@@ -3,27 +3,456 @@ title: Create a Blob Knowledge Source for Agentic Retrieval
 description: A blob knowledge source specifies a blob container that you want to read from. It also includes models and properties for creating an indexer, data source, skillset, and index used for agentic retrieval workloads.
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 03/25/2026
+ms.date: 04/14/2026
 zone_pivot_groups: search-csharp-python-rest
 ---
 
 # Create a blob knowledge source from Azure Blob Storage and ADLS Gen2
 
+[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
+
+Use a *blob knowledge source* to index and query Azure blob content in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+
+Unlike a [search index knowledge source](agentic-knowledge-source-how-to-search-index.md), which specifies an existing and qualified index, a blob knowledge source specifies an external data source, models, and properties to automatically generate the following Azure AI Search objects:
+
++ A data source that represents a blob container.
++ A skillset that chunks and optionally vectorizes multimodal content from the container.
++ An index that stores enriched content and meets the criteria for agentic retrieval.
++ An indexer that uses the previous objects to drive the indexing and enrichment pipeline.
+
+> [!NOTE]
+> If user access is specified at the document (blob) level in Azure Storage, a knowledge source can carry permission metadata forward to indexed content in Azure AI Search. For more information, see [ADLS Gen2 permission metadata](search-indexer-access-control-lists-and-role-based-access.md) or [Blob RBAC scopes](search-blob-indexer-role-based-access.md).
+
+### Usage support
+
+| [Azure portal](get-started-portal-agentic-retrieval.md) | [Microsoft Foundry portal](/azure/ai-foundry/agents/concepts/what-is-foundry-iq#workflow) | [.NET SDK](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/search/Azure.Search.Documents/CHANGELOG.md) | [Python SDK](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [Java SDK](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [JavaScript SDK](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/search/search-documents/CHANGELOG.md) | [REST API](/rest/api/searchservice/knowledge-sources?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |
+|--|--|--|--|--|--|--|
+| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
+
+## Prerequisites
+
++ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md). You must have [semantic ranker enabled](semantic-how-to-enable-disable.md).
+
++ An [Azure Blob Storage](/azure/storage/common/storage-account-create) or [Azure Data Lake Storage (ADLS) Gen2](/azure/storage/blobs/create-data-lake-storage-account) account.
+
++ A blob container with [supported content types](search-how-to-index-azure-blob-storage.md#supported-document-formats) for text content. For optional image verbalization, the supported content type depends on whether your chat completion model can analyze and describe the image file.
+
++ Permission to create and use objects on Azure AI Search. We recommend [role-based access](search-security-rbac.md), but you can use [API keys](search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](search-get-started-rbac.md).
+
+::: zone pivot="csharp"
+
++ The latest [`Azure.Search.Documents` preview package](https://www.nuget.org/packages/Azure.Search.Documents/11.8.0-beta.1): `dotnet add package Azure.Search.Documents --prerelease`
+
+::: zone-end
+
+::: zone pivot="python"
+
++ The latest [`azure-search-documents` preview package](https://pypi.org/project/azure-search-documents/11.7.0b2/): `pip install --pre azure-search-documents`
+
+::: zone-end
+
+::: zone pivot="rest"
+
++ The [2025-11-01-preview](/rest/api/searchservice/operation-groups?view=rest-searchservice-2025-11-01-preview&preserve-view=true) version of the Search Service REST APIs.
+
+::: zone-end
+
+## Check for existing knowledge sources
+
+::: zone pivot="csharp"
+
+[!INCLUDE [Check for existing knowledge sources using C#](includes/how-tos/knowledge-source-check-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Check for existing knowledge sources using Python](includes/how-tos/knowledge-source-check-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [Check for existing knowledge sources using REST](includes/how-tos/knowledge-source-check-rest.md)]
+
+::: zone-end
+
+The following JSON is an example response for a blob knowledge source.
+
+```json
+{
+  "name": "my-blob-ks",
+  "kind": "azureBlob",
+  "description": "A sample blob knowledge source.",
+  "encryptionKey": null,
+  "azureBlobParameters": {
+    "connectionString": "<REDACTED>",
+    "containerName": "blobcontainer",
+    "folderPath": null,
+    "isADLSGen2": false,
+    "ingestionParameters": {
+      "disableImageVerbalization": false,
+      "ingestionPermissionOptions": [],
+      "contentExtractionMode": "standard",
+      "identity": null,
+      "embeddingModel": {
+        "kind": "azureOpenAI",
+        "azureOpenAIParameters": {
+          "resourceUri": "<REDACTED>",
+          "deploymentId": "text-embedding-3-large",
+          "apiKey": "<REDACTED>",
+          "modelName": "text-embedding-3-large",
+          "authIdentity": null
+        }
+      },
+      "chatCompletionModel": {
+        "kind": "azureOpenAI",
+        "azureOpenAIParameters": {
+          "resourceUri": "<REDACTED>",
+          "deploymentId": "gpt-5-mini",
+          "apiKey": "<REDACTED>",
+          "modelName": "gpt-5-mini",
+          "authIdentity": null
+        }
+      },
+      "ingestionSchedule": null,
+      "assetStore": null,
+      "aiServices": {
+        "uri": "<REDACTED>",
+        "apiKey": "<REDACTED>"
+      }
+    },
+    "createdResources": {
+      "datasource": "my-blob-ks-datasource",
+      "indexer": "my-blob-ks-indexer",
+      "skillset": "my-blob-ks-skillset",
+      "index": "my-blob-ks-index"
+    }
+  }
+}
+```
+
+> [!NOTE]
+> Sensitive information is redacted. The generated resources appear at the end of the response.
+
+## Create a knowledge source
+
 ::: zone pivot="csharp"
-[!INCLUDE [C#](includes/how-tos/agentic-knowledge-source-how-to-blob-csharp.md)]
+
+Run the following code to [create a blob knowledge source](/dotnet/api/azure.search.documents.indexes.models.azureblobknowledgesource?view=azure-dotnet-preview&preserve-view=true).
+
+```csharp
+// Create a blob knowledge source
+using Azure.Search.Documents.Indexes;
+using Azure.Search.Documents.Indexes.Models;
+using Azure.Search.Documents.KnowledgeBases.Models;
+using Azure;
+
+var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new AzureKeyCredential(apiKey));
+
+var chatCompletionParams = new AzureOpenAIVectorizerParameters
+{
+    ResourceUri = new Uri(aoaiEndpoint),
+    DeploymentName = aoaiGptDeployment,
+    ModelName = aoaiGptModel
+};
+
+var embeddingParams = new AzureOpenAIVectorizerParameters
+{
+    ResourceUri = new Uri(aoaiEndpoint),
+    DeploymentName = aoaiEmbeddingDeployment,
+    ModelName = aoaiEmbeddingModel
+};
+
+var ingestionParams = new KnowledgeSourceIngestionParameters
+{
+    DisableImageVerbalization = false,
+    ChatCompletionModel = new KnowledgeBaseAzureOpenAIModel(azureOpenAIParameters: chatCompletionParams),
+    EmbeddingModel = new KnowledgeSourceAzureOpenAIVectorizer
+    {
+        AzureOpenAIParameters = embeddingParams
+    }
+};
+
+var blobParams = new AzureBlobKnowledgeSourceParameters(
+    connectionString: connectionString,
+    containerName: containerName
+)
+{
+    IsAdlsGen2 = false,
+    IngestionParameters = ingestionParams
+};
+
+var knowledgeSource = new AzureBlobKnowledgeSource(
+    name: "my-blob-ks",
+    azureBlobParameters: blobParams
+)
+{
+    Description = "This knowledge source pulls from a blob storage container."
+};
+
+await indexClient.CreateOrUpdateKnowledgeSourceAsync(knowledgeSource);
+Console.WriteLine($"Knowledge source '{knowledgeSource.Name}' created or updated successfully.");
+```
+
 ::: zone-end
 
 ::: zone pivot="python"
-[!INCLUDE [Python](includes/how-tos/agentic-knowledge-source-how-to-blob-python.md)]
+
+Run the following code to create a blob knowledge source.
+
+```python
+# Create a blob knowledge source
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient
+from azure.search.documents.indexes.models import AzureBlobKnowledgeSource, AzureBlobKnowledgeSourceParameters, KnowledgeBaseAzureOpenAIModel, AzureOpenAIVectorizerParameters, KnowledgeSourceAzureOpenAIVectorizer, KnowledgeSourceContentExtractionMode, KnowledgeSourceIngestionParameters
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+
+knowledge_source = AzureBlobKnowledgeSource(
+    name = "my-blob-ks",
+    description = "This knowledge source pulls from a blob storage container.",
+    encryption_key = None,
+    azure_blob_parameters = AzureBlobKnowledgeSourceParameters(
+        connection_string = "blob_connection_string",
+        container_name = "blob_container_name",
+        folder_path = None,
+        is_adls_gen2 = False,
+        ingestion_parameters = KnowledgeSourceIngestionParameters(
+            identity = None,
+            disable_image_verbalization = False,
+            chat_completion_model = KnowledgeBaseAzureOpenAIModel(
+                azure_open_ai_parameters = AzureOpenAIVectorizerParameters(
+                    resource_url = "aoai_endpoint",
+                    deployment_name = "aoai_gpt_deployment",
+                    model_name = "aoai_gpt_model",
+                    api_key = "aoai_api_key"
+                )
+            ),
+            embedding_model = KnowledgeSourceAzureOpenAIVectorizer(
+                azure_open_ai_parameters=AzureOpenAIVectorizerParameters(
+                    resource_url = "aoai_endpoint",
+                    deployment_name = "aoai_embedding_deployment",
+                    model_name = "aoai_embedding_model",
+                    api_key = "aoai_api_key"
+                )
+            ),
+            content_extraction_mode = KnowledgeSourceContentExtractionMode.MINIMAL,
+            ingestion_schedule = None,
+            ingestion_permission_options = None
+        )
+    )
+)
+
+index_client.create_or_update_knowledge_source(knowledge_source)
+print(f"Knowledge source '{knowledge_source.name}' created or updated successfully.")
+```
+
 ::: zone-end
 
 ::: zone pivot="rest"
-[!INCLUDE [REST](includes/how-tos/agentic-knowledge-source-how-to-blob-rest.md)]
+
+Use [Knowledge Sources - Create or Update (REST API)](/rest/api/searchservice/knowledge-sources/create-or-update?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to create a blob knowledge source.
+
+```http
+PUT {{search-url}}/knowledgesources/my-blob-ks?api-version=2025-11-01-preview
+api-key: {{api-key}}
+Content-Type: application/json
+
+{
+  "name": "my-blob-ks",
+  "kind": "azureBlob",
+  "description": "This knowledge source pulls from a blob storage container.",
+  "encryptionKey": null,
+  "azureBlobParameters": {
+    "connectionString": "<YOUR AZURE STORAGE CONNECTION STRING>",
+    "containerName": "<YOUR BLOB CONTAINER NAME>",
+    "folderPath": null,
+    "isADLSGen2": false,
+    "ingestionParameters": {
+        "identity": null,
+        "disableImageVerbalization": null,
+        "chatCompletionModel": {
+            "kind": "azureOpenAI",
+            "azureOpenAIParameters": {
+                "resourceUri": "{{aoai-endpoint}}",
+                "deploymentId": "{{aoai-gpt-deployment}}",
+                "modelName": "{{aoai-gpt-model}}",
+                "apiKey": "{{aoai-key}}"
+            }
+        },
+        "embeddingModel": {
+            "kind": "azureOpenAI",
+            "azureOpenAIParameters": {
+                "resourceUri": "{{aoai-endpoint}}",
+                "deploymentId": "{{aoai-embedding-deployment}}",
+                "modelName": "{{aoai-embedding-model}}",
+                "apiKey": "{{aoai-key}}"
+            }
+        },
+        "contentExtractionMode": "minimal",
+        "ingestionSchedule": null,
+        "ingestionPermissionOptions": []
+    }
+  }
+}
+```
+
+::: zone-end
+
+### Source-specific properties
+
+You can pass the following properties to create a blob knowledge source.
+
+::: zone pivot="csharp"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `Name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `Description` | A description of the knowledge source. | String | Yes | No |
+| `EncryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `AzureBlobParameters` | Parameters specific to blob knowledge sources: `ConnectionString`, `ContainerName`, `FolderPath`, and `IsAdlsGen2`. | Object |  | No |
+| `ConnectionString` | A key-based [connection string](search-how-to-index-azure-blob-storage.md#supported-credentials-and-connection-strings) or, if you're using a managed identity, the resource ID. | String | No | Yes |
+| `ContainerName` | The name of the blob storage container. | String | No | Yes |
+| `FolderPath` | A folder within the container. | String | No | No |
+| `IsAdlsGen2` | The default is `False`. Set to `True` if you're using an ADLS Gen2 storage account. | Boolean | No | No |
+
+::: zone-end
+
+::: zone pivot="python"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryption_key` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `azure_blob_parameters` | Parameters specific to blob knowledge sources: `connection_string`, `container_name`, `folder_path`, and `is_adls_gen2`. | Object |  | No |
+| `connection_string` | A key-based [connection string](search-how-to-index-azure-blob-storage.md#supported-credentials-and-connection-strings) or, if you're using a managed identity, the resource ID. | String | No | Yes |
+| `container_name` | The name of the blob storage container. | String | No | Yes |
+| `folder_path` | A folder within the container. | String | No | No |
+| `is_adls_gen2` | The default is `False`. Set to `True` if you're using an ADLS Gen2 storage account. | Boolean | No | No |
+
+::: zone-end
+
+::: zone pivot="rest"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `kind` | The kind of knowledge source, which is `azureBlob` in this case. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `azureBlobParameters` | Parameters specific to blob knowledge sources: `connectionString`, `containerName`, `folderPath`, and `isADLSGen2`. | Object |  | No |
+| `connectionString` | A key-based [connection string](search-how-to-index-azure-blob-storage.md#supported-credentials-and-connection-strings) or, if you're using a managed identity, the resource ID. | String | No | Yes |
+| `containerName` | The name of the blob storage container. | String | No | Yes |
+| `folderPath` | A folder within the container. | String | No | No |
+| `isADLSGen2` | The default is `false`. Set to `true` if you're using an ADLS Gen2 storage account. | Boolean | No | No |
+
+::: zone-end
+
+### Ingestion parameters properties
+
+::: zone pivot="csharp"
+
+[!INCLUDE [C# ingestionParameters properties](includes/how-tos/knowledge-source-ingestion-parameters-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Python ingestionParameters properties](includes/how-tos/knowledge-source-ingestion-parameters-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [REST ingestionParameters properties](includes/how-tos/knowledge-source-ingestion-parameters-rest.md)]
+
+::: zone-end
+
+## Check ingestion status
+
+::: zone pivot="csharp"
+
+[!INCLUDE [C# knowledge source status](includes/how-tos/knowledge-source-status-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Python knowledge source status](includes/how-tos/knowledge-source-status-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [REST knowledge source status](includes/how-tos/knowledge-source-status-rest.md)]
+
+::: zone-end
+
+## Review the created objects
+
+When you create a blob knowledge source, your search service also creates an indexer, index, skillset, and data source. We don't recommend that you edit these objects, as introducing an error or incompatibility can break the pipeline.
+
+After you create a knowledge source, the response lists the created objects. These objects are created according to a fixed template, and their names are based on the name of the knowledge source. You can't change the object names.
+
+We recommend using the Azure portal to validate output creation. The workflow is:
+
+1. Check the indexer for success or failure messages. Connection or quota errors appear here.
+1. Check the index for searchable content. Use Search Explorer to run queries.
+1. Check the skillset to learn how your content is chunked and optionally vectorized.
+1. Check the data source for connection details. Our example uses API keys for simplicity, but you can use Microsoft Entra ID for authentication and role-based access control for authorization.
+
+## Assign to a knowledge base
+
+If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+
+After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+
+::: zone pivot="csharp"
+
+> [!TIP]
+> To enforce document-level permissions, set `IngestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+::: zone-end
+
+::: zone pivot="python"
+
+> [!TIP]
+> To enforce document-level permissions, set `ingestion_permission_options` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+::: zone-end
+
+::: zone pivot="rest"
+
+> [!TIP]
+> To enforce document-level permissions, set `ingestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+::: zone-end
+
+## Delete a knowledge source
+
+::: zone pivot="csharp"
+
+[!INCLUDE [Delete knowledge source using C#](includes/how-tos/knowledge-source-delete-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Delete knowledge source using Python](includes/how-tos/knowledge-source-delete-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [Delete knowledge source using REST](includes/how-tos/knowledge-source-delete-rest.md)]
+
 ::: zone-end
 
 ## Related content
 
 + [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
 + [Azure AI Search blob knowledge source Python sample](https://github.com/Azure/azure-search-vector-samples/blob/main/demo-python/code/knowledge/blob-knowledge-source.ipynb)
 + [Agentic RAG: Build a reasoning retrieval engine with Azure AI Search (YouTube video)](https://www.youtube.com/watch?v=PeTmOidqHM8)
-+ [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)
\ No newline at end of file
++ [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)

@@ -5,26 +5,443 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2025
 ms.topic: how-to
-ms.date: 03/25/2026
+ms.date: 04/14/2026
 zone_pivot_groups: search-csharp-python-rest
 ---
 
 # Create an indexed OneLake knowledge source
 
+[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
+
+Use an *indexed OneLake knowledge source* to index and query Microsoft OneLake files in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+
+When you create an indexed OneLake knowledge source, you specify an external data source, models, and properties to automatically generate the following Azure AI Search objects:
+
++ A data source that represents a lakehouse.
++ A skillset that chunks and optionally vectorizes multimodal content from the lakehouse.
++ An index that stores enriched content and meets the criteria for agentic retrieval.
++ An indexer that uses the previous objects to drive the indexing and enrichment pipeline.
+
+The generated indexer conforms to the *OneLake indexer*, whose prerequisites, supported tasks, supported document formats, supported shortcuts, and limitations also apply to OneLake knowledge sources. For more information, see the [OneLake indexer documentation](search-how-to-index-onelake-files.md).
+
+### Usage support
+
+| [Azure portal](get-started-portal-agentic-retrieval.md) | [Microsoft Foundry portal](/azure/ai-foundry/agents/concepts/what-is-foundry-iq#workflow) | [.NET SDK](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/search/Azure.Search.Documents/CHANGELOG.md) | [Python SDK](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [Java SDK](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [JavaScript SDK](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/search/search-documents/CHANGELOG.md) | [REST API](/rest/api/searchservice/knowledge-sources?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |
+|--|--|--|--|--|--|--|
+| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
+
+## Prerequisites
+
++ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md). You must have [semantic ranker enabled](semantic-how-to-enable-disable.md).
+
++ Completion of the [OneLake indexer prerequisites](search-how-to-index-onelake-files.md#prerequisites).
+
++ Completion of the [OneLake indexer data preparation](search-how-to-index-onelake-files.md#prepare-data-for-indexing).
+
++ Permission to create and use objects on Azure AI Search. We recommend [role-based access](search-security-rbac.md), but you can use [API keys](search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](search-get-started-rbac.md).
+
+::: zone pivot="csharp"
+
++ The latest [`Azure.Search.Documents` preview package](https://www.nuget.org/packages/Azure.Search.Documents/11.8.0-beta.1): `dotnet add package Azure.Search.Documents --prerelease`
+
+::: zone-end
+
+::: zone pivot="python"
+
++ The latest [`azure-search-documents` preview package](https://pypi.org/project/azure-search-documents/11.7.0b2/): `pip install --pre azure-search-documents`
+
+::: zone-end
+
+::: zone pivot="rest"
+
++ The [2025-11-01-preview](/rest/api/searchservice/operation-groups?view=rest-searchservice-2025-11-01-preview&preserve-view=true) version of the Search Service REST APIs.
+
+::: zone-end
+
+## Check for existing knowledge sources
+
 ::: zone pivot="csharp"
-[!INCLUDE [C#](includes/how-tos/agentic-knowledge-source-how-to-onelake-csharp.md)]
+
+[!INCLUDE [Check for existing knowledge sources using C#](includes/how-tos/knowledge-source-check-csharp.md)]
+
 ::: zone-end
 
 ::: zone pivot="python"
-[!INCLUDE [Python](includes/how-tos/agentic-knowledge-source-how-to-onelake-python.md)]
+
+[!INCLUDE [Check for existing knowledge sources using Python](includes/how-tos/knowledge-source-check-python.md)]
+
 ::: zone-end
 
 ::: zone pivot="rest"
-[!INCLUDE [REST](includes/how-tos/agentic-knowledge-source-how-to-onelake-rest.md)]
+
+[!INCLUDE [Check for existing knowledge sources using REST](includes/how-tos/knowledge-source-check-rest.md)]
+
+::: zone-end
+
+The following JSON is an example response for an indexed OneLake knowledge source.
+
+```json
+{
+  "name": "my-onelake-ks",
+  "kind": "indexedOneLake",
+  "description": "A sample indexed OneLake knowledge source.",
+  "encryptionKey": null,
+  "indexedOneLakeParameters": {
+    "fabricWorkspaceId": "<REDACTED>",
+    "lakehouseId": "<REDACTED>",
+    "targetPath": null,
+    "ingestionParameters": {
+      "disableImageVerbalization": false,
+      "ingestionPermissionOptions": [],
+      "contentExtractionMode": "standard",
+      "identity": null,
+      "embeddingModel": {
+        "kind": "azureOpenAI",
+        "azureOpenAIParameters": {
+          "resourceUri": "<REDACTED>",
+          "deploymentId": "text-embedding-3-large",
+          "apiKey": "<REDACTED>",
+          "modelName": "text-embedding-3-large"
+        }
+      },
+      "chatCompletionModel": {
+        "kind": "azureOpenAI",
+        "azureOpenAIParameters": {
+          "resourceUri": "<REDACTED>",
+          "deploymentId": "gpt-5-mini",
+          "apiKey": "<REDACTED>",
+          "modelName": "gpt-5-mini"
+        }
+      },
+      "ingestionSchedule": null,
+      "aiServices": {
+        "uri": "<REDACTED>",
+        "apiKey": "<REDACTED>"
+      }
+    },
+    "createdResources": {
+    "datasource": "my-onelake-ks-datasource",
+    "indexer": "my-onelake-ks-indexer",
+    "skillset": "my-onelake-ks-skillset",
+    "index": "my-onelake-ks-index"
+    }
+  }
+}
+```
+
+> [!NOTE]
+> Sensitive information is redacted. The generated resources appear at the end of the response.
+
+## Create a knowledge source
+
+::: zone pivot="csharp"
+
+Run the following code to create an indexed OneLake knowledge source.
+
+```csharp
+// Create an IndexedOneLake knowledge source
+using Azure.Search.Documents.Indexes;
+using Azure.Search.Documents.Indexes.Models;
+using Azure.Search.Documents.KnowledgeBases.Models;
+using Azure;
+
+var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new AzureKeyCredential(apiKey));
+
+var chatCompletionParams = new AzureOpenAIVectorizerParameters
+{
+    ResourceUri = new Uri(aoaiEndpoint),
+    DeploymentName = aoaiGptDeployment,
+    ModelName = aoaiGptModel
+};
+
+var embeddingParams = new AzureOpenAIVectorizerParameters
+{
+    ResourceUri = new Uri(aoaiEndpoint),
+    DeploymentName = aoaiEmbeddingDeployment,
+    ModelName = aoaiEmbeddingModel
+};
+
+var ingestionParams = new KnowledgeSourceIngestionParameters
+{
+    DisableImageVerbalization = false,
+    ChatCompletionModel = new KnowledgeBaseAzureOpenAIModel(azureOpenAIParameters: chatCompletionParams),
+    EmbeddingModel = new KnowledgeSourceAzureOpenAIVectorizer
+    {
+        AzureOpenAIParameters = embeddingParams
+    }
+};
+
+var oneLakeParams = new IndexedOneLakeKnowledgeSourceParameters(
+    fabricWorkspaceId: fabricWorkspaceId,
+    lakehouseId: lakehouseId)
+{
+    IngestionParameters = ingestionParams
+};
+
+var knowledgeSource = new IndexedOneLakeKnowledgeSource(
+    name: "my-onelake-ks",
+    indexedOneLakeParameters: oneLakeParams)
+{
+    Description = "This knowledge source pulls content from a lakehouse."
+};
+
+await indexClient.CreateOrUpdateKnowledgeSourceAsync(knowledgeSource);
+Console.WriteLine($"Knowledge source '{knowledgeSource.Name}' created or updated successfully.");
+```
+
+::: zone-end
+
+::: zone pivot="python"
+
+Run the following code to create an indexed OneLake knowledge source.
+
+```python
+# Create an indexed OneLake knowledge source
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient
+from azure.search.documents.indexes.models import IndexedOneLakeKnowledgeSource, IndexedOneLakeKnowledgeSourceParameters, KnowledgeBaseAzureOpenAIModel, AzureOpenAIVectorizerParameters, KnowledgeSourceAzureOpenAIVectorizer, KnowledgeSourceContentExtractionMode, KnowledgeSourceIngestionParameters
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+
+knowledge_source = IndexedOneLakeKnowledgeSource(
+    name = "my-onelake-ks",
+    description= "This knowledge source pulls content from a lakehouse.",
+    encryption_key = None,
+    indexed_one_lake_parameters = IndexedOneLakeKnowledgeSourceParameters(
+        fabric_workspace_id = "fabric_workspace_id",
+        lakehouse_id = "lakehouse_id",
+        target_path = None,
+        ingestion_parameters = KnowledgeSourceIngestionParameters(
+            identity = None,
+            disable_image_verbalization = False,
+            chat_completion_model = KnowledgeBaseAzureOpenAIModel(
+                azure_open_ai_parameters = AzureOpenAIVectorizerParameters(
+                    resource_url = "aoai_endpoint",
+                    deployment_name = "aoai_gpt_deployment",
+                    model_name = "aoai_gpt_model",
+                    api_key = "aoai_api_key"
+                )
+            ),
+            embedding_model = KnowledgeSourceAzureOpenAIVectorizer(
+                azure_open_ai_parameters=AzureOpenAIVectorizerParameters(
+                    resource_url = "aoai_endpoint",
+                    deployment_name = "aoai_embedding_deployment",
+                    model_name = "aoai_embedding_model",
+                    api_key = "aoai_api_key"
+                )
+            ),
+            content_extraction_mode = KnowledgeSourceContentExtractionMode.MINIMAL,
+            ingestion_schedule = None,
+            ingestion_permission_options = None
+        )
+    )
+)
+
+index_client.create_or_update_knowledge_source(knowledge_source)
+print(f"Knowledge source '{knowledge_source.name}' created or updated successfully.")
+```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+Use [Knowledge Sources - Create or Update (REST API)](/rest/api/searchservice/knowledge-sources/create-or-update?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to create an indexed OneLake knowledge source.
+
+```http
+PUT {{search-url}}/knowledgesources/my-onelake-ks?api-version=2025-11-01-preview
+api-key: {{api-key}}
+Content-Type: application/json
+
+{
+    "name": "my-onelake-ks",
+    "kind": "indexedOneLake",
+    "description": "This knowledge source pulls content from a lakehouse.",
+    "indexedOneLakeParameters": {
+      "fabricWorkspaceId": "<YOUR FABRIC WORKSPACE GUID>",
+      "lakehouseId": "<YOUR LAKEHOUSE GUID>",
+      "targetPath": null,
+      "ingestionParameters": {
+        "identity": null,
+        "disableImageVerbalization": null,
+        "chatCompletionModel": {
+            "kind": "azureOpenAI",
+            "azureOpenAIParameters": {
+                "resourceUri": "{{aoai-endpoint}}",
+                "deploymentId": "{{aoai-gpt-deployment}}",
+                "modelName": "{{aoai-gpt-model}}",
+                "apiKey": "{{aoai-key}}"
+            }
+        },
+        "embeddingModel": {
+            "kind": "azureOpenAI",
+            "azureOpenAIParameters": {
+                "resourceUri": "{{aoai-endpoint}}",
+                "deploymentId": "{{aoai-embedding-deployment}}",
+                "modelName": "{{aoai-embedding-model}}",
+                "apiKey": "{{aoai-key}}"
+            }
+        },
+        "contentExtractionMode": "minimal",
+        "ingestionSchedule": null,
+        "ingestionPermissionOptions": []
+    }
+  }
+}
+```
+
+::: zone-end
+
+### Source-specific properties
+
+You can pass the following properties to create an indexed OneLake knowledge source.
+
+::: zone pivot="csharp"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `Name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `Description` | A description of the knowledge source. | String | Yes | No |
+| `EncryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `IndexedOneLakeKnowledgeSourceParameters` | Parameters specific to OneLake knowledge sources: `FabricWorkspaceId`, `LakehouseId`, and `TargetPath`. | Object |  | Yes |
+| `FabricWorkspaceId` | The GUID of the workspace that contains the lakehouse. | String | No | Yes |
+| `LakehouseId` | The GUID of the lakehouse. | String | No | Yes |
+| `TargetPath` | A folder or shortcut within the lakehouse. When unspecified, the entire lakehouse is indexed. | String | No | No |
+
+::: zone-end
+
+::: zone pivot="python"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryption_key` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `indexed_one_lake_parameters` | Parameters specific to OneLake knowledge sources: `fabric_workspace_id`, `lakehouse_id`, and `target_path`. | Object |  | Yes |
+| `fabric_workspace_id` | The GUID of the workspace that contains the lakehouse. | String | No | Yes |
+| `lakehouse_id` | The GUID of the lakehouse. | String | No | Yes |
+| `target_path` | A folder or shortcut within the lakehouse. When unspecified, the entire lakehouse is indexed. | String | No | No |
+
+::: zone-end
+
+::: zone pivot="rest"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `kind` | The kind of knowledge source, which is `indexedOneLake` in this case. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `indexedOneLakeParameters` | Parameters specific to OneLake knowledge sources: `fabricWorkspaceId`, `lakehouseId`, and `targetPath`. | Object |  | Yes |
+| `fabricWorkspaceId` | The GUID of the workspace that contains the lakehouse. | String | No | Yes |
+| `lakehouseId` | The GUID of the lakehouse. | String | No | Yes |
+| `targetPath` | A folder or shortcut within the lakehouse. When unspecified, the entire lakehouse is indexed. | String | No | No |
+
+::: zone-end
+
+### Ingestion parameters properties
+
+::: zone pivot="csharp"
+
+[!INCLUDE [C# ingestionParameters properties](includes/how-tos/knowledge-source-ingestion-parameters-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Python ingestionParameters properties](includes/how-tos/knowledge-source-ingestion-parameters-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [REST ingestionParameters properties](includes/how-tos/knowledge-source-ingestion-parameters-rest.md)]
+
+::: zone-end
+
+## Check ingestion status
+
+::: zone pivot="csharp"
+
+[!INCLUDE [C# knowledge source status](includes/how-tos/knowledge-source-status-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Python knowledge source status](includes/how-tos/knowledge-source-status-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [REST knowledge source status](includes/how-tos/knowledge-source-status-rest.md)]
+
+::: zone-end
+
+## Review the created objects
+
+When you create an indexed OneLake knowledge source, your search service also creates an indexer, index, skillset, and data source. We don't recommend that you edit these objects, as introducing an error or incompatibility can break the pipeline.
+
+After you create a knowledge source, the response lists the created objects. These objects are created according to a fixed template, and their names are based on the name of the knowledge source. You can't change the object names.
+
+We recommend using the Azure portal to validate output creation. The workflow is:
+
+1. Check the indexer for success or failure messages. Connection or quota errors appear here.
+1. Check the index for searchable content. Use Search Explorer to run queries.
+1. Check the skillset to learn how your content is chunked and optionally vectorized.
+1. Check the data source for connection details. Our example uses API keys for simplicity, but you can use Microsoft Entra ID for authentication and role-based access control for authorization.
+
+## Assign to a knowledge base
+
+If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+
+For any knowledge base that specifies an indexed OneLake knowledge source, be sure to set `includeReferenceSourceData` to `true`. This step is necessary for pulling the source document URL into the citation.
+
+After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+
+::: zone pivot="csharp"
+
+> [!TIP]
+> To enforce document-level permissions, set `IngestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+::: zone-end
+
+::: zone pivot="python"
+
+> [!TIP]
+> To enforce document-level permissions, set `ingestion_permission_options` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+::: zone-end
+
+::: zone pivot="rest"
+
+> [!TIP]
+> To enforce document-level permissions, set `ingestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+::: zone-end
+
+## Delete a knowledge source
+
+::: zone pivot="csharp"
+
+[!INCLUDE [Delete knowledge source using C#](includes/how-tos/knowledge-source-delete-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Delete knowledge source using Python](includes/how-tos/knowledge-source-delete-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [Delete knowledge source using REST](includes/how-tos/knowledge-source-delete-rest.md)]
+
 ::: zone-end
 
 ## Related content
 
-+ [Agentic retrieval in Azure AI Search](search-agentic-retrieval-concept.md)
++ [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
 + [Agentic RAG: Build a reasoning retrieval engine with Azure AI Search (YouTube video)](https://www.youtube.com/watch?v=PeTmOidqHM8)
 + [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)

@@ -3,22 +3,249 @@ title: Create a Search Index Knowledge Source
 description: Learn how to create a search index knowledge source, which specifies an index used by a knowledge base for agentic retrieval workloads.
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 03/25/2026
+ms.date: 04/14/2026
 zone_pivot_groups: search-csharp-python-rest
 ---
 
 # Create a search index knowledge source
 
+[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
+
+A *search index knowledge source* specifies a connection to an Azure AI Search index that provides searchable content in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+
+### Usage support
+
+| [Azure portal](get-started-portal-agentic-retrieval.md) | [Microsoft Foundry portal](/azure/ai-foundry/agents/concepts/what-is-foundry-iq#workflow) | [.NET SDK](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/search/Azure.Search.Documents/CHANGELOG.md) | [Python SDK](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [Java SDK](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [JavaScript SDK](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/search/search-documents/CHANGELOG.md) | [REST API](/rest/api/searchservice/knowledge-sources?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |
+|--|--|--|--|--|--|--|
+| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
+
+## Prerequisites
+
++ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md). You must have [semantic ranker enabled](semantic-how-to-enable-disable.md).
+
++ A search index containing plain text or vector content with a semantic configuration. [Review the index criteria for agentic retrieval](agentic-retrieval-how-to-create-index.md#criteria-for-agentic-retrieval). The index must be on the same search service as the knowledge base.
+
++ Permission to create and use objects on Azure AI Search. We recommend [role-based access](search-security-rbac.md), but you can use [API keys](search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](search-get-started-rbac.md).
+
+::: zone pivot="csharp"
+
++ The latest [`Azure.Search.Documents` preview package](https://www.nuget.org/packages/Azure.Search.Documents/11.8.0-beta.1): `dotnet add package Azure.Search.Documents --prerelease`
+
+::: zone-end
+
+::: zone pivot="python"
+
++ The latest [`azure-search-documents` preview package](https://pypi.org/project/azure-search-documents/11.7.0b2/): `pip install --pre azure-search-documents`
+
+::: zone-end
+
+::: zone pivot="rest"
+
++ The [2025-11-01-preview](/rest/api/searchservice/operation-groups?view=rest-searchservice-2025-11-01-preview&preserve-view=true) version of the Search Service REST APIs.
+
+::: zone-end
+
+## Check for existing knowledge sources
+
 ::: zone pivot="csharp"
-[!INCLUDE [C#](includes/how-tos/agentic-knowledge-source-how-to-search-index-csharp.md)]
+
+[!INCLUDE [Check for existing knowledge sources using C#](includes/how-tos/knowledge-source-check-csharp.md)]
+
 ::: zone-end
 
 ::: zone pivot="python"
-[!INCLUDE [Python](includes/how-tos/agentic-knowledge-source-how-to-search-index-python.md)]
+
+[!INCLUDE [Check for existing knowledge sources using Python](includes/how-tos/knowledge-source-check-python.md)]
+
 ::: zone-end
 
 ::: zone pivot="rest"
-[!INCLUDE [REST](includes/how-tos/agentic-knowledge-source-how-to-search-index-rest.md)]
+
+[!INCLUDE [Check for existing knowledge sources using REST](includes/how-tos/knowledge-source-check-rest.md)]
+
+::: zone-end
+
+The following JSON is an example response for a search index knowledge source. Notice that the knowledge source specifies a single index name and which fields in the index to include in the query.
+
+```json
+{
+  "name": "my-search-index-ks",
+  "kind": "searchIndex",
+  "description": "A sample search index knowledge source.",
+  "encryptionKey": null,
+  "searchIndexParameters": {
+    "searchIndexName": "my-search-index",
+    "semanticConfigurationName": null,
+    "sourceDataFields": [],
+    "searchFields": []
+  }
+}
+```
+
+## Create a knowledge source
+
+::: zone pivot="csharp"
+
+Run the following code to create a search index knowledge source.
+
+```csharp
+// Create a search index knowledge source
+using Azure.Search.Documents.Indexes;
+using Azure.Search.Documents.Indexes.Models;
+using Azure;
+
+var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new AzureKeyCredential(apiKey));
+
+var indexKnowledgeSource = new SearchIndexKnowledgeSource(
+    name: knowledgeSourceName,
+    searchIndexParameters: new SearchIndexKnowledgeSourceParameters(searchIndexName: indexName)
+    {
+        SourceDataFields = { new SearchIndexFieldReference(name: "id"), new SearchIndexFieldReference(name: "page_chunk"), new SearchIndexFieldReference(name: "page_number") }
+    }
+);
+
+await indexClient.CreateOrUpdateKnowledgeSourceAsync(indexKnowledgeSource);
+Console.WriteLine($"Knowledge source '{knowledgeSourceName}' created or updated successfully.");
+```
+
+::: zone-end
+
+::: zone pivot="python"
+
+Run the following code to create a search index knowledge source.
+
+```python
+# Create a search index knowledge source
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient
+from azure.search.documents.indexes.models import SearchIndexKnowledgeSource, SearchIndexKnowledgeSourceParameters, SearchIndexFieldReference
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+
+knowledge_source = SearchIndexKnowledgeSource(
+    name = "my-search-index-ks",
+    description= "This knowledge source pulls from an existing index designed for agentic retrieval.",
+    encryption_key = None,
+    search_index_parameters = SearchIndexKnowledgeSourceParameters(
+        search_index_name = "search_index_name",
+        semantic_configuration_name = "semantic_configuration_name",
+        source_data_fields = [
+            SearchIndexFieldReference(name="description"),
+            SearchIndexFieldReference(name="category"),
+        ],
+        search_fields = [
+            SearchIndexFieldReference(name="id")
+        ],
+    )
+)
+
+index_client.create_or_update_knowledge_source(knowledge_source)
+print(f"Knowledge source '{knowledge_source.name}' created or updated successfully.")
+```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+Use [Knowledge Sources - Create or Update (REST API)](/rest/api/searchservice/knowledge-sources/create-or-update?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to create a search index knowledge source.
+
+```http
+PUT {{search-url}}/knowledgesources/my-search-index-ks?api-version=2025-11-01-preview
+api-key: {{api-key}}
+Content-Type: application/json
+
+{
+    "name": "my-search-index-ks",
+    "kind": "searchIndex",
+    "description": "This knowledge source pulls from an existing index designed for agentic retrieval.",
+    "encryptionKey": null,
+    "searchIndexParameters": {
+        "searchIndexName": "<YOUR INDEX NAME>",
+        "semanticConfigurationName": "my-semantic-config",
+        "sourceDataFields": [
+          { "name": "description" },
+          { "name": "category" }
+        ]
+    }
+}
+```
+
+::: zone-end
+
+### Source-specific properties
+
+You can pass the following properties to create a search index knowledge source.
+
+::: zone pivot="csharp"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `Name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `Description` | A description of the knowledge source. | String | Yes | No |
+| `EncryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `SearchIndexParameters` | Parameters specific to search index knowledge sources: `SearchIndexName`, `SemanticConfigurationName`, `SourceDataFields`, and `SearchFields`. | Object | Yes | Yes |
+| `SearchIndexName` | The name of the existing search index. | String | Yes | Yes |
+| `SemanticConfigurationName` | Overrides the default semantic configuration for the search index. | String | Yes | No |
+| `SourceDataFields` | The index fields returned when you specify `IncludeReferenceSourceData` in the knowledge base definition. These fields are used for citations and should be `retrievable`. Examples include the document name, file name, page numbers, or chapter numbers. | Array | Yes | No |
+| `SearchFields` | The index fields to specifically search against. When unspecified, all fields are searched. | Array | Yes | No |
+
+::: zone-end
+
+::: zone pivot="python"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryption_key` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `search_index_parameters` | Parameters specific to search index knowledge sources: `search_index_name`, `semantic_configuration_name`, `source_data_fields`, and `search_fields`. | Object | Yes | Yes |
+| `search_index_name` | The name of the existing search index. | String | Yes | Yes |
+| `semantic_configuration_name` | Overrides the default semantic configuration for the search index. | String | Yes | No |
+| `source_data_fields` | The index fields returned when you specify `include_reference_source_data` in the knowledge base definition. These fields are used for citations and should be `retrievable`. Examples include the document name, file name, page numbers, or chapter numbers. | Array | Yes | No |
+| `search_fields` | The index fields to specifically search against. When unspecified, all fields are searched. | Array | Yes | No |
+
+::: zone-end
+
+::: zone pivot="rest"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `kind` | The kind of knowledge source, which is `searchIndex` in this case. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `searchIndexParameters` | Parameters specific to search index knowledge sources: `searchIndexName`, `semanticConfigurationName`, `sourceDataFields`, and `searchFields`. | Object | Yes | Yes |
+| `searchIndexName` | The name of the existing search index. | String | Yes | Yes |
+| `semanticConfigurationName` | Overrides the default semantic configuration for the search index. | String | Yes | No |
+| `sourceDataFields` | The index fields returned when you specify `includeReferenceSourceData` in the knowledge base definition. These fields are used for citations and should be `retrievable`. Examples include the document name, file name, page numbers, or chapter numbers. | Array | Yes | No |
+| `searchFields` | The index fields to specifically search against. When unspecified, all fields are searched. | Array | Yes | No |
+
+::: zone-end
+
+## Assign to a knowledge base
+
+If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+
+After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+
+## Delete a knowledge source
+
+::: zone pivot="csharp"
+
+[!INCLUDE [Delete knowledge source using C#](includes/how-tos/knowledge-source-delete-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Delete knowledge source using Python](includes/how-tos/knowledge-source-delete-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [Delete knowledge source using REST](includes/how-tos/knowledge-source-delete-rest.md)]
+
 ::: zone-end
 
 ## Related content

@@ -3,22 +3,426 @@ title: Create a SharePoint (Indexed) Knowledge Source
 description: Learn how to create an indexed SharePoint knowledge source, which ingests content from SharePoint sites into a searchable index on Azure AI Search.
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 03/25/2026
+ms.date: 04/14/2026
 zone_pivot_groups: search-csharp-python-rest
 ---
 
 # Create an indexed SharePoint knowledge source
 
+[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
+
+Use an *indexed SharePoint knowledge source* to index and query SharePoint content in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+
+When you create an indexed SharePoint knowledge source, you specify a SharePoint connection string, models, and properties to automatically generate the following Azure AI Search objects:
+
++ A data source that points to SharePoint sites.
++ A skillset that chunks and optionally vectorizes multimodal content.
++ An index that stores enriched content and meets the criteria for agentic retrieval.
++ An indexer that uses the previous objects to drive the indexing and enrichment pipeline.
+
+### Usage support
+
+| [Azure portal](get-started-portal-agentic-retrieval.md) | [Microsoft Foundry portal](/azure/ai-foundry/agents/concepts/what-is-foundry-iq#workflow) | [.NET SDK](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/search/Azure.Search.Documents/CHANGELOG.md) | [Python SDK](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [Java SDK](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [JavaScript SDK](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/search/search-documents/CHANGELOG.md) | [REST API](/rest/api/searchservice/knowledge-sources?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |
+|--|--|--|--|--|--|--|
+| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
+
+## Prerequisites
+
++ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md). You must have [semantic ranker enabled](semantic-how-to-enable-disable.md).
+
++ Completion of the [SharePoint indexer prerequisites](search-how-to-index-sharepoint-online.md#prerequisites).
+
++ Completion of the following SharePoint indexer configuration steps:
+
+  + [Step 1: Enable a managed identity for Azure AI Search](search-how-to-index-sharepoint-online.md#step-1-optional-enable-system-assigned-managed-identity) (required only for secretless authentication; skip if using a client secret)
+  + [Step 2: Choose either delegated or application permissions](search-how-to-index-sharepoint-online.md#step-2-decide-which-permissions-the-indexer-requires)
+  + [Step 3: Create a Microsoft Entra application registration](search-how-to-index-sharepoint-online.md#step-3-create-a-microsoft-entra-application-registration) (for application permissions, you also configure a [client secret](search-how-to-index-sharepoint-online.md#using-client-secret) or [secretless authentication](search-how-to-index-sharepoint-online.md#using-secretless-authentication-to-obtain-application-tokens))
+
++ Permission to create and use objects on Azure AI Search. We recommend [role-based access](search-security-rbac.md), but you can use [API keys](search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](search-get-started-rbac.md).
+
+::: zone pivot="csharp"
+
++ The latest [`Azure.Search.Documents` preview package](https://www.nuget.org/packages/Azure.Search.Documents/11.8.0-beta.1): `dotnet add package Azure.Search.Documents --prerelease`
+
+::: zone-end
+
+::: zone pivot="python"
+
++ The latest [`azure-search-documents` preview package](https://pypi.org/project/azure-search-documents/11.7.0b2/): `pip install --pre azure-search-documents`
+
+::: zone-end
+
+::: zone pivot="rest"
+
++ The [2025-11-01-preview](/rest/api/searchservice/operation-groups?view=rest-searchservice-2025-11-01-preview&preserve-view=true) version of the Search Service REST APIs.
+
+::: zone-end
+
+## Check for existing knowledge sources
+
 ::: zone pivot="csharp"
-[!INCLUDE [C#](includes/how-tos/agentic-knowledge-source-how-to-sharepoint-indexed-csharp.md)]
+
+[!INCLUDE [Check for existing knowledge sources using C#](includes/how-tos/knowledge-source-check-csharp.md)]
+
 ::: zone-end
 
 ::: zone pivot="python"
-[!INCLUDE [Python](includes/how-tos/agentic-knowledge-source-how-to-sharepoint-indexed-python.md)]
+
+[!INCLUDE [Check for existing knowledge sources using Python](includes/how-tos/knowledge-source-check-python.md)]
+
 ::: zone-end
 
 ::: zone pivot="rest"
-[!INCLUDE [REST](includes/how-tos/agentic-knowledge-source-how-to-sharepoint-indexed-rest.md)]
+
+[!INCLUDE [Check for existing knowledge sources using REST](includes/how-tos/knowledge-source-check-rest.md)]
+
+::: zone-end
+
+The following JSON is an example response for an indexed SharePoint knowledge source.
+
+```json
+{
+  "name": "my-indexed-sharepoint-ks",
+  "kind": "indexedSharePoint",
+  "description": "A sample indexed SharePoint knowledge source",
+  "encryptionKey": null,
+  "indexedSharePointParameters": {
+    "connectionString": "<redacted>",
+    "containerName": "defaultSiteLibrary",
+    "query": null,
+    "ingestionParameters": {
+      "disableImageVerbalization": false,
+      "ingestionPermissionOptions": [],
+      "contentExtractionMode": "minimal",
+      "identity": null,
+      "embeddingModel": {
+        "kind": "azureOpenAI",
+        "azureOpenAIParameters": {
+          "resourceUri": "<redacted>",
+          "deploymentId": "text-embedding-3-large",
+          "apiKey": "<redacted>",
+          "modelName": "text-embedding-3-large",
+          "authIdentity": null
+        }
+      },
+      "chatCompletionModel": null,
+      "ingestionSchedule": null,
+      "assetStore": null,
+      "aiServices": null
+    },
+    "createdResources": {
+      "datasource": "my-indexed-sharepoint-ks-datasource",
+      "indexer": "my-indexed-sharepoint-ks-indexer",
+      "skillset": "my-indexed-sharepoint-ks-skillset",
+      "index": "my-indexed-sharepoint-ks-index"
+    }
+  },
+  "indexedOneLakeParameters": null
+}
+```
+
+> [!NOTE]
+> Sensitive information is redacted. The generated resources appear at the end of the response.
+
+## Create a knowledge source
+
+::: zone pivot="csharp"
+
+Run the following code to create an indexed SharePoint knowledge source.
+
+```csharp
+// Create an IndexedSharePoint knowledge source
+using Azure.Search.Documents.Indexes;
+using Azure.Search.Documents.Indexes.Models;
+using Azure.Search.Documents.KnowledgeBases.Models;
+using Azure;
+
+var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new AzureKeyCredential(apiKey));
+
+var chatCompletionParams = new AzureOpenAIVectorizerParameters
+{
+    ResourceUri = new Uri(aoaiEndpoint),
+    DeploymentName = aoaiGptDeployment,
+    ModelName = aoaiGptModel
+};
+
+var embeddingParams = new AzureOpenAIVectorizerParameters
+{
+    ResourceUri = new Uri(aoaiEndpoint),
+    DeploymentName = aoaiEmbeddingDeployment,
+    ModelName = aoaiEmbeddingModel
+};
+
+var ingestionParams = new KnowledgeSourceIngestionParameters
+{
+    DisableImageVerbalization = false,
+    ChatCompletionModel = new KnowledgeBaseAzureOpenAIModel(azureOpenAIParameters: chatCompletionParams),
+    EmbeddingModel = new KnowledgeSourceAzureOpenAIVectorizer
+    {
+        AzureOpenAIParameters = embeddingParams
+    }
+};
+
+var sharePointParams = new IndexedSharePointKnowledgeSourceParameters(
+    connectionString: sharePointConnectionString,
+    containerName: "defaultSiteLibrary")
+{
+    IngestionParameters = ingestionParams
+};
+
+var knowledgeSource = new IndexedSharePointKnowledgeSource(
+    name: "my-indexed-sharepoint-ks",
+    indexedSharePointParameters: sharePointParams)
+{
+    Description = "A sample indexed SharePoint knowledge source."
+};
+
+await indexClient.CreateOrUpdateKnowledgeSourceAsync(knowledgeSource);
+Console.WriteLine($"Knowledge source '{knowledgeSource.Name}' created or updated successfully.");
+```
+
+::: zone-end
+
+::: zone pivot="python"
+
+Run the following code to create an indexed SharePoint knowledge source.
+
+```python
+# Create an indexed SharePoint knowledge source
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient
+from azure.search.documents.indexes.models import IndexedSharePointKnowledgeSource, IndexedSharePointKnowledgeSourceParameters, KnowledgeBaseAzureOpenAIModel, AzureOpenAIVectorizerParameters, KnowledgeSourceAzureOpenAIVectorizer, KnowledgeSourceContentExtractionMode, KnowledgeSourceIngestionParameters
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+
+knowledge_source = IndexedSharePointKnowledgeSource(
+    name = "my-indexed-sharepoint-ks",
+    description = "A sample indexed SharePoint knowledge source.",
+    encryption_key = None,
+    indexed_share_point_parameters = IndexedSharePointKnowledgeSourceParameters(
+        connection_string = "connection_string",
+        container_name = "defaultSiteLibrary",
+        query = None,
+        ingestion_parameters = KnowledgeSourceIngestionParameters(
+            identity = None,
+            disable_image_verbalization = False,
+            chat_completion_model = KnowledgeBaseAzureOpenAIModel(
+                azure_open_ai_parameters = AzureOpenAIVectorizerParameters(
+                    resource_url = "aoai_endpoint",
+                    deployment_name = "aoai_gpt_deployment",
+                    model_name = "aoai_gpt_model",
+                    api_key = "aoai_api_key"
+                )
+            ),
+            embedding_model = KnowledgeSourceAzureOpenAIVectorizer(
+                azure_open_ai_parameters=AzureOpenAIVectorizerParameters(
+                    resource_url = "aoai_endpoint",
+                    deployment_name = "aoai_embedding_deployment",
+                    model_name = "aoai_embedding_model",
+                    api_key = "aoai_api_key"
+                )
+            ),
+            content_extraction_mode = KnowledgeSourceContentExtractionMode.MINIMAL,
+            ingestion_schedule = None,
+            ingestion_permission_options = None
+        )
+    )
+)
+
+index_client.create_or_update_knowledge_source(knowledge_source)
+print(f"Knowledge source '{knowledge_source.name}' created or updated successfully.")
+```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+Use [Knowledge Sources - Create or Update (REST API)](/rest/api/searchservice/knowledge-sources/create-or-update?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to create an indexed SharePoint knowledge source.
+
+```http
+PUT {{search-url}}/knowledgesources/my-indexed-sharepoint-ks?api-version=2025-11-01-preview
+api-key: {{api-key}}
+Content-Type: application/json
+
+{
+    "name": "my-indexed-sharepoint-ks",
+    "kind": "indexedSharePoint",
+    "description": "A sample indexed SharePoint knowledge source.",
+    "encryptionKey": null,
+    "indexedSharePointParameters": {
+        "connectionString": "{{sharepoint-connection-string}}",
+        "containerName": "defaultSiteLibrary",
+        "query": null,
+        "ingestionParameters": {
+            "identity": null,
+            "embeddingModel": {
+                "kind": "azureOpenAI",
+                "azureOpenAIParameters": {
+                    "deploymentId": "text-embedding-3-large",
+                    "modelName": "text-embedding-3-large",
+                    "resourceUri": "{{aoai-endpoint}}",
+                    "apiKey": "{{aoai-key}}"
+                }
+            },
+            "chatCompletionModel": null,
+            "disableImageVerbalization": false,
+            "ingestionSchedule": null,
+            "ingestionPermissionOptions": [],
+            "contentExtractionMode": "minimal"
+        }
+    }
+}
+```
+
+::: zone-end
+
+### Source-specific properties
+
+You can pass the following properties to create an indexed SharePoint knowledge source.
+
+::: zone pivot="csharp"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `Name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `Description` | A description of the knowledge source. | String | Yes | No |
+| `EncryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `IndexedSharePointKnowledgeSourceParameters` | Parameters specific to indexed SharePoint knowledge sources: `ConnectionString`, `ContainerName`, and `Query`. | Object | No | No |
+| `ConnectionString` | The connection string to a SharePoint site. For more information, see [Connection string syntax](search-how-to-index-sharepoint-online.md#connection-string-format). | String | Yes | Yes |
+| `ContainerName` | The SharePoint library to access. Use `defaultSiteLibrary` to index content from the site's default document library or `allSiteLibraries` to index content from every document library in the site. Ignore `useQuery` for now. | String | No | Yes |
+| `Query` | Optional [query](search-how-to-index-sharepoint-online.md#query) to filter SharePoint content. | String | Yes | No |
+
+::: zone-end
+
+::: zone pivot="python"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryption_key` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `indexed_share_point_parameters` | Parameters specific to indexed SharePoint knowledge sources: `connection_string`, `container_name`, and `query`. | Object | No | No |
+| `connection_string` | The connection string to a SharePoint site. For more information, see [Connection string syntax](search-how-to-index-sharepoint-online.md#connection-string-format). | String | Yes | Yes |
+| `container_name` | The SharePoint library to access. Use `defaultSiteLibrary` to index content from the site's default document library or `allSiteLibraries` to index content from every document library in the site. Ignore `useQuery` for now. | String | No | Yes |
+| `query` | Optional [query](search-how-to-index-sharepoint-online.md#query) to filter SharePoint content. | String | Yes | No |
+
+::: zone-end
+
+::: zone pivot="rest"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `kind` | The kind of knowledge source, which is `indexedSharePoint` in this case. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge source and the generated objects. | Object | Yes | No |
+| `indexedSharePointParameters` | Parameters specific to indexed SharePoint knowledge sources: `connectionString`, `containerName`, and `query`. | Object | No | Yes |
+| `connectionString` | The connection string to a SharePoint site. For more information, see [Connection string syntax](search-how-to-index-sharepoint-online.md#connection-string-format). | String | Yes | Yes |
+| `containerName` | The SharePoint library to access. Use `defaultSiteLibrary` to index content from the site's default document library or `allSiteLibraries` to index content from every document library in the site. Ignore `useQuery` for now. | String | No | Yes |
+| `query` | Optional [query](search-how-to-index-sharepoint-online.md#query) to filter SharePoint content. | String | Yes | No |
+
+::: zone-end
+
+### Ingestion parameters properties
+
+::: zone pivot="csharp"
+
+[!INCLUDE [C# ingestionParameters properties](includes/how-tos/knowledge-source-ingestion-parameters-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Python ingestionParameters properties](includes/how-tos/knowledge-source-ingestion-parameters-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [REST ingestionParameters properties](includes/how-tos/knowledge-source-ingestion-parameters-rest.md)]
+
+::: zone-end
+
+## Check ingestion status
+
+::: zone pivot="csharp"
+
+[!INCLUDE [C# knowledge source status](includes/how-tos/knowledge-source-status-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Python knowledge source status](includes/how-tos/knowledge-source-status-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [REST knowledge source status](includes/how-tos/knowledge-source-status-rest.md)]
+
+::: zone-end
+
+## Review the created objects
+
+When you create an indexed SharePoint knowledge source, your search service also creates an indexer, index, skillset, and data source. We don't recommend that you edit these objects, as introducing an error or incompatibility can break the pipeline.
+
+After you create a knowledge source, the response lists the created objects. These objects are created according to a fixed template, and their names are based on the name of the knowledge source. You can't change the object names.
+
+We recommend using the Azure portal to validate output creation. The workflow is:
+
+1. Check the indexer for success or failure messages. Connection or quota errors appear here.
+1. Check the index for searchable content. Use Search Explorer to run queries.
+1. Check the skillset to learn how your content is chunked and optionally vectorized.
+1. Check the data source for connection details. Our example uses API keys for simplicity, but you can use Microsoft Entra ID for authentication and role-based access control for authorization.
+
+## Assign to a knowledge base
+
+If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+
+For any knowledge base that specifies an indexed SharePoint knowledge source, be sure to set `includeReferenceSourceData` to `true`. This step is necessary for pulling the source document URL into the citation.
+
+After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+
+::: zone pivot="csharp"
+
+> [!TIP]
+> To enforce document-level permissions, set `IngestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+::: zone-end
+
+::: zone pivot="python"
+
+> [!TIP]
+> To enforce document-level permissions, set `ingestion_permission_options` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+::: zone-end
+
+::: zone pivot="rest"
+
+> [!TIP]
+> To enforce document-level permissions, set `ingestionPermissionOptions` when you create this knowledge source, and then include the user's access token in the retrieve request. For more information, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+::: zone-end
+
+## Delete a knowledge source
+
+::: zone pivot="csharp"
+
+[!INCLUDE [Delete knowledge source using C#](includes/how-tos/knowledge-source-delete-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Delete knowledge source using Python](includes/how-tos/knowledge-source-delete-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [Delete knowledge source using REST](includes/how-tos/knowledge-source-delete-rest.md)]
+
 ::: zone-end
 
 ## Related content

@@ -3,24 +3,438 @@ title: Create a SharePoint (Remote) Knowledge Source
 description: Learn how to create a remote SharePoint knowledge source, which tells an agentic retrieval engine in Azure AI Search to query SharePoint sites directly.
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 03/25/2026
+ms.date: 04/14/2026
 zone_pivot_groups: search-csharp-python-rest
 ---
 
 # Create a remote SharePoint knowledge source
 
+[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
+
+A *remote SharePoint knowledge source* uses the [Copilot Retrieval API](/microsoft-365-copilot/extensibility/api/ai-services/retrieval/overview) to query textual content directly from SharePoint in Microsoft 365. No search index or connection string is needed. Only textual content is queried, and usage is billed through Microsoft 365 and a Copilot license.
+
+To limit sites or constrain search, set a [filter expression](#filter-expression-examples) to scope by URLs, date ranges, file types, and other metadata. The caller's identity must be recognized by both the Azure tenant and the Microsoft 365 tenant because the retrieval engine queries SharePoint on behalf of the user.
+
+Like any other knowledge source, you specify a remote SharePoint knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md) and use the results as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+
+### Usage support
+
+| [Azure portal](get-started-portal-agentic-retrieval.md) | [Microsoft Foundry portal](/azure/ai-foundry/agents/concepts/what-is-foundry-iq#workflow) | [.NET SDK](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/search/Azure.Search.Documents/CHANGELOG.md) | [Python SDK](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [Java SDK](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [JavaScript SDK](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/search/search-documents/CHANGELOG.md) | [REST API](/rest/api/searchservice/knowledge-sources?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |
+|--|--|--|--|--|--|--|
+| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
+
+## Prerequisites
+
++ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md). You must have [semantic ranker enabled](semantic-how-to-enable-disable.md). 
+
++ SharePoint in a Microsoft 365 tenant that's under the same Microsoft Entra ID tenant as Azure.
+
++ A Microsoft 365 Copilot license for query-time access to SharePoint content.
+
++ Permission to create and use objects on Azure AI Search. We recommend [role-based access](search-security-rbac.md), but you can use [API keys](search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](search-get-started-rbac.md).
+
+::: zone pivot="csharp"
+
++ The latest [`Azure.Search.Documents` preview package](https://www.nuget.org/packages/Azure.Search.Documents/11.8.0-beta.1): `dotnet add package Azure.Search.Documents --prerelease`
+
+::: zone-end
+
+::: zone pivot="python"
+
++ The latest [`azure-search-documents` preview package](https://pypi.org/project/azure-search-documents/11.7.0b2/): `pip install --pre azure-search-documents`
+
+::: zone-end
+
+::: zone pivot="rest"
+
++ The [2025-11-01-preview](/rest/api/searchservice/operation-groups?view=rest-searchservice-2025-11-01-preview&preserve-view=true) version of the Search Service REST APIs.
+
+::: zone-end
+
+## Limitations
+
+The following limitations in the [Copilot Retrieval API](/microsoft-365-copilot/extensibility/api/ai-services/retrieval/overview) apply to remote SharePoint knowledge sources.
+
++ There's no support for Copilot connectors or OneDrive content. Content is retrieved from SharePoint sites only.
+
++ Limit of 200 requests per user per hour.
+
++ Query character limit of 1,500 characters.
+
++ Hybrid queries are only supported for the following file extensions: .doc, .docx, .pptx, .pdf, .aspx, and .one.
+
++ Multimodal retrieval (nontextual content, including tables, images, and charts) isn't supported.
+
++ Maximum of 25 results from a query.
+
++ Results are returned by Copilot Retrieval API as unordered.
+
++ Invalid Keyword Query Language (KQL) filter expressions are ignored and the query continues to execute without the filter.
+
+## Check for existing knowledge sources
+
+::: zone pivot="csharp"
+
+[!INCLUDE [Check for existing knowledge sources using C#](includes/how-tos/knowledge-source-check-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Check for existing knowledge sources using Python](includes/how-tos/knowledge-source-check-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [Check for existing knowledge sources using REST](includes/how-tos/knowledge-source-check-rest.md)]
+
+::: zone-end
+
+The following JSON is an example response for a remote SharePoint knowledge source.
+
+```json
+{
+  "name": "my-sharepoint-ks",
+  "kind": "remoteSharePoint",
+  "description": "A sample remote SharePoint knowledge source",
+  "encryptionKey": null,
+  "remoteSharePointParameters": {
+    "filterExpression": "filetype:docx",
+    "containerTypeId": null,
+    "resourceMetadata": [
+      "Author",
+      "Title"
+    ]
+  }
+}
+```
+
+## Create a knowledge source
+
 ::: zone pivot="csharp"
-[!INCLUDE [C#](includes/how-tos/agentic-knowledge-source-how-to-sharepoint-remote-csharp.md)]
+
+Run the following code to create a remote SharePoint knowledge source.
+
+```csharp
+// Create a remote SharePoint knowledge source
+using Azure.Search.Documents.Indexes;
+using Azure.Search.Documents.Indexes.Models;
+using Azure.Search.Documents.KnowledgeBases.Models;
+using Azure;
+
+var indexClient = new SearchIndexClient(new Uri(searchEndpoint), credential);
+
+var knowledgeSource = new RemoteSharePointKnowledgeSource(name: "my-remote-sharepoint-ks")
+{
+    Description = "This knowledge source queries .docx files in a trusted Microsoft 365 tenant.",
+    RemoteSharePointParameters = new RemoteSharePointKnowledgeSourceParameters()
+    {
+        FilterExpression = "filetype:docx",
+        ResourceMetadata = { "Author", "Title" }
+    }
+};
+
+await indexClient.CreateOrUpdateKnowledgeSourceAsync(knowledgeSource);
+Console.WriteLine($"Knowledge source '{knowledgeSource.Name}' created or updated successfully.");
+```
+
 ::: zone-end
 
 ::: zone pivot="python"
-[!INCLUDE [Python](includes/how-tos/agentic-knowledge-source-how-to-sharepoint-remote-python.md)]
+
+Run the following code to create a remote SharePoint knowledge source.
+
+```python
+# Create a remote SharePoint knowledge source
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient
+from azure.search.documents.indexes.models import RemoteSharePointKnowledgeSource, RemoteSharePointKnowledgeSourceParameters
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+
+knowledge_source = RemoteSharePointKnowledgeSource(
+    name = "my-remote-sharepoint-ks",
+    description= "This knowledge source queries .docx files in a trusted Microsoft 365 tenant.",
+    encryption_key = None,
+    remote_share_point_parameters = RemoteSharePointKnowledgeSourceParameters(
+        filter_expression = "filetype:docx",
+        resource_metadata = ["Author", "Title"],
+        container_type_id = None
+    )
+)
+
+index_client.create_or_update_knowledge_source(knowledge_source)
+print(f"Knowledge source '{knowledge_source.name}' created or updated successfully.")
+```
+
 ::: zone-end
 
 ::: zone pivot="rest"
-[!INCLUDE [REST](includes/how-tos/agentic-knowledge-source-how-to-sharepoint-remote-rest.md)]
+
+Use [Knowledge Sources - Create or Update (REST API)](/rest/api/searchservice/knowledge-sources/create-or-update?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to create a remote SharePoint knowledge source.
+
+```http
+PUT {{search-url}}/knowledgesources/my-remote-sharepoint-ks?api-version=2025-11-01-preview
+api-key: {{api-key}}
+Content-Type: application/json
+
+{
+    "name": "my-remote-sharepoint-ks",
+    "kind": "remoteSharePoint",
+    "description": "This knowledge source queries .docx files in a trusted Microsoft 365 tenant.",
+    "encryptionKey": null,
+    "remoteSharePointParameters": {
+        "filterExpression": "filetype:docx",
+        "resourceMetadata": [ "Author", "Title" ],
+        "containerTypeId": null
+    }
+}
+```
+
+::: zone-end
+
+### Source-specific properties
+
+You can pass the following properties to create a remote SharePoint knowledge source.
+
+::: zone pivot="csharp"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `Name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `Description` | A description of the knowledge source. | String | Yes | No |
+| `EncryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in the knowledge source. | Object | Yes | No |
+| `RemoteSharePointParameters` | Parameters specific to remote SharePoint knowledge sources: `FilterExpression`, `ResourceMetadata`, and `ContainerTypeId`. | Object | No | No |
+| `FilterExpression` | An expression written in the SharePoint [KQL](/sharepoint/dev/general-development/keyword-query-language-kql-syntax-reference), which is used to specify sites and paths to content. | String | Yes | No |
+| `ResourceMetadata` | An array of standard metadata fields: author, file name, creation date, content type, and file type. | Array | Yes | No |
+| `ContainerTypeId` | Container ID for the SharePoint Embedded connection. When unspecified, SharePoint Online is used. | String | Yes | No |
+
 ::: zone-end
 
+::: zone pivot="python"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryption_key` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in the knowledge source. | Object | Yes | No |
+| `remote_share_point_parameters` | Parameters specific to remote SharePoint knowledge sources: `filter_expression`, `resource_metadata`, and `container_type_id`. | Object | No | No |
+| `filter_expression` | An expression written in the SharePoint [KQL](/sharepoint/dev/general-development/keyword-query-language-kql-syntax-reference), which is used to specify sites and paths to content. | String | Yes | No |
+| `resource_metadata` | An array of standard metadata fields: author, file name, creation date, content type, and file type. | Array | Yes | No |
+| `container_type_id` | Container ID for the SharePoint Embedded connection. When unspecified, SharePoint Online is used. | String | Yes | No |
+
+::: zone-end
+
+::: zone pivot="rest"
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `kind` | The kind of knowledge source, which is `remoteSharePoint` in this case. | String | No | Yes |
+| `description` | A description of the knowledge source. | String | Yes | No |
+| `encryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in the knowledge source. | Object | Yes | No |
+| `remoteSharePointParameters` | Parameters specific to remote SharePoint knowledge sources: `filterExpression`, `resourceMetadata`, and `containerTypeId`. | Object | No | No |
+| `filterExpression` | An expression written in the SharePoint [KQL](/sharepoint/dev/general-development/keyword-query-language-kql-syntax-reference), which is used to specify sites and paths to content. | String | Yes | No |
+| `resourceMetadata` | An array of standard metadata fields: author, file name, creation date, content type, and file type. | Array | Yes | No |
+| `containerTypeId` | Container ID for the SharePoint Embedded connection. When unspecified, SharePoint Online is used. | String | Yes | No |
+
+::: zone-end
+
+### Filter expression examples
+
+Not all SharePoint properties are supported in the `filterExpression`. For a list of supported properties, see the [API reference](/microsoft-365-copilot/extensibility/api/ai-services/retrieval/copilotroot-retrieval). For queryable properties, see [Queryable](/graph/connecting-external-content-manage-schema#queryable).
+
+Learn more about [KQL filters](/microsoft-365-copilot/extensibility/api/ai-services/retrieval/copilotroot-retrieval?pivots=graph-v1#example-7-use-filter-expressions) in the syntax reference.
+
+| Example | Filter expression |
+|---------|-------------------|
+| Filter to a single site by ID | `"filterExpression": "SiteID:\"00aa00aa-bb11-cc22-dd33-44ee44ee44ee\""` |
+| Filter to multiple sites by ID | `"filterExpression": "SiteID:\"00aa00aa-bb11-cc22-dd33-44ee44ee44ee\" OR SiteID:\"11bb11bb-cc22-dd33-ee44-55ff55ff55ff\""` |
+| Filter to files under a specific path | `"filterExpression": "Path:\"https://my-demo.sharepoint.com/sites/mysite/Shared Documents/en/mydocs\""` |
+| Filter to a specific date range | `"filterExpression": "LastModifiedTime >= 2024-07-22 AND LastModifiedTime <= 2025-01-08"` |
+| Filter to files of a specific file type | `"filterExpression": "FileExtension:\"docx\" OR FileExtension:\"pdf\" OR FileExtension:\"pptx\""` |
+| Filter to files of a specific information protection label | `"filterExpression": "InformationProtectionLabelId:\"f0ddcc93-d3c0-4993-b5cc-76b0a283e252\""` |
+
+## Assign to a knowledge base
+
+If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+
+## Query a knowledge base
+
+After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query SharePoint content. Remote SharePoint has source-specific behaviors for query-time filtering, query formulation, response fields, and permissions enforcement.
+
+### Apply a KQL filter at query time
+
+::: zone pivot="csharp"
+
+You can pass a `FilterExpressionAddOn` in the `KnowledgeSourceParams` on the retrieve request to apply a KQL filter at query time. If you specify `FilterExpressionAddOn` on the retrieve request and a `FilterExpression` on the knowledge source definition, the filters are AND'd together.
+
+```csharp
+var retrievalRequest = new KnowledgeBaseRetrievalRequest();
+retrievalRequest.Messages.Add(
+    new KnowledgeBaseMessage(
+        content: new[] {
+            new KnowledgeBaseMessageTextContent("contoso product planning")
+        }
+    ) { Role = "user" }
+);
+retrievalRequest.KnowledgeSourceParams.Add(
+    new RemoteSharePointKnowledgeSourceParams("my-remote-sharepoint-ks")
+    {
+        FilterExpressionAddOn = "filetype:docx"
+    }
+);
+
+var result = await kbClient.RetrieveAsync(
+    retrievalRequest, xMsQuerySourceAuthorization: token
+);
+```
+
+::: zone-end
+
+::: zone pivot="python"
+
+You can pass a `filter_expression_add_on` in the `knowledge_source_params` on the retrieve request to apply a KQL filter at query time. If you specify `filter_expression_add_on` on the retrieve request and a `filter_expression` on the knowledge source definition, the filters are AND'd together.
+
+```python
+from azure.search.documents.knowledgebases.models import (
+    KnowledgeBaseMessage,
+    KnowledgeBaseMessageTextContent,
+    KnowledgeBaseRetrievalRequest,
+    RemoteSharePointKnowledgeSourceParams,
+)
+
+request = KnowledgeBaseRetrievalRequest(
+    messages=[
+        KnowledgeBaseMessage(
+            role="user",
+            content=[
+                KnowledgeBaseMessageTextContent(
+                    text="contoso product planning"
+                )
+            ],
+        )
+    ],
+    knowledge_source_params=[
+        RemoteSharePointKnowledgeSourceParams(
+            knowledge_source_name="my-remote-sharepoint-ks",
+            filter_expression_add_on="filetype:docx",
+        )
+    ],
+)
+
+result = kb_client.retrieve(
+    retrieval_request=request,
+    x_ms_query_source_authorization=token,
+)
+```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+You can pass a `filterExpressionAddOn` in the `knowledgeSourceParams` on the retrieve request to apply a KQL filter at query time. If you specify `filterExpressionAddOn` on the retrieve request and a `filterExpression` on the knowledge source definition, the filters are AND'd together.
+
+```http
+POST {{search-url}}/knowledgebases/{{knowledge-base-name}}/retrieve?api-version=2025-11-01-preview
+Authorization: Bearer {{accessToken}}
+Content-Type: application/json
+x-ms-query-source-authorization: {{user-access-token}}
+
+{
+    "messages": [
+        {
+            "role": "user",
+            "content": [
+                { "type": "text", "text": "contoso product planning" }
+            ]
+        }
+    ],
+    "knowledgeSourceParams": [
+        {
+            "knowledgeSourceName": "my-remote-sharepoint-ks",
+            "kind": "remoteSharePoint",
+            "filterExpressionAddOn": "filetype:docx"
+        }
+    ]
+}
+```
+
+::: zone-end
+
+### Write effective queries
+
+::: zone pivot="csharp"
+
+Queries that ask about the content itself are more effective than questions about where a file is located or when it was last updated. For example, "Where is the keynote doc for Ignite 2024" might return no results because the content itself doesn't disclose its location. A `FilterExpression` on metadata is a better approach for file location or date-specific queries.
+
+::: zone-end
+
+::: zone pivot="python"
+
+Queries that ask about the content itself are more effective than questions about where a file is located or when it was last updated. For example, "Where is the keynote doc for Ignite 2024" might return no results because the content itself doesn't disclose its location. A `filter_expression` on metadata is a better approach for file location or date-specific queries.
+
+::: zone-end
+
+::: zone pivot="rest"
+
+Queries that ask about the content itself are more effective than questions about where a file is located or when it was last updated. For example, "Where is the keynote doc for Ignite 2024" might return no results because the content itself doesn't disclose its location. A `filterExpression` on metadata is a better approach for file location or date-specific queries.
+
+::: zone-end
+
+A more effective question is "What is the keynote doc for Ignite 2024". The response includes the synthesized answer, query activity and token counts, plus the URL and other metadata.
+
+### SharePoint-specific response fields
+
+Remote SharePoint results include fields that don't appear for other knowledge source types, such as `resourceMetadata`, `webUrl`, and `searchSensitivityLabelInfo`.
+
+```json
+{
+    "resourceMetadata": {
+        "Author": "Nuwan Amarathunga;Nurul Izzati",
+        "Title": "Ignite 2024 Keynote Address"
+    },
+    "rerankerScore": 2.489522,
+    "webUrl": "https://contoso-my.sharepoint.com/keynotes/Documents/Keynote-Ignite-2024.docx",
+    "searchSensitivityLabelInfo": {
+        "displayName": "Confidential\\Contoso Extended",
+        "sensitivityLabelId": "aaaaaaaa-0b0b-1c1c-2d2d-333333333333",
+        "tooltip": "Data is classified and protected.",
+        "priority": 5,
+        "color": "#FF8C00",
+        "isEncrypted": true
+    }
+}
+```
+
+### Enforce permissions at query time
+
+Remote SharePoint knowledge sources can enforce SharePoint permissions at query time. To enable this filtering, include the end user's access token in the retrieve request. The retrieval engine passes the token to the Copilot Retrieval API, which queries SharePoint and returns only content to which the user has access. SharePoint permissions and Microsoft Purview sensitivity labels are honored.
+
+Because remote SharePoint doesn't use a search index, no ingestion-time permissions configuration is needed. The access token is the only requirement.
+
+For instructions on passing the token, see [Enforce permissions at query time](agentic-retrieval-how-to-retrieve.md#enforce-permissions-at-query-time).
+
+## Delete a knowledge source
+
+::: zone pivot="csharp"
+
+[!INCLUDE [Delete knowledge source using C#](includes/how-tos/knowledge-source-delete-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Delete knowledge source using Python](includes/how-tos/knowledge-source-delete-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [Delete knowledge source using REST](includes/how-tos/knowledge-source-delete-rest.md)]
+
+::: zone-end
 
 ## Related content
 

@@ -5,25 +5,269 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2025
 ms.topic: how-to
-ms.date: 03/25/2026
+ms.date: 04/14/2026
 zone_pivot_groups: search-csharp-python-rest
 ---
 
 # Create a Web Knowledge Source resource
 
+> [!IMPORTANT]
+> + Web Knowledge Source, which uses Grounding with Bing Search and/or Grounding with Bing Custom Search, is a [First Party Consumption Service](https://www.microsoft.com/licensing/terms/product/ForOnlineServices/EAEAS) governed by the [Grounding with Bing terms of use](https://www.microsoft.com/en-us/bing/apis/grounding-legal-enterprise) and the [Microsoft Privacy Statement](https://www.microsoft.com/privacy/privacystatement).
+>
+> + The [Microsoft Data Protection Addendum](https://www.microsoft.com/licensing/docs/view/Microsoft-Products-and-Services-Data-Protection-Addendum-DPA) doesn't apply to data sent to Web Knowledge Source. When Customer uses Web Knowledge Source, Customer Data flows outside the Azure compliance and Geo boundary. This also means use of Web Knowledge Source waives all elevated Government Community Cloud security and compliance commitments to include data sovereignty and screened/citizenship-based support, as applicable.
+>
+> + Use of Web Knowledge Source incurs costs; learn more about [pricing](https://www.microsoft.com/en-us/bing/apis/grounding-pricing).
+>
+> + Learn more about how Azure admins can [manage access to use of Web Knowledge Source](agentic-knowledge-source-how-to-web-manage.md).
+
+[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
+
+*Web Knowledge Source* enables retrieval of real-time web data from Microsoft Bing in an agentic retrieval pipeline. [Knowledge sources](agentic-knowledge-source-overview.md) are created independently, referenced in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md), and used as grounding data when an agent or chatbot calls a [retrieve action](agentic-retrieval-how-to-retrieve.md) at query time.
+
+Bing Custom Search is always the search provider for Web Knowledge Source. Although you can't specify alternative search providers or engines, you can include or exclude specific *domains*, such as https://learn.microsoft.com. When no domains are specified, Web Knowledge Source has unrestricted access to the entire public internet.
+
+Web Knowledge Source works best alongside other knowledge sources. Use Web Knowledge Source when your proprietary content doesn't provide complete, up-to-date answers or when you want to supplement results with information from a commercial search engine.
+
+When you use Web Knowledge Source, keep the following in mind:
+
++ The response is always a single, formulated answer to the query instead of raw search results from the web.
+
++ Because Web Knowledge Source doesn't support extractive data, your knowledge base must use [answer synthesis](agentic-retrieval-how-to-answer-synthesis.md) and [low or medium reasoning effort](agentic-retrieval-how-to-create-knowledge-base.md#create-a-knowledge-base). You also can't define answer instructions.
+
+### Usage support
+
+| [Azure portal](get-started-portal-agentic-retrieval.md) | [Microsoft Foundry portal](/azure/ai-foundry/agents/concepts/what-is-foundry-iq#workflow) | [.NET SDK](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/search/Azure.Search.Documents/CHANGELOG.md) | [Python SDK](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [Java SDK](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [JavaScript SDK](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/search/search-documents/CHANGELOG.md) | [REST API](/rest/api/searchservice/knowledge-sources?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |
+|--|--|--|--|--|--|--|
+| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
+
+## Prerequisites
+
++ An Azure subscription with [access to Web Knowledge Source](agentic-knowledge-source-how-to-web-manage.md). By default, access is enabled. Contact your admin if access is disabled.
+
++ An Azure AI Search service in any [region that provides agentic retrieval](search-region-support.md). You must have [semantic ranker enabled](semantic-how-to-enable-disable.md). The service must also be in an [Azure public region](search-region-support.md#azure-public-regions), as Web Knowledge Source isn't supported in private or sovereign clouds.
+
++ Permission to create and use objects on Azure AI Search. We recommend [role-based access](search-security-rbac.md), but you can use [API keys](search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](search-get-started-rbac.md).
+
+::: zone pivot="csharp"
+
++ The latest [`Azure.Search.Documents` preview package](https://www.nuget.org/packages/Azure.Search.Documents/11.8.0-beta.1): `dotnet add package Azure.Search.Documents --prerelease`
+
+::: zone-end
+
+::: zone pivot="python"
+
++ The latest [`azure-search-documents` preview package](https://pypi.org/project/azure-search-documents/11.7.0b2/): `pip install --pre azure-search-documents`
+
+::: zone-end
+
+::: zone pivot="rest"
+
++ The [2025-11-01-preview](/rest/api/searchservice/operation-groups?view=rest-searchservice-2025-11-01-preview&preserve-view=true) version of the Search Service REST APIs.
+
+::: zone-end
+
+## Check for existing knowledge sources
+
+::: zone pivot="csharp"
+
+[!INCLUDE [Check for existing knowledge sources using C#](includes/how-tos/knowledge-source-check-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Check for existing knowledge sources using Python](includes/how-tos/knowledge-source-check-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [Check for existing knowledge sources using REST](includes/how-tos/knowledge-source-check-rest.md)]
+
+::: zone-end
+
+The following JSON is an example response for a Web Knowledge Source resource.
+
+```json
+{
+  "name": "my-web-ks",
+  "kind": "web",
+  "description": "A sample Web Knowledge Source.",
+  "encryptionKey": null,
+  "webParameters": {
+    "domains": null
+  }
+}
+```
+
+## Create a knowledge source
+
+::: zone pivot="csharp"
+
+Run the following code to create a Web Knowledge Source resource.
+
+```csharp
+// Create Web Knowledge Source
+using Azure.Search.Documents.Indexes;
+using Azure.Search.Documents.Indexes.Models;
+using Azure;
+
+var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new AzureKeyCredential(apiKey));
+
+var knowledgeSource = new WebKnowledgeSource(name: "my-web-ks")
+{
+    Description = "A sample Web Knowledge Source.",
+    WebParameters = new WebKnowledgeSourceParameters
+    {
+        Domains = new WebKnowledgeSourceDomains
+        {
+            AllowedDomains = 
+            {
+                new WebKnowledgeSourceDomain(address: "learn.microsoft.com") { IncludeSubpages = true }
+            },
+            BlockedDomains = 
+            {
+                new WebKnowledgeSourceDomain(address: "bing.com") { IncludeSubpages = false }
+            }
+        }
+    }
+};
+
+await indexClient.CreateOrUpdateKnowledgeSourceAsync(knowledgeSource);
+Console.WriteLine($"Knowledge source '{knowledgeSource.Name}' created or updated successfully.");
+```
+
+::: zone-end
+
+::: zone pivot="python"
+
+Run the following code to create a Web Knowledge Source resource.
+
+```python
+# Create Web Knowledge Source
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient
+from azure.search.documents.indexes.models import WebKnowledgeSource, WebKnowledgeSourceParameters, WebKnowledgeSourceDomains
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+
+knowledge_source = WebKnowledgeSource(
+    name = "my-web-ks",
+    description = "A sample Web Knowledge Source.",
+    encryption_key = None,
+    web_parameters = WebKnowledgeSourceParameters(
+        domains = WebKnowledgeSourceDomains(
+            allowed_domains = [ { "address": "learn.microsoft.com", "include_subpages": True } ],
+            blocked_domains = [ { "address": "bing.com", "include_subpages": False } ]
+        )
+    )
+)
+
+index_client.create_or_update_knowledge_source(knowledge_source)
+print(f"Knowledge source '{knowledge_source.name}' created or updated successfully.")
+```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+Use [Knowledge Sources - Create or Update (REST API)](/rest/api/searchservice/knowledge-sources/create-or-update?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to create a Web Knowledge Source resource.
+
+```http
+PUT {{search-url}}/knowledgesources/my-web-ks?api-version=2025-11-01-preview
+Content-Type: application/json
+api-key: {{api-key}}
+
+{
+  "name": "my-web-ks",
+  "kind": "web",
+  "description": "This knowledge source pulls content from the web.",
+  "encryptionKey": null,
+  "webParameters": {
+    "domains": {
+      "allowedDomains": [ { "address": "learn.microsoft.com", "includeSubpages": true } ],
+      "blockedDomains": [ { "address": "bing.com", "includeSubpages": false } ]
+    }
+  }
+}
+```
+
+::: zone-end
+
+### Source-specific properties
+
+You can pass the following properties to create a Web Knowledge Source resource.
+
 ::: zone pivot="csharp"
-[!INCLUDE [C#](includes/how-tos/agentic-knowledge-source-how-to-web-csharp.md)]
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `Name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `Description` | A description of the knowledge source. When unspecified, Azure AI Search applies a default description. | String | Yes | No |
+| `EncryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in the knowledge source. | Object | Yes | No |
+| `WebParameters` | Parameters specific to Web Knowledge Source. Currently, this is only `Domains`. | Object | Yes | No |
+| `Domains` | Domains to allow or block from the search space. By default, the knowledge source uses [Grounding with Bing Search](/azure/ai-foundry/agents/how-to/tools/bing-grounding) to search the entire public internet. When you specify domains, the knowledge source uses [Grounding with Bing Custom Search](/azure/ai-foundry/agents/how-to/tools/bing-custom-search) to restrict results to the specified domains. In both cases, Bing Custom Search is the search provider. | Object | Yes | No |
+| `AllowedDomains` | Domains to include in the search space. For each domain, you must specify its `address` in the `website.com` format. You can also specify whether to include the domain's subpages by setting `IncludeSubpages` to `true` or `false`. | Array | Yes | No |
+| `BlockedDomains` | Domains to exclude from the search space. For each domain, you must specify its `address` in the `website.com` format. You can also specify whether to include the domain's subpages by setting `IncludeSubpages` to `true` or `false`. | Array | Yes | No |
+
 ::: zone-end
 
 ::: zone pivot="python"
-[!INCLUDE [Python](includes/how-tos/agentic-knowledge-source-how-to-web-python.md)]
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `description` | A description of the knowledge source. When unspecified, Azure AI Search applies a default description. | String | Yes | No |
+| `encryption_key` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in the knowledge source. | Object | Yes | No |
+| `web_parameters` | Parameters specific to Web Knowledge Source. Currently, this is only `domains`. | Object | Yes | No |
+| `domains` | Domains to allow or block from the search space. By default, the knowledge source uses [Grounding with Bing Search](/azure/ai-foundry/agents/how-to/tools/bing-grounding) to search the entire public internet. When you specify domains, the knowledge source uses [Grounding with Bing Custom Search](/azure/ai-foundry/agents/how-to/tools/bing-custom-search) to restrict results to the specified domains. In both cases, Bing Custom Search is the search provider. | Object | Yes | No |
+| `allowed_domains` | Domains to include in the search space. For each domain, you must specify its `address` in the `website.com` format. You can also specify whether to include the domain's subpages by setting `include_subpages` to `true` or `false`. | Array | Yes | No |
+| `blocked_domains` | Domains to exclude from the search space. For each domain, you must specify its `address` in the `website.com` format. You can also specify whether to include the domain's subpages by setting `include_subpages` to `true` or `false`. | Array | Yes | No |
+
 ::: zone-end
 
 ::: zone pivot="rest"
-[!INCLUDE [REST](includes/how-tos/agentic-knowledge-source-how-to-web-rest.md)]
+
+| Name | Description | Type | Editable | Required |
+|--|--|--|--|--|
+| `name` | The name of the knowledge source, which must be unique within the knowledge sources collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | No | Yes |
+| `kind` | The kind of knowledge source, which is `web` in this case. | String | No | Yes |
+| `description` | A description of the knowledge source. When unspecified, Azure AI Search applies a default description. | String | Yes | No |
+| `encryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in the knowledge source. | Object | Yes | No |
+| `webParameters` | Parameters specific to Web Knowledge Source. Currently, this is only `domains`. | Object | Yes | No |
+| `domains` | Domains to allow or block from the search space. By default, the knowledge source uses [Grounding with Bing Search](/azure/ai-foundry/agents/how-to/tools/bing-grounding) to search the entire public internet. When you specify domains, the knowledge source uses [Grounding with Bing Custom Search](/azure/ai-foundry/agents/how-to/tools/bing-custom-search) to restrict results to the specified domains. In both cases, Bing Custom Search is the search provider. | Object | Yes | No |
+| `allowedDomains` | Domains to include in the search space. For each domain, you must specify its `address` in the `website.com` format. You can also specify whether to include the domain's subpages by setting `includeSubpages` to `true` or `false`. | Array | Yes | No |
+| `blockedDomains` | Domains to exclude from the search space. For each domain, you must specify its `address` in the `website.com` format. You can also specify whether to include the domain's subpages by setting `includeSubpages` to `true` or `false`. | Array | Yes | No |
+
+::: zone-end
+
+## Assign to a knowledge base
+
+If you're satisfied with the knowledge source, continue to the next step: specify the knowledge source in a [knowledge base](agentic-retrieval-how-to-create-knowledge-base.md).
+
+After the knowledge base is configured, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query the knowledge source.
+
+## Delete a knowledge source
+
+::: zone pivot="csharp"
+
+[!INCLUDE [Delete knowledge source using C#](includes/how-tos/knowledge-source-delete-csharp.md)]
+
+::: zone-end
+
+::: zone pivot="python"
+
+[!INCLUDE [Delete knowledge source using Python](includes/how-tos/knowledge-source-delete-python.md)]
+
+::: zone-end
+
+::: zone pivot="rest"
+
+[!INCLUDE [Delete knowledge source using REST](includes/how-tos/knowledge-source-delete-rest.md)]
+
 ::: zone-end
 
 ## Related content
 
 + [Manage access to Web Knowledge Source in your Azure subscription](agentic-knowledge-source-how-to-web-manage.md)
-+ [Agentic retrieval in Azure AI Search](search-agentic-retrieval-concept.md)
++ [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)

@@ -3,26 +3,542 @@ title: Create a Knowledge Base
 description: Learn how to create a knowledge base for agentic retrieval workloads in Azure AI Search.
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 01/15/2026
+ms.date: 04/14/2026
 zone_pivot_groups: search-csharp-python-rest
 ---
 
 # Create a knowledge base in Azure AI Search
 
+[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
+
+In Azure AI Search, a *knowledge base* is a top-level object that orchestrates [agentic retrieval](agentic-retrieval-overview.md). It defines which knowledge sources to query and the default behavior for retrieval operations. At query time, the [retrieve method](agentic-retrieval-how-to-retrieve.md) targets the knowledge base to run the configured retrieval pipeline.
+
+You can create a knowledge base in a [Foundry IQ](/azure/ai-foundry/agents/concepts/what-is-foundry-iq) workload in the Microsoft Foundry (new) portal. You also need a knowledge base in any agentic solutions that you create using the Azure AI Search APIs.
+
+A knowledge base specifies:
+
++ One or more knowledge sources that point to searchable content.
++ An optional LLM that provides reasoning capabilities for query planning and answer formulation.
++ A retrieval reasoning effort that determines whether an LLM is invoked and manages cost, latency, and quality.
++ Custom properties that control routing, source selection, output format, and object encryption.
+
+After you create a knowledge base, you can update its properties at any time. If the knowledge base is in use, updates take effect on the next retrieval.
+
+> [!IMPORTANT]
+> 2025-11-01-preview renames the 2025-08-01-preview "knowledge agent" to "knowledge base." This is a breaking change. We recommend [migrating existing code](agentic-retrieval-how-to-migrate.md) to the new APIs as soon as possible.
+
+### Usage support
+
+| [Azure portal](get-started-portal-agentic-retrieval.md) | [Microsoft Foundry portal](/azure/ai-foundry/agents/concepts/what-is-foundry-iq#workflow) | [.NET SDK](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/search/Azure.Search.Documents/CHANGELOG.md) | [Python SDK](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [Java SDK](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/search/azure-search-documents/CHANGELOG.md) | [JavaScript SDK](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/search/search-documents/CHANGELOG.md) | [REST API](/rest/api/searchservice/knowledge-bases?view=rest-searchservice-2025-11-01-preview&preserve-view=true) |
+|--|--|--|--|--|--|--|
+| ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
+
+## Prerequisites
+
++ Azure AI Search in any [region that provides agentic retrieval](search-region-support.md). You must have [semantic ranker enabled](semantic-how-to-enable-disable.md). If you're using a [managed identity](search-how-to-managed-identities.md) for role-based access to deployed models, your search service must be on the Basic pricing tier or higher.
+
++ One or more [knowledge sources](agentic-knowledge-source-overview.md#supported-knowledge-sources) on your search service.
+
++ Azure OpenAI with a [supported LLM](#supported-models) deployment.
+
++ Permission to create and use objects on Azure AI Search. We recommend [role-based access](search-security-rbac.md). **Search Service Contributor** can create and manage a knowledge base. **Search Index Data Reader** can run queries. Alternatively, you can use [API keys](search-security-api-keys.md) if a role assignment isn't feasible. For more information, see [Connect to a search service](search-get-started-rbac.md).
+
+::: zone pivot="csharp"
+
++ The latest [`Azure.Search.Documents` preview package](https://www.nuget.org/packages/Azure.Search.Documents/11.8.0-beta.1): `dotnet add package Azure.Search.Documents --prerelease`
+
+::: zone-end
+
+::: zone pivot="python"
+
++ The latest [`azure-search-documents` preview package](https://pypi.org/project/azure-search-documents/11.7.0b2/): `pip install --pre azure-search-documents`
+
+::: zone-end
+
+::: zone pivot="rest"
+
++ The [2025-11-01-preview](/rest/api/searchservice/operation-groups?view=rest-searchservice-2025-11-01-preview&preserve-view=true) version of the Search Service REST APIs.
+
+::: zone-end
+
+### Supported models
+
+Use one of the following LLMs from Azure OpenAI in Foundry Models. For deployment instructions, see [Deploy Microsoft Foundry Models in the Foundry portal](/azure/ai-foundry/how-to/deploy-models-openai).
+
++ `gpt-4o`
++ `gpt-4o-mini`
++ `gpt-4.1`
++ `gpt-4.1-nano`
++ `gpt-4.1-mini`
++ `gpt-5`
++ `gpt-5-nano`
++ `gpt-5-mini`
+
+## Configure access
+
+Azure AI Search needs access to the LLM from Azure OpenAI. We recommend Microsoft Entra ID for authentication and role-based access for authorization. To assign roles, you must be an **Owner or User Access Administrator**. If you can't use roles, use key-based authentication instead.
+
+### [**Use roles**](#tab/rbac)
+
 ::: zone pivot="csharp"
-[!INCLUDE [C#](includes/how-tos/agentic-retrieval-how-to-create-knowledge-base-csharp.md)]
+
+1. [Configure Azure AI Search to use a managed identity](search-how-to-managed-identities.md).
+
+1. On your model provider, such as Foundry Models, assign **Cognitive Services User** to the managed identity of your search service. If you're testing locally, assign the same role to your user account.
+
+1. For local testing, follow the steps in [Quickstart: Connect without keys](search-get-started-rbac.md) to sign in to a specific subscription and tenant. Use `DefaultAzureCredential` instead of `AzureKeyCredential` in each request, which should look similar to the following example:
+
+```csharp
+    using Azure.Search.Documents.Indexes;
+    using Azure.Identity;
+    
+    var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new DefaultAzureCredential());
+    ```
+
 ::: zone-end
 
 ::: zone pivot="python"
-[!INCLUDE [Python](includes/how-tos/agentic-retrieval-how-to-create-knowledge-base-python.md)]
+
+1. [Configure Azure AI Search to use a managed identity](search-how-to-managed-identities.md).
+
+1. On your model provider, such as Foundry Models, assign **Cognitive Services User** to the managed identity of your search service. If you're testing locally, assign the same role to your user account.
+
+1. For local testing, follow the steps in [Quickstart: Connect without keys](search-get-started-rbac.md) to sign in to a specific subscription and tenant. Use `DefaultAzureCredential` instead of `AzureKeyCredential` in each request, which should look similar to the following example:
+
+```python
+    # Authenticate using roles
+    from azure.identity import DefaultAzureCredential
+    index_client = SearchIndexClient(endpoint = "search_url", credential = DefaultAzureCredential())
+    ```
+
 ::: zone-end
 
 ::: zone pivot="rest"
-[!INCLUDE [REST](includes/how-tos/agentic-retrieval-how-to-create-knowledge-base-rest.md)]
+
+1. [Configure Azure AI Search to use a managed identity](search-how-to-managed-identities.md).
+
+1. On your model provider, such as Foundry Models, assign **Cognitive Services User** to the managed identity of your search service. If you're testing locally, assign the same role to your user account.
+
+1. For local testing, follow the steps in [Quickstart: Connect without keys](search-get-started-rbac.md) to get a personal access token for a specific subscription and tenant. Specify your access token in each request, which should look similar to the following example:
+
+```http
+    # List indexes using roles
+    GET https://{{search-url}}/indexes?api-version=2025-11-01-preview
+    Content-Type: application/json
+    Authorization: Bearer {{access-token}}
+    ```
+
+::: zone-end
+
+### [**Use keys**](#tab/keys)
+
+::: zone pivot="csharp"
+
+1. [Copy an Azure AI Search admin API key](search-security-api-keys.md#find-existing-keys) from the Azure portal.
+
+1. Use `AzureKeyCredential` to specify the API key in each request. Your code should look similar to the following example:
+
+```csharp
+    using Azure.Search.Documents.Indexes;
+    using Azure;
+    
+    var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new AzureKeyCredential(apiKey));
+    ```
+
+::: zone-end
+
+::: zone pivot="python"
+
+1. [Copy an Azure AI Search admin API key](search-security-api-keys.md#find-existing-keys) from the Azure portal.
+
+1. Use `AzureKeyCredential` to specify the API key in each request. Your code should look similar to the following example:
+
+```python
+    # Authenticate using keys
+    from azure.core.credentials import AzureKeyCredential
+    index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+    ```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+1. [Copy an Azure AI Search admin API key](search-security-api-keys.md#find-existing-keys) from the Azure portal.
+
+1. Specify the API key in each request. The key should look similar to the following example:
+
+```http
+   # List indexes using keys
+   GET {{search-url}}/indexes?api-version=2025-11-01-preview
+   Content-Type: application/json
+   api-key: {{search-api-key}}
+   ```
+
+::: zone-end
+
+---
+
+> [!IMPORTANT]
+> Code snippets in this article use API keys. If you use role-based authentication, update each request accordingly. In a request that specifies both approaches, the API key takes precedence.
+
+## Check for existing knowledge bases
+
+A knowledge base is a top-level, reusable object. Knowing about existing knowledge bases is helpful for either reuse or naming new objects. Any 2025-08-01-preview knowledge agents are returned in the knowledge bases collection.
+
+::: zone pivot="csharp"
+
+Run the following code to list existing knowledge bases by name.
+
+```csharp
+// List knowledge bases by name
+  using Azure.Search.Documents.Indexes;
+  
+  var indexClient = new SearchIndexClient(new Uri(searchEndpoint), credential);
+  var knowledgeBases = indexClient.GetKnowledgeBasesAsync();
+  
+  Console.WriteLine("Knowledge Bases:");
+  
+  await foreach (var kb in knowledgeBases)
+  {
+      Console.WriteLine($"  - {kb.Name}");
+  }
+```
+
+::: zone-end
+
+::: zone pivot="python"
+
+Run the following code to list existing knowledge bases by name.
+
+```python
+# List knowledge bases by name
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+
+for kb in index_client.list_knowledge_bases():
+    print(f"  - {kb.name}")
+```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+Use [Knowledge Bases - List (REST API)](/rest/api/searchservice/knowledge-bases/list?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to list knowledge bases by name and type.
+
+```http
+# List knowledge bases
+GET {{search-url}}/knowledgebases?api-version=2025-11-01-preview&$select=name
+Content-Type: application/json
+api-key: {{search-api-key}}
+```
+
+::: zone-end
+
+You can also return a single knowledge base by name to review its JSON definition.
+
+::: zone pivot="csharp"
+
+```csharp
+using Azure.Search.Documents.Indexes;
+using System.Text.Json;
+
+var indexClient = new SearchIndexClient(new Uri(searchEndpoint), credential);
+
+// Specify the knowledge base name to retrieve
+string kbNameToGet = "earth-knowledge-base";
+
+// Get a specific knowledge base definition
+var knowledgeBaseResponse = await indexClient.GetKnowledgeBaseAsync(kbNameToGet);
+var kb = knowledgeBaseResponse.Value;
+
+// Serialize to JSON for display
+string json = JsonSerializer.Serialize(kb, new JsonSerializerOptions { WriteIndented = true });
+Console.WriteLine(json);
+```
+
+::: zone-end
+
+::: zone pivot="python"
+
+```python
+# Get a knowledge base definition
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient
+import json
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+
+kb = index_client.get_knowledge_base("knowledge_base_name")
+print(json.dumps(kb.as_dict(), indent = 2))
+```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+```http
+# Get knowledge base
+GET {{search-url}}/knowledgebases/{{knowledge-base-name}}?api-version=2025-11-01-preview
+Content-Type: application/json
+api-key: {{search-api-key}}
+```
+
+::: zone-end
+
+The following JSON is an example response for a knowledge base.
+
+```json
+{
+  "name": "my-kb",
+  "description": "A sample knowledge base.",
+  "retrievalInstructions": null,
+  "answerInstructions": null,
+  "outputMode": null,
+  "knowledgeSources": [
+    {
+      "name": "my-blob-ks"
+    }
+  ],
+  "models": [],
+  "encryptionKey": null,
+  "retrievalReasoningEffort": {
+    "kind": "low"
+  }
+}
+```
+
+## Create a knowledge base
+
+A knowledge base drives the agentic retrieval pipeline. In application code, other agents or chatbots call it.
+
+A knowledge base connects knowledge sources (searchable content) to an LLM deployment from Azure OpenAI. Properties on the LLM establish the connection, while properties on the knowledge source establish defaults that inform query execution and the response.
+
+::: zone pivot="csharp"
+
+Run the following code to create a knowledge base.
+
+```csharp
+// Create a knowledge base
+using Azure.Search.Documents.Indexes;
+using Azure.Search.Documents.Indexes.Models;
+using Azure.Search.Documents.KnowledgeBases.Models;
+using Azure;
+
+var indexClient = new SearchIndexClient(new Uri(searchEndpoint), new AzureKeyCredential(apiKey));
+
+var aoaiParams = new AzureOpenAIVectorizerParameters
+{
+    ResourceUri = new Uri(aoaiEndpoint),
+    DeploymentName = aoaiGptDeployment,
+    ModelName = aoaiGptModel
+};
+
+var knowledgeBase = new KnowledgeBase(
+    name: "my-kb",
+    knowledgeSources: new KnowledgeSourceReference[] 
+    { 
+        new KnowledgeSourceReference("hotels-ks"),
+        new KnowledgeSourceReference("earth-at-night-ks")
+    }
+)
+{
+    Description = "This knowledge base handles questions directed at two unrelated sample indexes.",
+    RetrievalInstructions = "Use the hotels knowledge source for queries about where to stay, otherwise use the earth at night knowledge source.",
+    AnswerInstructions = "Provide a two sentence concise and informative answer based on the retrieved documents.",
+    OutputMode = KnowledgeRetrievalOutputMode.AnswerSynthesis,
+    Models = { new KnowledgeBaseAzureOpenAIModel(azureOpenAIParameters: aoaiParams) },
+    RetrievalReasoningEffort = new KnowledgeRetrievalLowReasoningEffort()
+};
+
+await indexClient.CreateOrUpdateKnowledgeBaseAsync(knowledgeBase);
+Console.WriteLine($"Knowledge base '{knowledgeBase.Name}' created or updated successfully.");
+```
+
+::: zone-end
+
+::: zone pivot="python"
+
+Run the following code to create a knowledge base.
+
+```python
+# Create a knowledge base
+from azure.core.credentials import AzureKeyCredential
+from azure.search.documents.indexes import SearchIndexClient
+from azure.search.documents.indexes.models import KnowledgeBase, KnowledgeBaseAzureOpenAIModel, KnowledgeSourceReference, AzureOpenAIVectorizerParameters, KnowledgeRetrievalOutputMode, KnowledgeRetrievalLowReasoningEffort
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+
+aoai_params = AzureOpenAIVectorizerParameters(
+    resource_url = "aoai_endpoint",
+    api_key="aoai_api_key",
+    deployment_name = "aoai_gpt_deployment",
+    model_name = "aoai_gpt_model",
+)
+
+knowledge_base = KnowledgeBase(
+    name = "my-kb",
+    description = "This knowledge base handles questions directed at two unrelated sample indexes.",
+    retrieval_instructions = "Use the hotels knowledge source for queries about where to stay, otherwise use the earth at night knowledge source.",
+    answer_instructions = "Provide a two sentence concise and informative answer based on the retrieved documents.",
+    output_mode = KnowledgeRetrievalOutputMode.ANSWER_SYNTHESIS,
+    knowledge_sources = [
+        KnowledgeSourceReference(name = "hotels-ks"),
+        KnowledgeSourceReference(name = "earth-at-night-ks"),
+    ],
+    models = [KnowledgeBaseAzureOpenAIModel(azure_open_ai_parameters = aoai_params)],
+    encryption_key = None,
+    retrieval_reasoning_effort = KnowledgeRetrievalLowReasoningEffort(),
+)
+
+index_client.create_or_update_knowledge_base(knowledge_base)
+print(f"Knowledge base '{knowledge_base.name}' created or updated successfully.")
+```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+Use [Knowledge Bases - Create or Update (REST API)](/rest/api/searchservice/knowledge-bases/create-or-update?view=rest-searchservice-2025-11-01-preview&preserve-view=true) to create a knowledge base.
+
+```http
+# Create a knowledge base
+PUT {{search-url}}/knowledgebases/{{knowledge-base-name}}?api-version=2025-11-01-preview
+Content-Type: application/json
+api-key: {{search-api-key}}
+
+{
+    "name" : "my-kb",
+    "description": "This knowledge base handles questions directed at two unrelated sample indexes.",
+    "retrievalInstructions": "Use the hotels knowledge source for queries about where to stay, otherwise use the earth at night knowledge source.",
+    "answerInstructions": null,
+    "outputMode": "answerSynthesis",
+    "knowledgeSources": [
+        {
+            "name": "hotels-ks"
+        },
+        {
+            "name": "earth-at-night-ks"
+        }
+    ],
+    "models" : [ 
+        {
+            "kind": "azureOpenAI",
+            "azureOpenAIParameters": {
+                "resourceUri": "{{model-provider-url}}",
+                "apiKey": "{{model-api-key}}",
+                "deploymentId": "gpt-4.1-mini",
+                "modelName": "gpt-4.1-mini"
+            }
+        }
+    ],
+    "encryptionKey": null,
+    "retrievalReasoningEffort": {
+        "kind": "low"
+    }
+}
+```
+
+::: zone-end
+
+### Knowledge base properties
+
+Pass the following properties to create a knowledge base.
+
+::: zone pivot="csharp"
+
+| Name | Description | Type | Required |
+|--|--|--|--|
+| `Name` | The name of the knowledge base. It must be unique within the knowledge bases collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | Yes |
+| `KnowledgeSources` | One or more [supported knowledge sources](agentic-knowledge-source-overview.md#supported-knowledge-sources). | Array | Yes |
+| `Description` | A description of the knowledge base. The LLM uses the description to inform query planning. | String | No |
+| `RetrievalInstructions` | A prompt for the LLM to determine whether a knowledge source should be in scope for a query. Include this prompt when you have multiple knowledge sources. This field influences both knowledge source selection and query formulation. For example, instructions could append information or prioritize a knowledge source. Instructions are passed directly to the LLM, which means it's possible to provide instructions that break query planning, such as instructions that result in bypassing an essential knowledge source. | String | No |
+| `AnswerInstructions` | Custom instructions to shape synthesized answers. The default is null. For more information, see [Use answer synthesis for citation-backed responses](agentic-retrieval-how-to-answer-synthesis.md). | String | No |
+| `OutputMode` | Valid values are `AnswerSynthesis` for an LLM-formulated answer or `ExtractedData` for full search results that you can pass to an LLM as a downstream step. | String | No |
+| `Models` | A connection to a [supported LLM](#supported-models) used for answer formulation or query planning. In this preview, `Models` can contain just one model, and the model provider must be Azure OpenAI. Obtain model information from the Foundry portal or a command-line request. Provide the parameters by using the [KnowledgeBaseAzureOpenAIModel class](/dotnet/api/azure.search.documents.indexes.models.knowledgebaseazureopenaimodel?view=azure-dotnet-preview&preserve-view=true). You can use role-based access control instead of API keys for the Azure AI Search connection to the model. | Object | No |
+| `RetrievalReasoningEffort` | Determines the level of LLM-related query processing. Valid values are `minimal`, `low` (default), and `medium`. For more information, see [Set the retrieval reasoning effort](agentic-retrieval-how-to-set-retrieval-reasoning-effort.md). | Object | No |
+
+::: zone-end
+
+::: zone pivot="python"
+
+| Name | Description | Type | Required |
+|--|--|--|--|
+| `name` | The name of the knowledge base. It must be unique within the knowledge bases collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | Yes |
+| `description` | A description of the knowledge base. The LLM uses the description to inform query planning. | String | No |
+| `retrieval_instructions` | A prompt for the LLM to determine whether a knowledge source should be in scope for a query. Include this prompt when you have multiple knowledge sources. This field influences both knowledge source selection and query formulation. For example, instructions could append information or prioritize a knowledge source. Pass instructions directly to the LLM. It's possible to provide instructions that break query planning, such as instructions that result in bypassing an essential knowledge source. | String | No |
+| `answer_instructions` | Custom instructions to shape synthesized answers. The default is null. For more information, see [Use answer synthesis for citation-backed responses](agentic-retrieval-how-to-answer-synthesis.md). | String | No |
+| `output_mode` | Valid values are `answer_synthesis` for an LLM-formulated answer or `extracted_data` for full search results that you can pass to an LLM as a downstream step. | String | No |
+| `knowledge_sources` | One or more [supported knowledge sources](agentic-knowledge-source-overview.md#supported-knowledge-sources). | Array | Yes |
+| `models` | A connection to a [supported LLM](#supported-models) used for answer formulation or query planning. In this preview, `models` can contain just one model, and the model provider must be Azure OpenAI. Obtain model information from the Foundry portal or a command-line request. You can use role-based access control instead of API keys for the Azure AI Search connection to the model. | Object | No |
+| `encryption_key` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge base and the generated objects. | Object | No |
+| `retrieval_reasoning_effort` | Determines the level of LLM-related query processing. Valid values are `minimal`, `low` (default), and `medium`. For more information, see [Set the retrieval reasoning effort](agentic-retrieval-how-to-set-retrieval-reasoning-effort.md). | Object | No |
+
+::: zone-end
+
+::: zone pivot="rest"
+
+| Name | Description | Type | Required |
+|--|--|--|--|
+| `name` | The name of the knowledge base. It must be unique within the knowledge bases collection and follow the [naming guidelines](/rest/api/searchservice/naming-rules) for objects in Azure AI Search. | String | Yes |
+| `description` | A description of the knowledge base. The LLM uses the description to inform query planning. | String | No |
+| `retrievalInstructions` | A prompt for the LLM to determine whether a knowledge source should be in scope for a query. Include this prompt when you have multiple knowledge sources. This field influences both knowledge source selection and query formulation. For example, instructions could append information or prioritize a knowledge source. You pass instructions directly to the LLM, which means it's possible to provide instructions that break query planning, such as instructions that result in bypassing an essential knowledge source. | String | No |
+| `answerInstructions` | Custom instructions to shape synthesized answers. The default is null. For more information, see [Use answer synthesis for citation-backed responses](agentic-retrieval-how-to-answer-synthesis.md). | String | No |
+| `outputMode` | Valid values are `answerSynthesis` for an LLM-formulated answer or `extractedData` for full search results that you can pass to an LLM as a downstream step. | String | No |
+| `knowledgeSources` | One or more [supported knowledge sources](agentic-knowledge-source-overview.md#supported-knowledge-sources). | Array | Yes |
+| `models` | A connection to a [supported LLM](#supported-models) used for answer formulation or query planning. In this preview, `models` can contain just one model, and the model provider must be Azure OpenAI. Obtain model information from the Foundry portal or a command-line request. You can use role-based access control instead of API keys for the Azure AI Search connection to the model. | Object | No |
+| `encryptionKey` | A [customer-managed key](search-security-manage-encryption-keys.md) to encrypt sensitive information in both the knowledge base and the generated objects. | Object | No |
+| `retrievalReasoningEffort.kind` | Determines the level of LLM-related query processing. Valid values are `minimal`, `low` (default), and `medium`. For more information, see [Set the retrieval reasoning effort](agentic-retrieval-how-to-set-retrieval-reasoning-effort.md). | Object | No |
+
+::: zone-end
+
+## Query a knowledge base
+
+After you create a knowledge base, use the [retrieve action](agentic-retrieval-how-to-retrieve.md) to query it and verify the LLM connection.
+
+## Delete a knowledge base
+
+If you no longer need the knowledge base or need to rebuild it on your search service, run the following code to delete the object.
+
+::: zone pivot="csharp"
+
+```csharp
+using Azure.Search.Documents.Indexes;
+var indexClient = new SearchIndexClient(new Uri(searchEndpoint), credential);
+
+await indexClient.DeleteKnowledgeBaseAsync(knowledgeBaseName);
+System.Console.WriteLine($"Knowledge base '{knowledgeBaseName}' deleted successfully.");
+```
+
+::: zone-end
+
+::: zone pivot="python"
+
+```python
+# Delete a knowledge base
+from azure.core.credentials import AzureKeyCredential 
+from azure.search.documents.indexes import SearchIndexClient
+
+index_client = SearchIndexClient(endpoint = "search_url", credential = AzureKeyCredential("api_key"))
+index_client.delete_knowledge_base("knowledge_base_name")
+print(f"Knowledge base deleted successfully.")
+```
+
+::: zone-end
+
+::: zone pivot="rest"
+
+```http
+# Delete a knowledge base
+DELETE {{search-url}}/knowledgebases/{{knowledge-base-name}}?api-version=2025-11-01-preview
+api-key: {{search-api-key}}
+```
+
 ::: zone-end
 
 ## Related content
 
 + [Agentic retrieval in Azure AI Search](agentic-retrieval-overview.md)
 + [Agentic RAG: Build a reasoning retrieval engine with Azure AI Search (YouTube video)](https://www.youtube.com/watch?v=PeTmOidqHM8)
-+ [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)
\ No newline at end of file
++ [Azure OpenAI demo featuring agentic retrieval](https://github.com/Azure-Samples/azure-search-openai-demo)