-> - Add vector profiles and configurations
-> - Add structured data
-> - Add filtering
-
-## Prerequisites
-
-[Visual Studio Code](https://code.visualstudio.com/download) with the [Python extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python) and the [Jupyter package](https://pypi.org/project/jupyter/). For more information, see [Python in Visual Studio Code](https://code.visualstudio.com/docs/languages/python).
-
-The output of this exercise is an index definition in JSON. At this point, it's not uploaded to Azure AI Search, so there are no requirements for cloud services or permissions in this exercise.
-
-## Review schema considerations for RAG
-
-In conversational search, LLMs compose the response that the user sees, not the search engine, so you don't need to think about what fields to show in your search results, and whether the representations of individual search documents are coherent to the user. Depending on the question, the LLM might return verbatim content from your index, or more likely, repackage the content for a better answer.
-
-### Organized around chunks
-
-When LLMs generate a response, they operate on chunks of content for message inputs, and while they need to know where the chunk came from for citation purposes, what matters most is the quality of message inputs and its relevance to the user's question. Whether the chunks come from one document or a thousand, the LLM ingests the information or *grounding data*, and formulates the response using instructions provided in a system prompt.
-
-Chunks are the focus of the schema, and each chunk is the defining element of a search document in a RAG pattern. You can think of your index as a large collection of chunks, as opposed to traditional search documents that probably have more structure, such as fields containing uniform content for a name, descriptions, categories, and addresses.
-
-### Enhanced with generated data
-
-In this tutorial, sample data consists of PDFs and content from the [NASA Earth Book](https://www.nasa.gov/ebooks/earth/). This content is descriptive and informative, with numerous references to geographies, countries, and areas across the world. All of the textual content is captured in chunks, but recurring instances of place names create an opportunity for adding structure to the index. Using skills, it's possible to recognize entities in the text and capture them in an index for use in queries and filters. In this tutorial, we include an [entity recognition skill](cognitive-search-skill-entity-recognition-v3.md) that recognizes and extracts location entities, loading it into a searchable and filterable `locations` field. Adding structured content to your index gives you more options for filtering, improved relevance, and more focused answers.
-
-### Parent-child fields in one or two indexes?
-
-Chunked content typically derives from a larger document. And although the schema is organized around chunks, you also want to capture properties and content at the parent level. Examples of these properties might include the parent file path, title, authors, publication date, or a summary.
-
-An inflection point in schema design is whether to have two indexes for parent and child/chunked content, or a single index that repeats parent elements for each chunk.
-
-In this tutorial, because all of the chunks of text originate from a single parent (NASA Earth Book), you don't need a separate index dedicated to up level the parent fields. However, if you're indexing from multiple parent PDFs, you might want a parent-child index pair to capture level-specific fields and then send [lookup queries](/rest/api/searchservice/documents/get) to the parent index to retrieve those fields relevant to each chunk.
-
-### Checklist of schema considerations
-
-In Azure AI Search, an index that works best for RAG workloads has these qualities:
-
-- Returns chunks that are relevant to the query and readable to the LLM. LLMs can handle a certain level of dirty data in chunks, such as mark up, redundancy, and incomplete strings. While chunks need to be readable and relevant to the question, they don't need to be pristine.
-
-- Maintains a parent-child relationship between chunks of a document and the properties of the parent document, such as the file name, file type, title, author, and so forth. To answer a query, chunks could be pulled from anywhere in the index. Association with the parent document providing the chunk is useful for context, citations, and follow up queries.
-
-- Accommodates the queries you want create. You should have fields for vector and hybrid content, and those fields should be attributed to support specific query behaviors, such as searchable or filterable. You can only query one index at a time (no joins) so your fields collection should define all of your searchable content.
-
-- Your schema should either be flat (no complex types or structures), or you should [format the complext type output as JSON](search-get-started-rag.md#send-a-complex-rag-query) before sending it to the LLM. This requirement is specific to the RAG pattern in Azure AI Search.
-
-> [!NOTE]
-> Schema design affects storage and costs. This exercise is focused on schema fundamentals. In the [Minimize storage and costs](tutorial-rag-build-solution-minimize-storage.md) tutorial, you revisit schemas to learn how narrow data types, compression, and storage options significantly reduce the amount of storage used by vectors.
-
-## Create an index for RAG workloads
-
-A minimal index for LLM is designed to store chunks of content. It typically includes vector fields if you want similarity search for highly relevant results. It also includes nonvector fields for human-readable inputs to the LLM for conversational search. Nonvector chunked content in the search results becomes the grounding data sent to the LLM.
-
-1. Open Visual Studio Code and create a new file. It doesn't have to be a Python file type for this exercise.
-
-1. Here's a minimal index definition for RAG solutions that support vector and hybrid search. Review it for an introduction to required elements: index name, fields, and a configuration section for vector fields.
-
-    ```json
-    {
-      "name": "example-minimal-index",
-      "fields": [
-        { "name": "id", "type": "Edm.String", "key": true },
-        { "name": "chunked_content", "type": "Edm.String", "searchable": true, "retrievable": true },
-        { "name": "chunked_content_vectorized", "type": "Edm.Single", "dimensions": 1536, "vectorSearchProfile": "my-vector-profile", "searchable": true, "retrievable": false, "stored": false },
-        { "name": "metadata", "type": "Edm.String", "retrievable": true, "searchable": true, "filterable": true }
-      ],
-      "vectorSearch": {
-          "algorithms": [
-              { "name": "my-algo-config", "kind": "hnsw", "hnswParameters": { }  }
-          ],
-          "profiles": [ 
-            { "name": "my-vector-profile", "algorithm": "my-algo-config" }
-          ]
-      }
-    }
-    ```
-
-   Fields must include key field (`"id"` in this example) and should include vector chunks for similarity search, and nonvector chunks for inputs to the LLM. 
-
-   Vector fields are associated with algorithms that determine the search paths at query time. The index has a vectorSearch section for specifying multiple algorithm configurations. Vector fields also have [specific types](/rest/api/searchservice/supported-data-types#edm-data-types-for-vector-fields) and extra attributes for embedding model dimensions. `Edm.Single` is a data type that works for commonly used LLMs. For more information about vector fields, see [Create a vector index](vector-search-how-to-create-index.md).
-
-   Metadata fields might be the parent file path, creation date, or content type and are useful for [filters](vector-search-filters.md).
-
-1. Here's the index schema for the [tutorial source code](https://github.com/Azure-Samples/azure-search-python-samples/blob/main/Tutorial-RAG/Tutorial-rag.ipynb) and the [Earth Book content](https://github.com/Azure-Samples/azure-search-sample-data/tree/main/nasa-e-book/earth_book_2019_text_pages). 
-
-   Like the basic schema, it's organized around chunks. The `chunk_id` uniquely identifies each chunk. The `text_vector` field is an embedding of the chunk. The nonvector `chunk` field is a readable string. The `title` maps to a unique metadata storage path for the blobs. The `parent_id` is the only parent-level field, and it's a base64-encoded version of the parent file URI. 
-
-   In integrated vectorization workloads like the one used in this tutorial series, the `dimensions` property on your vector fields should be identical to the number of `dimensions` generated by the embedding skill used to vectorize your data. In this series, we use the Azure OpenAI embedding skill, which calls the text-embedding-3-large model on Azure OpenAI. The skill is specified in the next tutorial. We set dimensions to 1024 in both the vector field and in the skill definition.
-
-   The schema also includes a `locations` field for storing generated content that's created by the [indexing pipeline](tutorial-rag-build-solution-pipeline.md).
-
-   ```python
-    from azure.identity import DefaultAzureCredential
-    from azure.identity import get_bearer_token_provider
-    from azure.search.documents.indexes import SearchIndexClient
-    from azure.search.documents.indexes.models import (
-        SearchField,
-        SearchFieldDataType,
-        VectorSearch,
-        HnswAlgorithmConfiguration,
-        VectorSearchProfile,
-        AzureOpenAIVectorizer,
-        AzureOpenAIVectorizerParameters,
-        SearchIndex
-    )
-    
-    credential = DefaultAzureCredential()
-    
-    # Create a search index  
-    index_name = "py-rag-tutorial-idx"
-    index_client = SearchIndexClient(endpoint=AZURE_SEARCH_SERVICE, credential=credential)  
-    fields = [
-        SearchField(name="parent_id", type=SearchFieldDataType.String),  
-        SearchField(name="title", type=SearchFieldDataType.String),
-        SearchField(name="locations", type=SearchFieldDataType.Collection(SearchFieldDataType.String), filterable=True),
-        SearchField(name="chunk_id", type=SearchFieldDataType.String, key=True, sortable=True, filterable=True, facetable=True, analyzer_name="keyword"),  
-        SearchField(name="chunk", type=SearchFieldDataType.String, sortable=False, filterable=False, facetable=False),  
-        SearchField(name="text_vector", type=SearchFieldDataType.Collection(SearchFieldDataType.Single), vector_search_dimensions=1024, vector_search_profile_name="myHnswProfile")
-        ]  
-      
-    # Configure the vector search configuration  
-    vector_search = VectorSearch(  
-        algorithms=[  
-            HnswAlgorithmConfiguration(name="myHnsw"),
-        ],  
-        profiles=[  
-            VectorSearchProfile(  
-                name="myHnswProfile",  
-                algorithm_configuration_name="myHnsw",  
-                vectorizer_name="myOpenAI",  
-            )
-        ],  
-        vectorizers=[  
-            AzureOpenAIVectorizer(  
-                vectorizer_name="myOpenAI",  
-                kind="azureOpenAI",  
-                parameters=AzureOpenAIVectorizerParameters(  
-                    resource_url=AZURE_OPENAI_ACCOUNT,  
-                    deployment_name="text-embedding-3-large",
-                    model_name="text-embedding-3-large"
-                ),
-            ),  
-        ], 
-    )  
-      
-    # Create the search index
-    index = SearchIndex(name=index_name, fields=fields, vector_search=vector_search)  
-    result = index_client.create_or_update_index(index)  
-    print(f"{result.name} created")  
-    ```
-
-1. For an index schema that more closely mimics structured content, you would have separate indexes for parent and child (chunked) fields. You would need [index projections](index-projections-concept-intro.md) to coordinate the indexing of the two indexes simultaneously. Queries execute against the child index. Query logic includes a lookup query, using the parent_idt  retrieve content from the parent index.
-
-   Fields in the child index:
-
-   - ID
-   - chunk
-   - chunkVectcor
-   - parent_id
-
-   Fields in the parent index (everything that you want "one of"):
-
-   - parent_id
-   - parent-level fields (name, title, category)
-
-<!-- Objective:
-
-- Design an index schema that generates results in a format that works for LLMs.
-
-Key points:
-
-- schema for rag is designed for producing chunks of content
-- schema should be flat (no complex types or structures)
-- schema determines what queries you can create (be generous in attribute assignments)
-- schema must cover all the queries you want to run. You can only query one index at a time (no joins), but you can create indexes that preserve parent-child relationship, and then use nested queries or parallel queries in your search logic to pull from both.
-- schema has impact on storage/size. Consider narrow data types, attribution, vector configuration.
-- show schema patterns: one for parent-child all-up, one for paired indexes via index projections
-- note metadata for filters
-- TBD: add fields for location and use entity recognition to pull this values out of the PDFs? Not sure how the extraction will work on chunked documents or how it will query, but goal would be to show that you can add structured data to the schema.
-
-Tasks:
-
-- H2 How to create an index for chunked and vectorized data (show examples for parent-child variants)
-- H2 How to define vector profiles and configuration (discuss pros and cons, shouldn't be a rehash of existing how-to)
-- H2 How to add filters
-- H2 How to add structured data (example is "location", top-level field, data aquisition is through the pipeline) -->
-
-## Next step
-
-> [!div class="nextstepaction"]
-> [Create an indexing pipeline](tutorial-rag-build-solution-pipeline.md)

@@ -1,333 +0,0 @@
----
-title: 'Classic RAG tutorial: Tune relevance'
-titleSuffix: Azure AI Search
-description: Learn how to use the relevance tuning capabilities to return high quality results for generative search.
-manager: nitinme
-author: HeidiSteen
-ms.author: heidist
-ms.service: azure-ai-search
-ms.update-cycle: 180-days
-ms.custom:
-  - ignite-2024
-ms.topic: tutorial
-ms.date: 10/14/2025
----
-
-# Tutorial: Maximize relevance (classic RAG in Azure AI Search)
-
-Azure AI Search provides relevance tuning strategies for improving the relevance of search results in classic RAG solutions.  Relevance tuning can be an important factor in delivering a RAG solution that meets user expectations. 
-
-> [!NOTE]
-> We now recommend [agentic retrieval](agentic-retrieval-overview.md) for RAG workflows, but classic RAG is simpler. If it meets your application requirements, it's still a good choice.
-
-In Azure AI Search, relevance tuning includes L2 semantic ranking and scoring profiles. To implement these capabilities, you revisit the index schema to add configurations for semantic ranking and scoring profiles. You then rerun the queries using the new constructs.
-
-In this tutorial, you modify the existing search index and queries to use:
-
-> [!div class="checklist"]
-> - L2 semantic ranking
-> - Scoring profile for document boosting
-
-This tutorial updates the search index created by the [indexing pipeline](tutorial-rag-build-solution-pipeline.md). Updates don't affect the existing content, so no rebuild is necessary and you don't need to rerun the indexer.
-
-## Prerequisites
-
-- [Visual Studio Code](https://code.visualstudio.com/download) with the [Python extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python) and the [Jupyter package](https://pypi.org/project/jupyter/).
-
-- [Azure AI Search](search-create-service-portal.md), Basic tier or higher for managed identity and semantic ranking.
-
-- [Azure OpenAI](/azure/ai-services/openai/how-to/create-resource), with a deployment of text-embedding-3-small and gpt-4o.
-
-## Download the sample
-
-The [sample notebook](https://github.com/Azure-Samples/azure-search-python-samples/blob/main/Tutorial-RAG/Tutorial-rag.ipynb) includes an updated index and query request.
-
-## Run a baseline query for comparison
-
-Let's start with a new query, "Are there any cloud formations specific to oceans and large bodies of water?".
-
-To compare outcomes after adding relevance features, run the query against the existing index schema, before you add semantic ranking or a scoring profile.
-
-For the Azure Government cloud, modify the API endpoint on the token provider to `"https://cognitiveservices.azure.us/.default"`.
-
-```python
-from azure.search.documents import SearchClient
-from openai import AzureOpenAI
-
-token_provider = get_bearer_token_provider(credential, "https://cognitiveservices.azure.com/.default")
-openai_client = AzureOpenAI(
-     api_version="2024-06-01",
-     azure_endpoint=AZURE_OPENAI_ACCOUNT,
-     azure_ad_token_provider=token_provider
- )
-
-deployment_name = "gpt-4o"
-
-search_client = SearchClient(
-     endpoint=AZURE_SEARCH_SERVICE,
-     index_name=index_name,
-     credential=credential
- )
-
-GROUNDED_PROMPT="""
-You are an AI assistant that helps users learn from the information found in the source material.
-Answer the query using only the sources provided below.
-Use bullets if the answer has multiple points.
-If the answer is longer than 3 sentences, provide a summary.
-Answer ONLY with the facts listed in the list of sources below. Cite your source when you answer the question
-If there isn't enough information below, say you don't know.
-Do not generate answers that don't use the sources below.
-Query: {query}
-Sources:\n{sources}
-"""
-
-# Focused query on cloud formations and bodies of water
-query="Are there any cloud formations specific to oceans and large bodies of water?"
-vector_query = VectorizableTextQuery(text=query, k_nearest_neighbors=50, fields="text_vector")
-
-search_results = search_client.search(
-    search_text=query,
-    vector_queries= [vector_query],
-    select=["title", "chunk", "locations"],
-    top=5,
-)
-
-sources_formatted = "=================\n".join([f'TITLE: {document["title"]}, CONTENT: {document["chunk"]}, LOCATIONS: {document["locations"]}' for document in search_results])
-
-response = openai_client.chat.completions.create(
-    messages=[
-        {
-            "role": "user",
-            "content": GROUNDED_PROMPT.format(query=query, sources=sources_formatted)
-        }
-    ],
-    model=deployment_name
-)
-
-print(response.choices[0].message.content)
-```
-
-Output from this request might look like the following example.
-
-```
-Yes, there are cloud formations specific to oceans and large bodies of water. 
-A notable example is "cloud streets," which are parallel rows of clouds that form over 
-the Bering Strait in the Arctic Ocean. These cloud streets occur when wind blows from 
-a cold surface like sea ice over warmer, moister air near the open ocean, leading to 
-the formation of spinning air cylinders. Clouds form along the upward cycle of these cylinders, 
-while skies remain clear along the downward cycle (Source: page-21.pdf).
-```
-
-## Update the index for semantic ranking and scoring profiles
-
-In a previous tutorial, you [designed an index schema](tutorial-rag-build-solution-index-schema.md) for RAG workloads. We purposely omitted relevance enhancements from that schema so that you could focus on the fundamentals. Deferring relevance to a separate exercise gives you a before-and-after comparison of the quality of search results after the updates are made.
-
-1. Update the import statements to include classes for semantic ranking and scoring profiles.
-
-   ```python
-    from azure.identity import DefaultAzureCredential
-    from azure.identity import get_bearer_token_provider
-    from azure.search.documents.indexes import SearchIndexClient
-    from azure.search.documents.indexes.models import (
-        SearchField,
-        SearchFieldDataType,
-        VectorSearch,
-        HnswAlgorithmConfiguration,
-        VectorSearchProfile,
-        AzureOpenAIVectorizer,
-        AzureOpenAIVectorizerParameters,
-        SearchIndex,
-        SemanticConfiguration,
-        SemanticPrioritizedFields,
-        SemanticField,
-        SemanticSearch,
-        ScoringProfile,
-        TagScoringFunction,
-        TagScoringParameters
-    )
-    ```
-
-1. Add the following semantic configuration to the search index. This example can be found in the update schema step in the notebook.
-
-    ```python
-    # New semantic configuration
-    semantic_config = SemanticConfiguration(
-        name="my-semantic-config",
-        prioritized_fields=SemanticPrioritizedFields(
-            title_field=SemanticField(field_name="title"),
-            keywords_fields=[SemanticField(field_name="locations")],
-            content_fields=[SemanticField(field_name="chunk")]
-        )
-    )
-    
-    # Create the semantic settings with the configuration
-    semantic_search = SemanticSearch(configurations=[semantic_config])
-    ```
-
-   A semantic configuration has a name and a prioritized list of fields to help optimize the inputs to semantic ranker. For more information, see [Configure semantic ranking](/azure/search/semantic-how-to-configure).
-
-1. Next, add a scoring profile definition. As with semantic configuration, a scoring profile can be added to an index schema at any time. This example is also in the update schema step in the notebook, following the semantic configuration.
-
-    ```python
-    # New scoring profile
-    scoring_profiles = [  
-        ScoringProfile(  
-            name="my-scoring-profile",
-            functions=[
-                TagScoringFunction(  
-                    field_name="locations",  
-                    boost=5.0,  
-                    parameters=TagScoringParameters(  
-                        tags_parameter="tags",  
-                    ),  
-                ) 
-            ]
-        )
-    ]
-    ```
-
-   This profile uses the tag function which boosts the scores of documents where a match was found in the locations field. Recall that the search index has a vector field, and multiple nonvector fields for title, chunks, and locations. The locations field is a string collection, and string collections can be boosted using the tags function in a scoring profile. For more information, see [Add a scoring profile](index-add-scoring-profiles.md) and [Enhancing Search Relevance with Document Boosting (blog post)](https://farzzy.hashnode.dev/enhance-azure-ai-search-document-boosting).
-
-1. Update the index definition on the search service.
-
-   ```python
-   # Update the search index with the semantic configuration
-    index = SearchIndex(name=index_name, fields=fields, vector_search=vector_search, semantic_search=semantic_search, scoring_profiles=scoring_profiles)  
-    result = index_client.create_or_update_index(index)  
-    print(f"{result.name} updated")  
-    ```
-
-## Update queries for semantic ranking and scoring profiles
-
-In a previous tutorial, you [ran queries](tutorial-rag-build-solution-query.md) that execute on the search engine, passing the response and other information to an LLM for chat completion.
-
-This example modifies the query request to include the semantic configuration and scoring profile.
-
-For the Azure Government cloud, modify the API endpoint on the token provider to `"https://cognitiveservices.azure.us/.default"`.
-
-```python
-# Import libraries
-from azure.search.documents import SearchClient
-from openai import AzureOpenAI
-
-token_provider = get_bearer_token_provider(credential, "https://cognitiveservices.azure.com/.default")
-openai_client = AzureOpenAI(
-     api_version="2024-06-01",
-     azure_endpoint=AZURE_OPENAI_ACCOUNT,
-     azure_ad_token_provider=token_provider
- )
-
-deployment_name = "gpt-4o"
-
-search_client = SearchClient(
-     endpoint=AZURE_SEARCH_SERVICE,
-     index_name=index_name,
-     credential=credential
- )
-
-# Prompt is unchanged in this update
-GROUNDED_PROMPT="""
-You are an AI assistant that helps users learn from the information found in the source material.
-Answer the query using only the sources provided below.
-Use bullets if the answer has multiple points.
-If the answer is longer than 3 sentences, provide a summary.
-Answer ONLY with the facts listed in the list of sources below.
-If there isn't enough information below, say you don't know.
-Do not generate answers that don't use the sources below.
-Query: {query}
-Sources:\n{sources}
-"""
-
-# Queries are unchanged in this update
-query="Are there any cloud formations specific to oceans and large bodies of water?"
-vector_query = VectorizableTextQuery(text=query, k_nearest_neighbors=50, fields="text_vector")
-
-# Add query_type semantic and semantic_configuration_name
-# Add scoring_profile and scoring_parameters
-search_results = search_client.search(
-    query_type="semantic",
-    semantic_configuration_name="my-semantic-config",
-    scoring_profile="my-scoring-profile",
-    scoring_parameters=["tags-ocean, 'sea surface', seas, surface"],
-    search_text=query,
-    vector_queries= [vector_query],
-    select="title, chunk, locations",
-    top=5,
-)
-sources_formatted = "=================\n".join([f'TITLE: {document["title"]}, CONTENT: {document["chunk"]}, LOCATIONS: {document["locations"]}' for document in search_results])
-
-response = openai_client.chat.completions.create(
-    messages=[
-        {
-            "role": "user",
-            "content": GROUNDED_PROMPT.format(query=query, sources=sources_formatted)
-        }
-    ],
-    model=deployment_name
-)
-
-print(response.choices[0].message.content)
-```
-
-Output from a semantically ranked and boosted query might look like the following example.
-
-```
-Yes, there are specific cloud formations influenced by oceans and large bodies of water:
-
-- **Stratus Clouds Over Icebergs**: Low stratus clouds can frame holes over icebergs, 
-such as Iceberg A-56 in the South Atlantic Ocean, likely due to thermal instability caused 
-by the iceberg (source: page-39.pdf).
-
-- **Undular Bores**: These are wave structures in the atmosphere created by the collision 
-of cool, dry air from a continent with warm, moist air over the ocean, as seen off the 
-coast of Mauritania (source: page-23.pdf).
-
-- **Ship Tracks**: These are narrow clouds formed by water vapor condensing around tiny 
-particles from ship exhaust. They are observed over the oceans, such as in the Pacific Ocean 
-off the coast of California (source: page-31.pdf).
-
-These specific formations are influenced by unique interactions between atmospheric conditions 
-and the presence of large water bodies or objects within them.
-```
-
-Adding semantic ranking and scoring profiles positively affects the response from the LLM by promoting results that meet scoring criteria and are semantically relevant. 
-
-Now that you have a better understanding of index and query design, let's move on to optimizing for speed and concision. We revisit the schema definition to implement quantization and storage reduction, but the rest of the pipeline and models remain intact.
-
-<!-- ## Update queries for minimum thresholds ** NOT AVAILABLE IN PYTHON SDK
-
-Keyword search only returns results if there's match found in the index, up to a maximum of 50 results by default. In contrast, vector search returns `k`-results every time, even if the matching vectors aren't a close match.
-
-In the vector query portion of the request, add a threshold object and set a minimum value for including vector matches in the results.
-
-Vector scores range from 0.333 to 1.00. For more information, see [Set thresholds to exclude low-scoring results](vector-search-how-to-query.md#set-thresholds-to-exclude-low-scoring-results-preview) and [Scores in a vector search results](vector-search-ranking.md#scores-in-a-vector-search-results).
-
-```python
-# Update the vector_query to include a minimum threshold.
-query="how much of earth is covered by water"
-vector_query = VectorizableTextQuery(text=query, k_nearest_neighbors=1, fields="text_vector", threshold.kind="vectorSImiliarty", threshold.value=0.8, exhaustive=True) -->
-
-<!-- ## Update queries for vector weighting
-
-<!-- Using preview features, you can unpack a hybrid search score to review the individual component scores. Based on that information, you can set minimum thresholds to exclude any match that falls below it.
-
-Semantic ranking and scoring profiles operate on nonvector content, but you can tune the vector portion of a hybrid query to amplify or diminish its importance based on how much value it adds to the results. For example, if you run keyword search and vector search independently and find that one of them is outperforming the other, you can adjust the weight on the vector side to higher or lower. This approach gives you more control over query processing.
- -->
-
-<!-- Key points:
-
-- How to measure relevance (?) to determine if changes are improving results
-- Try different algorithms (HNSW vs eKnn)
-- Change query structure (hybrid with vector/non over same content (double-down), hybrid over multiple fields)
-- semantic ranking
-- scoring profiles
-- thresholds for minimum score
-- set weights
-- filters
-- analyzers and normalizers
-- advanced query formats (regular expressions, fuzzy search) -->
-
-## Next step
-
-> [!div class="nextstepaction"]
-> [Minimize vector storage and costs](tutorial-rag-build-solution-minimize-storage.md)