@@ -10,7 +10,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: concept-article
-ms.date: 10/06/2025
+ms.date: 10/23/2025
 ms.update-cycle: 365-days
 ---
 
@@ -22,7 +22,7 @@ A *skill* is an atomic operation that transforms content in some way. Often, it'
 
 Skills are organized into the following categories:
 
-* A *built-in skill* wraps API calls to an Azure AI resource, where the inputs, outputs, and processing steps are well understood. For skills that call an Azure AI resource, the connection is made over the internal network. For skills that call Azure OpenAI, you provide the connection information that the search service uses to connect to the resource. A small quantity of processing is nonbillable, but at larger volumes, processing is billable. Built-in skills are based on pretrained models from Microsoft, which means you can't train the model using your own training data.
+* A *built-in skill* wraps API calls to an Azure AI resource, where the inputs, outputs, and processing steps are well understood. For skills that call an Azure AI resource, the connection is made over the internal network. For skills that run AI workloads on your own Azure-hosted models or services, you provide the connection information that the search service uses to connect to the resource. A small quantity of processing is nonbillable, but at larger volumes, processing is billable. Built-in skills are based on pretrained models from Microsoft, which means you can't train the model using your own training data.
 
 * A *custom skill* provides custom code that executes externally to the search service. It's accessed through a URI. Custom code is often made available through an Azure function app. To attach an open-source or third-party vectorization model, use a custom skill.
 
@@ -47,9 +47,9 @@ Skills that call Azure AI are billed at the Standard rate when you [attach an Az
 | [Microsoft.Skills.Vision.VectorizeSkill](cognitive-search-skill-vision-vectorize.md) | Multimodal image and text vectorization. | Azure AI services ([pricing](https://azure.microsoft.com/pricing/details/cognitive-services/)) |
 | [Microsoft.Skills.Util.DocumentIntelligenceLayoutSkill](cognitive-search-skill-document-intelligence-layout.md) | Accelerate information extraction from documents. | Azure AI services ([pricing](https://azure.microsoft.com/pricing/details/cognitive-services/)) |
 
-## Azure OpenAI skills
+## "Bring your own capacity" skills
 
-Skills that call models deployed on Azure OpenAI are billed at the Standard rate.
+Skills that run AI workloads on your own Azure-hosted models or services are billed at the Standard rate.
 
 | OData type  | Description | Metered by |
 |-------|-------------|-------------|

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.custom:
   - build-2025
 ms.topic: reference
-ms.date: 09/18/2025
+ms.date: 10/23/2025
 ---
 
 # GenAI Prompt skill
@@ -35,7 +35,7 @@ The GenAI Prompt skill is available in the [latest preview REST API](/rest/api/s
 
 ## Supported models
 
-- You can use any [chat completion inference model](/azure/ai-foundry/model-inference/concepts/models) deployed in AI Foundry, such as GPT models, Deepseek R#, Llama-4-Mavericj, Cohere-command-r, and so forth.
+- You can use any [chat completion inference model](/azure/ai-foundry/model-inference/concepts/models) deployed in AI Foundry, such as GPT models, Deepseek R#, Llama-4-Mavericj, Cohere-command-r, and so forth. For GPT models specifically, only the chat completions API endpoints are supported. Endpoints using the Azure OpenAI Responses API (containing `/openai/responses` as part of the URI) are not currently compatible.
 
 - For image verbalization, the model you use to analyze the image determines what image formats are supported.
 

@@ -9,7 +9,7 @@ ms.update-cycle: 180-days
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 09/28/2025
+ms.date: 10/21/2025
 ---
 
 # Data sources gallery
@@ -141,7 +141,7 @@ Connect to a OneLake lakehouse to extract supported files content from a hierarc
 
 ## Logic app connectors
 
-Pull in content [using logic app workflows](search-how-to-index-logic-apps.md) and the following supported data sources.
+Pull in content [using logic app workflows](search-how-to-index-logic-apps.md) and the following supported data sources. Note that the Logic Apps artifacts mentioned below, they have a pre-built workflow, however, you can use [any connectors listed under Logic Apps](/connectors/connector-reference/connector-reference-logicapps-connectors) that pull data from sources and create your own indexing pipeline workflow that pushes data to [Azure AI Search via a Logic App connector](/azure/logic-apps/connectors/azure-ai#azure-ai-search).
 
 :::row:::
 :::column span="":::

@@ -9,14 +9,14 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 07/31/2025
+ms.date: 10/22/2025
 ms.update-cycle: 365-days
 #customer intent: I want to learn how to connect to Azure AI Search using API keys so that I can authenticate inbound requests to my search service.
 ---
 
 # Connect to Azure AI Search using keys
 
-Azure AI Search supports both identity-based and key-based authentication for connections to your search service. An API key is a unique string composed of 52 randomly generated numbers and letters. In your source code, you can specify it in a request header, or as an [environment variable](/azure/ai-services/cognitive-services-environment-variables) or as an app setting in your project, and then reference the variable on the request.
+Azure AI Search supports both identity-based and key-based authentication for connections to your search service. An API key is a unique string composed of 52 randomly generated numbers and letters. In your source code, you can specify it in a request header, or as an [environment variable](/azure/ai-services/cognitive-services-environment-variables) or app setting in your project, and then reference the variable on the request.
 
 > [!IMPORTANT]
 > When you create a search service, key-based authentication is the default, but it's not the most secure option. We recommend that you replace it with [role-based access](search-security-enable-roles.md).
@@ -45,18 +45,21 @@ Visually, there's no distinction between an admin key or query key. Both keys ar
 API keys are used for data plane (content) requests, such as creating or accessing an index or, any other request that's represented in the [Search REST APIs](/rest/api/searchservice/). 
 
 You can use either an API key or [Azure roles](search-security-rbac.md) for control plane (service) requests. When you use an API key:
-- Admin keys are used for creating, modifying, or deleting objects. Admin keys are also used to GET object definitions and system information.
+
+- Admin keys are used for creating, modifying, or deleting objects. Admin keys are also used to GET object definitions and system information, such as [LIST Indexes](/rest/api/searchservice/indexes/list) or [GET Service Statistics](/rest/api/searchservice/get-service-statistics/get-service-statistics).
+
 - Query keys are typically distributed to client applications that issue queries.
 
 ### [**REST API**](#tab/rest-use)
 
-**How API keys are used in REST calls**:
-
-Set an admin key in the request header. You can't pass admin keys on the URI or in the body of the request. Admin keys are used for create-read-update-delete operation and on requests issued to the search service itself, such as [LIST Indexes](/rest/api/searchservice/indexes/list) or [GET Service Statistics](/rest/api/searchservice/get-service-statistics/get-service-statistics).
+Set an admin key in the request header. You can't pass admin keys on the URI or in the body of the request.
 
 Here's an example of admin API key usage on a create index request:
 
 ```http
+@baseUrl=https://my-demo-search-service.search.windows.net
+@adminApiKey=aaaabbbb-0000-cccc-1111-dddd2222eeee
+
 ### Create an index
 POST {{baseUrl}}/indexes?api-version=2025-09-01  HTTP/1.1
   Content-Type: application/json
@@ -71,7 +74,7 @@ POST {{baseUrl}}/indexes?api-version=2025-09-01  HTTP/1.1
    }
 ```
 
-Set a query key in a request header for POST, or on the URI for GET. Query keys are used for operations that target the `index/docs` collection: [Search Documents](/rest/api/searchservice/documents/search-get), [Autocomplete](/rest/api/searchservice/documents/autocomplete-get), [Suggest](/rest/api/searchservice/documents/suggest-get), or [GET Document](/rest/api/searchservice/documents/get). 
+Set a query key in a request header for POST, or on the URI for GET. Query keys are used for operations that target the `index/docs` collection: [Search Documents](/rest/api/searchservice/documents/search-get), [Autocomplete](/rest/api/searchservice/documents/autocomplete-get), [Suggest](/rest/api/searchservice/documents/suggest-get), or [GET Document](/rest/api/searchservice/documents/get).
 
 Here's an example of query API key usage on a Search Documents (GET) request:
 
@@ -83,26 +86,69 @@ GET /indexes/my-new-index/docs?search=*&api-version=2025-09-01&api-key={{queryAp
 > [!NOTE]  
 > It's considered a poor security practice to pass sensitive data such as an `api-key` in the request URI. For this reason, Azure AI Search only accepts a query key as an `api-key` in the query string. As a general rule, we recommend passing your `api-key` as a request header.
 
-### [**PowerShell**](#tab/azure-ps-use)
+### [**Python**](#tab/python-use)
+
+It's a best practice to set the API key as an environment variable, but for simplicity, this example shows it as a string. The example uses a query API key for a query operation.
+
+```python
+# Import libraries
+from azure.core.credentials import AzureKeyCredential
+from azure.identity import DefaultAzureCredential, AzureAuthorityHosts
+
+# Variables for endpoint, keys, index
+search_endpoint: str = "https://<Put your search service NAME here>.search.windows.net/"
+credential = AzureKeyCredential("Your search service query key")
+index_name: str = "hotels-quickstart-python"
+
+# Set up the client
+search_client = SearchClient(endpoint=search_endpoint,
+                      index_name=index_name,
+                      credential=credential)
+
+# Run the query
+results =  search_client.search(query_type='simple',
+    search_text="*" ,
+    select='HotelName,Description,Tags',
+    include_total_count=True)
+
+print ('Total Documents Matching Query:', results.get_count())
+for result in results:
+    print(result["@search.score"])
+    print(result["HotelName"])
+    print(result["Tags"])
+    print(f"Description: {result['Description']}")
+```
 
-**How API keys are used in PowerShell**:
+### [**PowerShell**](#tab/azure-ps-use)
 
 Set API keys in the request header using the following syntax:
 
-```azurepowershell
+```powershell
 $headers = @{
 'api-key' = '<YOUR-ADMIN-OR-QUERY-API-KEY>'
 'Content-Type' = 'application/json' 
 'Accept' = 'application/json' }
 ```
 
-A script example showing API key usage for various operations can be found at [Quickstart: Create an Azure AI Search index in PowerShell using REST APIs](search-get-started-text.md).
+Use a variable to contain the fully qualified query:
+
+```powershell
+$url = '<YOUR-SEARCH-SERVICE>/indexes/hotels-quickstart/docs?api-version=2025-09-01&search=attached restaurant&searchFields=Description,Tags&$select=HotelId,HotelName,Tags,Description&$count=true'
+```
+
+Send the request to the search service:
+
+```powershell
+Invoke-RestMethod -Uri $url -Headers $headers | ConvertTo-Json
+```
+
+More script examples for other operations can be found at [Quickstart: Create an Azure AI Search index in PowerShell using REST APIs](search-get-started-text.md).
 
 ### [**Portal**](#tab/portal-use)
 
-**How API keys are used in the Azure portal**:
+Recall that key authentication is enabled by default and supports data plane operations such as indexing and queries. 
 
-Key authentication applies to data plane operations such as indexing and queries. It's enabled by default. However, if you [disable API keys](search-security-enable-roles.md#disable-api-key-authentication) and set up role assignments, the Azure portal uses role assignments instead.
+However, if you [disable API keys](search-security-enable-roles.md#disable-api-key-authentication) and set up role assignments, the Azure portal uses role assignments instead.
 
 ---