@@ -3,7 +3,7 @@ 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: 06/02/2026
+ms.date: 07/20/2026
 ai-usage: ai-assisted
 zone_pivot_groups: search-csharp-python-rest
 ---
@@ -87,13 +87,17 @@ A knowledge base specifies:
 
 Use one of the following LLMs from Azure OpenAI in Foundry Models. Azure OpenAI determines regional availability for the deployment you select. For deployment instructions, see [Deploy Microsoft Foundry Models in the Foundry portal](/azure/ai-foundry/how-to/deploy-models-openai).
 
+For the latest model lifecycle guidance, including deprecations, review [Model retirement and deprecation](/azure/ai-foundry/openai/concepts/model-retirements).
+
+GPT-4 family models are deprecated. For retirement dates and current status in Microsoft Foundry, see [Model retirement schedule - Microsoft Foundry](/azure/foundry/openai/concepts/model-retirement-schedule).
+
 | Model | Supported API versions |
 |--|--|
-| `gpt-4o` | 2025-11-01-preview, 2026-05-01-preview |
-| `gpt-4o-mini` | 2025-11-01-preview, 2026-05-01-preview |
-| `gpt-4.1` | 2025-11-01-preview, 2026-05-01-preview |
-| `gpt-4.1-mini` | 2025-11-01-preview, 2026-05-01-preview |
-| `gpt-4.1-nano` | 2025-11-01-preview, 2026-05-01-preview |
+| `gpt-4o` (deprecated) | 2025-11-01-preview, 2026-05-01-preview |
+| `gpt-4o-mini` (deprecated) | 2025-11-01-preview, 2026-05-01-preview |
+| `gpt-4.1` (deprecated) | 2025-11-01-preview, 2026-05-01-preview |
+| `gpt-4.1-mini` (deprecated) | 2025-11-01-preview, 2026-05-01-preview |
+| `gpt-4.1-nano` (deprecated) | 2025-11-01-preview, 2026-05-01-preview |
 | `gpt-5` | 2025-11-01-preview, 2026-05-01-preview |
 | `gpt-5-mini` | 2025-11-01-preview, 2026-05-01-preview |
 | `gpt-5-nano` | 2025-11-01-preview, 2026-05-01-preview |

@@ -1,7 +1,7 @@
 ---
 title: 'Tutorial: Build an Agentic Retrieval Solution'
 description: Build an agentic retrieval solution that connects Azure AI Search to Foundry Agent Service via MCP. Follow this tutorial to create a knowledge base and agent.
-ms.date: 06/02/2026
+ms.date: 07/20/2026
 ms.service: azure-ai-search
 ms.topic: tutorial
 ms.custom:
@@ -54,7 +54,9 @@ In this tutorial, you:
 
 + A text embedding model deployed to your project for [query-time vectorization](vector-search-integrated-vectorization.md#using-integrated-vectorization-in-queries). This solution uses `text-embedding-3-large`.
 
-+ An LLM deployed to your project for the agent. This solution uses `gpt-4.1-mini`.
++ An LLM deployed to your project for the agent. This solution uses `gpt-5-mini`.
+
+    GPT-4 family models are deprecated. For retirement dates and current status in Microsoft Foundry, see [Model retirement schedule - Microsoft Foundry](/azure/foundry/openai/concepts/model-retirement-schedule).
 
 + Permissions to access and manage Azure AI Search and Microsoft Foundry resources. For more information, see [Configure access](#configure-access).
 
@@ -131,7 +133,7 @@ To configure access for this solution:
    PROJECT_RESOURCE_ID = /subscriptions/{subscription-id}/resourceGroups/{resource-group-name}/providers/Microsoft.CognitiveServices/accounts/{account-name}/projects/{project-name}
    AZURE_OPENAI_ENDPOINT = https://{your-resource-name}.openai.azure.com
    AZURE_OPENAI_EMBEDDING_DEPLOYMENT = text-embedding-3-large
-   AGENT_MODEL = gpt-4.1-mini
+    AGENT_MODEL = gpt-5-mini
    ```
 
    You can find the endpoints and resource ID in the Azure portal:
@@ -185,7 +187,7 @@ load_dotenv(override=True) # Take environment variables from .env
 project_endpoint = os.environ["PROJECT_ENDPOINT"]
 project_resource_id = os.environ["PROJECT_RESOURCE_ID"]
 project_connection_name = os.getenv("PROJECT_CONNECTION_NAME", "earthknowledgeconnection")
-agent_model = os.getenv("AGENT_MODEL", "gpt-4.1-mini")
+agent_model = os.getenv("AGENT_MODEL", "gpt-5-mini")
 agent_name = os.getenv("AGENT_NAME", "earth-knowledge-agent")
 endpoint = os.environ["AZURE_SEARCH_ENDPOINT"]
 credential = DefaultAzureCredential()
@@ -614,7 +616,7 @@ To optimize performance and reduce latency, consider the following strategies:
 
 + Summarize message threads.
 
-+ Use `gpt-4.1-mini` or a smaller model that performs faster.
++ Use `gpt-5-mini` or a smaller model that performs faster.
 
 + Set `maxOutputSize` on the [retrieve action](agentic-retrieval-how-to-retrieve.md) to govern the size of the response or `maxRuntimeInSeconds` for time-bound processing.
 

@@ -7,7 +7,8 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2025
 ms.topic: quickstart
-ms.date: 02/23/2026
+ms.date: 07/20/2026
+ai-usage: ai-assisted
 ---
 
 # Quickstart: Agentic retrieval in the Azure portal
@@ -16,7 +17,7 @@ ms.date: 02/23/2026
 
 [!INCLUDE [GA announcement](./includes/previews/agentic-retrieval-ga-announcement.md)]
 
-In this quickstart, you use [agentic retrieval](agentic-retrieval-overview.md) in the Azure portal to create a conversational search experience powered by documents indexed in Azure AI Search and a large language model (LLM) from Azure OpenAI in Foundry Models.
+In this quickstart, use [agentic retrieval](agentic-retrieval-overview.md) in the Azure portal to create a conversational search experience powered by documents indexed in Azure AI Search and a large language model (LLM) from Azure OpenAI in Foundry Models.
 
 The portal guides you through the process of creating the following objects:
 
@@ -27,7 +28,7 @@ The portal guides you through the process of creating the following objects:
 Afterwards, you test the knowledge base by submitting a complex query that requires information from multiple documents and reviewing the synthesized answer.
 
 > [!IMPORTANT]
-> The portal now uses the 2026-05-01-preview REST APIs for knowledge sources and knowledge bases. If you previously created agentic retrieval objects in the portal, those objects might be subject to breaking changes. For migration guidance, see [Migrate agentic retrieval code to the latest version](agentic-retrieval-how-to-migrate.md).
+> Some agentic retrieval features are generally available in the 2026-04-01 REST API through programmatic access. The Azure portal continues to use 2026-05-01-preview for the full feature set. If you previously created agentic retrieval objects in the portal, those objects might be subject to breaking changes. For migration guidance, see [Migrate agentic retrieval code to the latest version](agentic-retrieval-how-to-migrate.md).
 
 ## Prerequisites
 
@@ -99,7 +100,7 @@ To prepare the sample data for this quickstart:
 
 A knowledge source is a reusable reference to your source data. In this section, you create a [blob knowledge source](agentic-knowledge-source-how-to-blob.md), which triggers the creation of a *data source*, *skillset*, *index*, and *indexer* to automate data indexing and enrichment. You review these objects in a later section.
 
-You also configure a *vectorizer*, which uses your deployed embedding model to convert text into vectors and match documents based on semantic similarity. The vectorizer, vector fields, and vectors will be added to the auto-generated index.
+You also configure a *vectorizer*, which uses your deployed embedding model to convert text into vectors and match documents based on semantic similarity. The vectorizer, vector fields, and vectors are added to the auto-generated index.
 
 To create the knowledge source for this quickstart:
 
@@ -157,7 +158,7 @@ To create the knowledge base for this quickstart:
 
 ## Test agentic retrieval
 
-The portal provides a chat playground where you can submit `retrieve` requests to the knowledge base, whose responses include references to your knowledge sources and debug information about the retrieval process.
+The portal provides a chat playground where you can submit `retrieve` requests to the knowledge base. The responses include references to your knowledge sources and debug information about the retrieval process.
 
 To query the knowledge base:
 

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/23/2026
+ms.date: 08/03/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---
@@ -45,13 +45,13 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
     git clone https://github.com/Azure-Samples/azure-search-dotnet-samples
     ```
 
-1. Navigate to the quickstart folder.
+1. Go to the quickstart folder.
 
     ```bash
     cd azure-search-dotnet-samples/quickstart-agentic-retrieval
     ```
 
-1. In `sample.env`, replace the placeholder values for `SEARCH_ENDPOINT` and `AOAI_ENDPOINT` with the URLs you obtained in [Get endpoints](#get-endpoints).
+1. In `sample.env`, replace the placeholder values for `SEARCH_ENDPOINT` and `AOAI_ENDPOINT` with the URLs you got in [Get endpoints](#get-endpoints).
 
 1. Rename `sample.env` to `.env`.
 
@@ -65,7 +65,7 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
     dotnet restore AgenticRetrievalQuickstart.csproj
     ```
 
-    When the restore completes, verify that no errors appear in the output.
+    When the restore finishes, make sure no errors appear in the output.
 
 1. For keyless authentication with Microsoft Entra ID, sign in to your Azure account. If you have multiple subscriptions, select the one that contains your Azure AI Search and Microsoft Foundry resources.
 
@@ -499,7 +499,7 @@ foreach (var reference in retrievalResult.Value.References)
 
 [!INCLUDE [clean up resources (paid)](../resource-cleanup-paid.md)]
 
-Otherwise, the following code from `program.cs` deleted the objects you created in this quickstart.
+Otherwise, the following code from `program.cs` deletes the objects you created in this quickstart.
 
 ### Delete the knowledge base
 

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/23/2026
+ms.date: 07/20/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---
@@ -49,13 +49,13 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
     git clone https://github.com/Azure-Samples/azure-search-java-samples
     ```
 
-1. Navigate to the quickstart folder.
+1. Go to the quickstart folder.
 
     ```bash
     cd azure-search-java-samples/quickstart-agentic-retrieval
     ```
 
-1. In `sample.env`, replace the placeholder values for `SEARCH_ENDPOINT` and `AOAI_ENDPOINT` with the URLs you obtained in [Get endpoints](#get-endpoints).
+1. In `sample.env`, replace the placeholder values for `SEARCH_ENDPOINT` and `AOAI_ENDPOINT` with the URLs you got in [Get endpoints](#get-endpoints).
 
 1. Rename `sample.env` to `.env`.
 
@@ -323,7 +323,7 @@ searchClient.uploadDocuments(documents);
 ```
 
 
-**Reference:** [SearchClient](/java/api/com.azure.search.documents.searchclient), SearchDocument
+**Reference:** [SearchClient](/java/api/com.azure.search.documents.searchclient), [SearchDocument](/java/api/com.azure.search.documents)
 
 ### Create a knowledge source
 
@@ -352,7 +352,7 @@ indexClient.createOrUpdateKnowledgeSource(indexKnowledgeSource);
 
 To target `earth-knowledge-source` and your `gpt-5-mini` deployment at query time, you need a knowledge base. The following code defines a knowledge base named `earth-knowledge-base`.
 
-`OutputMode` is set to `ANSWER_SYNTHESIS`, enabling natural-language answers that cite the retrieved documents and follow the provided `AnswerInstructions`.
+Set `OutputMode` to `ANSWER_SYNTHESIS` to enable natural-language answers that cite the retrieved documents and follow the provided `AnswerInstructions`.
 
 ```java
 AzureOpenAIVectorizerParameters openAiParameters =
@@ -545,7 +545,7 @@ printResult(responseText, retrievalResult);
 
 [!INCLUDE [clean up resources (paid)](../resource-cleanup-paid.md)]
 
-Otherwise, the following code from `AgenticRetrievalQuickstart.java` deleted the objects you created in this quickstart.
+Otherwise, the following code from `AgenticRetrievalQuickstart.java` deletes the objects you created in this quickstart.
 
 ### Delete the knowledge base
 

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 03/23/2026
+ms.date: 07/20/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---
@@ -49,13 +49,13 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
     git clone https://github.com/Azure-Samples/azure-search-javascript-samples
     ```
 
-1. Navigate to the quickstart folder.
+1. Go to the quickstart folder.
 
     ```bash
     cd azure-search-javascript-samples/quickstart-agentic-retrieval-js
     ```
 
-1. In `sample.env`, replace the placeholder values for `AZURE_SEARCH_ENDPOINT` and `AZURE_OPENAI_ENDPOINT` with the URLs you obtained in [Get endpoints](#get-endpoints).
+1. In `sample.env`, replace the placeholder values for `AZURE_SEARCH_ENDPOINT` and `AZURE_OPENAI_ENDPOINT` with the URLs you got in [Get endpoints](#get-endpoints).
 
 1. Rename `sample.env` to `.env`.
 
@@ -69,7 +69,7 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
     npm install
     ```
 
-   When the installation completes, you should see a `node_modules` folder in the project directory.
+   When the installation finishes, you see a `node_modules` folder in the project directory.
 
 1. For keyless authentication with Microsoft Entra ID, sign in to your Azure account. If you have multiple subscriptions, select the one that contains your Azure AI Search and Microsoft Foundry resources.
 
@@ -568,7 +568,7 @@ if (result2.references) {
 
 [!INCLUDE [clean up resources (paid)](../resource-cleanup-paid.md)]
 
-Otherwise, the following code from `index.js` deleted the objects you created in this quickstart.
+Otherwise, the following code from `index.js` deletes the objects you created in this quickstart.
 
 ```javascript
 await searchIndexClient.deleteKnowledgeBase('earth-knowledge-base');

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/23/2026
+ms.date: 07/20/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---
@@ -51,14 +51,14 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
     git clone https://github.com/Azure-Samples/azure-search-python-samples
     ```
 
-1. Navigate to the quickstart folder and open it in Visual Studio Code.
+1. Go to the quickstart folder and open it in Visual Studio Code.
 
     ```bash
     cd azure-search-python-samples/Quickstart-Agentic-Retrieval
     code .
     ```
 
-1. In `sample.env`, replace the placeholder values for `SEARCH_ENDPOINT` and `AOAI_ENDPOINT` with the URLs you obtained in [Get endpoints](#get-endpoints).
+1. In `sample.env`, replace the placeholder values for `SEARCH_ENDPOINT` and `AOAI_ENDPOINT` with the URLs you got in [Get endpoints](#get-endpoints).
 
 1. Rename `sample.env` to `.env`.
 
@@ -86,7 +86,7 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
 
 ### Output
 
-Each code cell prints its output to the notebook. The following example is the output after running all cells:
+Each code cell prints its output to the notebook. The following example shows the output after running all cells:
 
 ```
 Documents uploaded to index 'earth-at-night' successfully.
@@ -502,7 +502,7 @@ print("references_content:\n", references_content)
 
 [!INCLUDE [clean up resources (paid)](../resource-cleanup-paid.md)]
 
-Otherwise, the following code from `quickstart-agentic-retrieval.ipynb` deleted the objects you created in this quickstart.
+Otherwise, the following code from `quickstart-agentic-retrieval.ipynb` deletes the objects you created in this quickstart.
 
 ### Delete the knowledge base
 

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/23/2026
+ms.date: 07/20/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---
@@ -45,14 +45,14 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
     git clone https://github.com/Azure-Samples/azure-search-rest-samples
     ```
 
-1. Navigate to the quickstart folder and open it in Visual Studio Code.
+1. Go to the quickstart folder and open it in Visual Studio Code.
 
     ```bash
     cd azure-search-rest-samples/Quickstart-agentic-retrieval
     code .
     ```
 
-1. In `agentic-retrieval.rest`, replace the placeholder values for `@search-url` and `@aoai-url` with the URLs you obtained in [Get endpoints](#get-endpoints).
+1. In `agentic-retrieval.rest`, replace the placeholder values for `@search-url` and `@aoai-url` with the URLs you got in [Get endpoints](#get-endpoints).
 
 1. For keyless authentication with Microsoft Entra ID, sign in to your Azure account. If you have multiple subscriptions, select the one that contains your Azure AI Search and Microsoft Foundry resources.
 
@@ -72,7 +72,7 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
 
 Send each request sequentially, starting with `### Create an index`.
 
-Each request should return a `200 OK`, `201 Created`, or `204 No Content` status code. If you receive an error, check the request for typos and ensure that your token is valid.
+Each request should return a `200 OK`, `201 Created`, or `204 No Content` status code. If you get an error, check the request for typos and make sure your token is valid.
 
 ### Output
 
@@ -371,7 +371,7 @@ You're ready to run agentic retrieval. The following code sends a two-part user
 1. Analyzes the entire conversation to infer the user's information need.
 1. Decomposes the compound query into focused subqueries.
 1. Runs the subqueries concurrently against your knowledge source.
-1. Uses semantic ranker to rerank and filter the results. Our example excludes responses with a reranker score of `2.5` or lower.
+1. Uses semantic ranker to rerank and filter the results. This example excludes responses with a reranker score of `2.5` or lower.
 1. Synthesizes the top results into a natural-language answer.
 
 ```HTTP
@@ -409,7 +409,7 @@ Authorization: Bearer {{token}}
 
 **Reference:** [Knowledge Retrieval - Retrieve](/rest/api/searchservice/knowledge-retrieval/retrieve?view=rest-searchservice-2026-05-01-preview&preserve-view=true)
 
-The output should contain the following components:
+The output contains the following components:
 
 + `response` provides a synthesized, LLM-generated answer to the query that cites the retrieved documents. When answer synthesis isn't enabled, this section contains content extracted directly from the documents.
 
@@ -421,7 +421,7 @@ The output should contain the following components:
 
 [!INCLUDE [clean up resources (paid)](../resource-cleanup-paid.md)]
 
-Otherwise, the following requests from `agentic-retrieval.rest` deleted the objects you created in this quickstart.
+Otherwise, the following requests from `agentic-retrieval.rest` delete the objects you created in this quickstart.
 
 ### Delete the knowledge base
 

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 03/23/2026
+ms.date: 07/20/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---
@@ -51,13 +51,13 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
     git clone https://github.com/Azure-Samples/azure-search-javascript-samples
     ```
 
-1. Navigate to the quickstart folder.
+1. Go to the quickstart folder.
 
     ```bash
     cd azure-search-javascript-samples/quickstart-agentic-retrieval-ts
     ```
 
-1. In `sample.env`, replace the placeholder values for `AZURE_SEARCH_ENDPOINT` and `AZURE_OPENAI_ENDPOINT` with the URLs you obtained in [Get endpoints](#get-endpoints).
+1. In `sample.env`, replace the placeholder values for `AZURE_SEARCH_ENDPOINT` and `AZURE_OPENAI_ENDPOINT` with the URLs you got in [Get endpoints](#get-endpoints).
 
 1. Rename `sample.env` to `.env`.
 
@@ -71,7 +71,7 @@ Although you can use your own data, this quickstart uses [sample JSON documents]
     npm install
     ```
 
-   When the installation completes, you should see a `node_modules` folder in the project directory.
+   When the installation finishes, you see a `node_modules` folder in the project directory.
 
 1. Compile the TypeScript files to JavaScript.
 
@@ -94,7 +94,7 @@ npm start
 ```
 
 > [!NOTE]
-> This command runs the compiled `.js` files from the `dist` folder. TypeScript code must be transpiled to JavaScript before Node.js can execute it, which is why you previously ran `npm run build`.
+> This command runs the compiled `.js` files from the `dist` folder. Node.js requires TypeScript code to be transpiled to JavaScript before it can execute, which is why you previously ran `npm run build`.
 
 ### Output
 
@@ -581,7 +581,7 @@ console.log("\n✅ Quickstart completed successfully!");
 
 [!INCLUDE [clean up resources (paid)](../resource-cleanup-paid.md)]
 
-Otherwise, the following code from `index.ts` deleted the objects you created in this quickstart.
+Otherwise, the following code from `index.ts` deletes the objects you created in this quickstart.
 
 ```typescript
 await searchIndexClient.deleteKnowledgeBase('earth-knowledge-base');

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/02/2026
+ms.date: 07/20/2026
 ---
 
 In this quickstart, you use the [Azure AI Search client library for .NET](/dotnet/api/overview/azure/search) to create, load, and query a search index for [full-text search](../../search-lucene-query-architecture.md), also known as keyword search.
@@ -183,11 +183,11 @@ You create two helper classes, `Hotel.cs` and `Address.cs`, to define the struct
 
 In the Azure.Search.Documents client library, you can use [SearchableField](/dotnet/api/azure.search.documents.indexes.models.searchablefield) and [SimpleField](/dotnet/api/azure.search.documents.indexes.models.simplefield) to streamline field definitions. Both are helper classes that generate a [SearchField](/dotnet/api/azure.search.documents.indexes.models.searchfield) and can potentially simplify your code:
 
-+ `SimpleField` can be any data type, is always nonsearchable (ignored for full-text search queries), and is retrievable (not hidden). Other attributes are off by default, but can be enabled. You might use a `SimpleField` for document IDs or fields used only in filters, facets, or scoring profiles. If so, apply any attributes that are necessary for the scenario, such as `IsKey = true` for a document ID.
+- `SimpleField` can be any data type, is always nonsearchable (ignored for full-text search queries), and is retrievable (not hidden). Other attributes are off by default, but can be enabled. You might use a `SimpleField` for document IDs or fields used only in filters, facets, or scoring profiles. If so, apply any attributes that are necessary for the scenario, such as `IsKey = true` for a document ID.
 
-+ `SearchableField` must be a string, and is always searchable and retrievable. Other attributes are off by default, but can be enabled. Because this field type is searchable, it supports synonyms and the full complement of analyzer properties.
+- `SearchableField` must be a string, and is always searchable and retrievable. Other attributes are off by default, but can be enabled. Because this field type is searchable, it supports synonyms and the full complement of analyzer properties.
 
-Whether you use the basic `SearchField` API or either one of the helper models, you must explicitly enable filter, facet, and sort attributes. For example, [IsFilterable](/dotnet/api/azure.search.documents.indexes.models.searchfield.isfilterable), [IsSortable](/dotnet/api/azure.search.documents.indexes.models.searchfield.issortable), and [IsFacetable](/dotnet/api/azure.search.documents.indexes.models.searchfield.isfacetable) must be explicitly attributed, as shown in the previous sample.
+Whether you use the basic `SearchField` API or either one of the helper models, you must explicitly enable filter, facet, and sort attributes. For example, [IsFilterable](/dotnet/api/azure.search.documents.indexes.models.searchfield.isfilterable), [IsSortable](/dotnet/api/azure.search.documents.indexes.models.searchfield.issortable), and [IsFacetable](/dotnet/api/azure.search.documents.indexes.models.searchfield.isfacetable) must be explicitly set, as shown in the previous sample.
 
 #### Create the search index
 

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/02/2026
+ms.date: 07/20/2026
 ---
 
 In this quickstart, you use the [Azure AI Search client library for Java](/java/api/overview/azure/search-documents-readme) to create, load, and query a search index for [full-text search](../../search-lucene-query-architecture.md), also known as keyword search.
@@ -162,12 +162,12 @@ This example uses synchronous methods of the [SearchIndexClient](/java/api/com.a
 
 You create two helper classes, `Hotel.java` and `Address.java`, to define the structure of a hotel document and its address. The `Hotel` class includes fields for a hotel ID, name, description, category, tags, parking, renovation date, rating, and address. The `Address` class includes fields for street address, city, state/province, postal code, and country/region.
 
-In the azure-search-documents client library, you can use `SearchableField` and `SimpleField` to streamline field definitions. Both are annotations that you can apply to fields or methods to generate a [SearchField](/java/api/com.azure.search.documents.indexes.models.searchfield):
+In the azure-search-documents client library, you can use [SearchableField](/java/api/com.azure.search.documents.indexes) and [SimpleField](/java/api/com.azure.search.documents.indexes) to streamline field definitions. Both are annotations that you can apply to fields or methods to generate a [SearchField](/java/api/com.azure.search.documents.indexes.models.searchfield):
 
-+ `SimpleField` can be any data type, is always nonsearchable (ignored for full-text search queries), and is retrievable (not hidden). Other attributes are off by default, but can be enabled. You might use a `SimpleField` for document IDs or fields used only in filters, facets, or scoring profiles. If so, apply any attributes that are necessary for the scenario, such as `isKey = true` for a document ID.
-+ `SearchableField` must be a string, and is always searchable and retrievable. Other attributes are off by default, but can be enabled. Because this field type is searchable, it supports synonyms and the full complement of analyzer properties.
+- `SimpleField` can be any data type, is always nonsearchable (ignored for full-text search queries), and is retrievable (not hidden). Other attributes are off by default, but can be enabled. You might use a `SimpleField` for document IDs or fields used only in filters, facets, or scoring profiles. If so, apply any attributes that are necessary for the scenario, such as `isKey = true` for a document ID.
+- `SearchableField` must be a string, and is always searchable and retrievable. Other attributes are off by default, but can be enabled. Because this field type is searchable, it supports synonyms and the full complement of analyzer properties.
 
-Whether you use the basic `SearchField` API or either one of the helper models, you must explicitly enable filter, facet, and sort attributes. For example, [isFilterable](/java/api/com.azure.search.documents.indexes.models.searchfield), [isSortable](/java/api/com.azure.search.documents.indexes.models.searchfield), and [isFacetable](/java/api/com.azure.search.documents.indexes.models.searchfield) must be explicitly attributed, as shown in the previous sample.
+Whether you use the basic `SearchField` API or either one of the helper models, you must explicitly enable filter, facet, and sort attributes. For example, [isFilterable](/java/api/com.azure.search.documents.indexes.models.searchfield), [isSortable](/java/api/com.azure.search.documents.indexes.models.searchfield), and [isFacetable](/java/api/com.azure.search.documents.indexes.models.searchfield) must be explicitly set, as shown in the previous sample.
 
 #### Create the search index
 
@@ -186,7 +186,7 @@ Azure AI Search searches over content stored in the service. In this step, you l
 
 In Azure AI Search, search documents are data structures that are both inputs to indexing and outputs from queries. As obtained from an external data source, document inputs might be rows in a database, blobs in Azure Blob Storage, or JSON documents on disk. In this example, you take a shortcut and embed JSON documents for four hotels directly.
 
-When uploading documents, you must use an `IndexDocumentsBatch` object. An `IndexDocumentsBatch` object contains a collection of [IndexActions](/java/api/com.azure.search.documents.models.indexaction), each of which contains a document and a property that tells Azure AI Search what action to perform ([upload, merge, delete, and mergeOrUpload](/azure/search/search-what-is-data-import#indexing-actions)).
+When uploading documents, you must use an [IndexDocumentsBatch](/java/api/com.azure.search.documents.indexes.models) object. An `IndexDocumentsBatch` object contains a collection of [IndexActions](/java/api/com.azure.search.documents.models.indexaction), each of which contains a document and a property telling Azure AI Search what action to perform ([upload, merge, delete, and mergeOrUpload](/azure/search/search-what-is-data-import#indexing-actions)).
 
 In `App.java`, you create an array of documents and index actions, and then pass the array to `IndexDocumentsBatch`. The following documents conform to the hotels-quickstart index, as defined by the hotel class.
 
@@ -230,7 +230,7 @@ private static void uploadDocuments(SearchClient searchClient)
 }
 ```
 
-The `uploadDocuments` method creates an `IndexDocumentsBatch` and calls [indexDocuments](/java/api/com.azure.search.documents.searchclient) on a [SearchClient](/java/api/com.azure.search.documents.searchclient) to upload the documents. This quickstart creates `SearchClient` independently by using [SearchClientBuilder](/java/api/com.azure.search.documents.searchclientbuilder), which requires configuring the endpoint and credentials separately.
+The `uploadDocuments` method creates an [IndexDocumentsBatch](/java/api/com.azure.search.documents.indexes.models) and calls [indexDocuments](/java/api/com.azure.search.documents.searchclient) on a [SearchClient](/java/api/com.azure.search.documents.searchclient) to upload the documents. This quickstart creates `SearchClient` independently using [SearchClientBuilder](/java/api/com.azure.search.documents.searchclientbuilder), which requires configuring the endpoint and credentials separately.
 
 ```java
 uploadDocuments(searchClient);
@@ -258,7 +258,7 @@ You can get query results as soon as the first document is indexed, but actual t
 
 This section adds two pieces of functionality: query logic and results. For queries, use the [search](/java/api/com.azure.search.documents.searchclient) method. This method takes search text (the query string) and other [options](/java/api/com.azure.search.documents.models.searchoptions).
 
-The `SearchPagedIterable` class represents the results.
+The [SearchPagedIterable](/java/api/com.azure.search.documents.models.searchpagediterable) class represents the results.
 
 In `App.java`, the `WriteDocuments` method prints search results to the console.
 

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/02/2026
+ms.date: 07/20/2026
 ---
 
 In this quickstart, you use the [Azure AI Search client library for JavaScript](/javascript/api/overview/azure/search-documents-readme) to create, load, and query a search index for [full-text search](../../search-lucene-query-architecture.md), also known as keyword search.
@@ -80,7 +80,7 @@ node index.js
 The output should be similar to the following:
 
 ```
-Running Azure AI Search Javascript quickstart...
+Running Azure AI Search JavaScript quickstart...
 Checking if index exists...
 Deleting index...
 Creating index...

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/02/2026
+ms.date: 07/20/2026
 ---
 
 In this quickstart, you use PowerShell and the [Azure AI Search REST APIs](/rest/api/searchservice/) to create, load, and query a search index for [full-text search](../../search-lucene-query-architecture.md), also known as keyword search.
@@ -126,11 +126,11 @@ Within the index schema, the `fields` collection defines the structure of hotel
 
 Key points about the index schema:
 
-+ Use string fields (`Edm.String`) to make numeric data full-text searchable. Other [supported data types](/rest/api/searchservice/supported-data-types), such as `Edm.Int32`, are filterable, sortable, facetable, and retrievable but aren't searchable.
+- Use string fields (`Edm.String`) to make numeric data full-text searchable. Other [supported data types](/rest/api/searchservice/supported-data-types), such as `Edm.Int32`, are filterable, sortable, facetable, and retrievable but aren't searchable.
 
-+ Most of the fields are simple data types, but you can define complex types to represent nested data, such as the `Address` field.
+- Most of the fields are simple data types, but you can define complex types to represent nested data, such as the `Address` field.
 
-+ Field attributes determine allowed actions. The REST APIs allow [many actions by default](/rest/api/searchservice/indexes/create#request-body). For example, all strings are searchable and retrievable. With the REST APIs, you might only use attributes if you need to disable a behavior.
+- Field attributes determine allowed actions. The REST APIs allow [many actions by default](/rest/api/searchservice/indexes/create#request-body). For example, all strings are searchable and retrievable. With the REST APIs, you might only use attributes if you need to disable a behavior.
 
 ### Upload documents to the index
 
@@ -202,7 +202,7 @@ $body = @"
 Send-RequestWithBody POST "$baseUrl/indexes/hotels-quickstart/docs/search?api-version=2026-04-01" $headers $body
 ```
 
-The `search` parameter is set to `*`, which matches all documents. The `filter` parameter applies a Boolean condition to narrow the results.
+The `search` parameter is set to `*`, which matches all documents. The `filter` parameter applies a boolean condition to narrow the results.
 
 #### Query example 3
 

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/02/2026
+ms.date: 07/20/2026
 ---
 
 In this quickstart, you use the [Azure AI Search client library for Python](/python/api/overview/azure/search-documents-readme) to create, load, and query a search index for [full-text search](../../search-lucene-query-architecture.md), also known as keyword search.

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/02/2026
+ms.date: 07/20/2026
 ---
 
 In this quickstart, you use the [Azure AI Search REST APIs](/rest/api/searchservice) to create, load, and query a search index for [full-text search](../../search-lucene-query-architecture.md), also known as keyword search.
@@ -72,7 +72,7 @@ Full-text search uses Apache Lucene for indexing and queries and the BM25 rankin
 
 ### Output
 
-Each request returns different JSON based on the operation.  The key output is from `### Run a query`, which should look similar to the following:
+Each request returns different JSON based on the operation. The key output is from `### Run a query`, which should look similar to the following:
 
 ```json
 {
@@ -142,11 +142,11 @@ Authorization: Bearer {{token}}
 
 Key points about the index schema:
 
-+ Use string fields (`Edm.String`) to make numeric data full-text searchable. Other [supported data types](/rest/api/searchservice/supported-data-types), such as `Edm.Int32`, are filterable, sortable, facetable, and retrievable but aren't searchable.
+- Use string fields (`Edm.String`) to make numeric data full-text searchable. Other [supported data types](/rest/api/searchservice/supported-data-types), such as `Edm.Int32`, are filterable, sortable, facetable, and retrievable but aren't searchable.
 
-+ Most of the fields are simple data types, but you can define complex types to represent nested data, such as the `Address` field.
+- Most of the fields are simple data types, but you can define complex types to represent nested data, such as the `Address` field.
 
-+ Field attributes determine allowed actions. The REST APIs allow [many actions by default](/rest/api/searchservice/indexes/create#request-body). For example, all strings are searchable and retrievable. With the REST APIs, you might only use attributes if you need to disable a behavior.
+- Field attributes determine allowed actions. The REST APIs allow [many actions by default](/rest/api/searchservice/indexes/create#request-body). For example, all strings are searchable and retrievable. With the REST APIs, you might only use attributes if you need to disable a behavior.
 
 ### Upload documents to the index
 

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/02/2026
+ms.date: 07/20/2026
 ---
 
 In this quickstart, you use the [Azure AI Search client library for JavaScript](/javascript/api/overview/azure/search-documents-readme) (compatible with TypeScript) to create, load, and query a search index for [full-text search](../../search-lucene-query-architecture.md), also known as keyword search.

@@ -2,7 +2,7 @@
 ms.reviewer: rotabor
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 04/24/2026
+ms.date: 07/21/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---

@@ -2,7 +2,7 @@
 ms.reviewer: diberry
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 04/24/2026
+ms.date: 07/21/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---

@@ -2,7 +2,7 @@
 ms.reviewer: rotabor
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 04/24/2026
+ms.date: 07/21/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---

@@ -1,7 +1,7 @@
 ---
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 04/24/2026
+ms.date: 07/21/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---

@@ -2,7 +2,7 @@
 ms.reviewer: diberry
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 04/24/2026
+ms.date: 07/21/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 ---

@@ -3,7 +3,7 @@ title: Include File
 description: Include file for cleaning up Azure AI Search resources on the free tier.
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 02/02/2026
+ms.date: 07/20/2026
 # Use this file for quickstarts that only use a free search service.
 ---
 

@@ -3,7 +3,7 @@ title: Include File
 description: Include file for the Foundry IQ banner displayed across Azure AI Search documentation.
 ms.service: azure-ai-search
 ms.topic: include
-ms.date: 06/05/2026
+ms.date: 07/20/2026
 ai-usage: ai-assisted
 ---
 

@@ -1,12 +1,13 @@
 ---
-title: Create a Search Service in the Azure Portal
-description: Learn how to set up an Azure AI Search service in the Azure portal. Choose a resource group, region, and pricing tier.
+title: Create a search service in the Azure portal
+description: Learn how to set up an Azure AI Search service in the Azure portal, including resource group, region, and pricing tier selection.
 author: mattwojo
 ms.author: mattwoj
 ms.service: azure-ai-search
 ms.update-cycle: 180-days
 ms.topic: how-to
-ms.date: 06/10/2026
+ms.date: 07/20/2026
+ai-usage: ai-assisted
 ms.custom:
   - references_regions
   - build-2024
@@ -42,14 +43,14 @@ Some properties are fixed for the lifetime of the search service. Before you cre
 | -- | -- |
 | [Name](#name-your-service) | Becomes part of the URL endpoint. The name must be unique and follow naming rules. |
 | [Region](search-region-support.md) | Determines data residency and availability of certain features. For example, semantic ranker and Azure AI integration have region requirements. Choose a region that supports the features you need. |
-| [Tier](search-sku-tier.md) | Determines infrastructure, service limits, and billing. Some features aren't available on lower or specialized tiers. After you create your service, you will need to [Choose a pricing model and service tier](search-sku-tier.md). |
+| [Tier](search-sku-tier.md) | Determines infrastructure, service limits, and billing. Some features aren't available on lower or specialized tiers. After you create your service, you need to [Choose a pricing model and service tier](search-sku-tier.md). |
 | [Compute type](search-security-best-practices.md#optional-enable-confidential-computing) | Determines virtualization and security model. You can choose between standard VMs (recommended) and confidential VMs, which are intended for select workloads requiring data-in-use privacy and isolation. |
 
 ## Subscribe to Azure
 
 Azure AI Search requires a free or Standard Azure subscription.
 
-To try Azure AI Search for free, [start a trial subscription](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn) and then [create your search service on the Free tier](#choose-a-tier). Each Azure subscription can have one free search service, which is intended for short-term, non-production evaluation of the product. You can complete all of our quickstarts and most of our tutorials on the Free tier. For more information, see [Try Azure AI Search for free](search-try-for-free.md).
+To try Azure AI Search for free, [start a trial subscription](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn) and then [create your search service on the Free tier](#choose-a-tier). Each Azure subscription can have one free search service, which is intended for short-term, non-production evaluation of the product. You can complete all of the quickstarts and most of the tutorials on the Free tier. For more information, see [Try Azure AI Search for free](search-try-for-free.md).
 
 > [!IMPORTANT]
 > To make room for other services, Microsoft might delete free services that are inactive for an extended period of time.
@@ -100,7 +101,7 @@ When naming your service, follow these rules:
 ## Choose a region
 
 > [!IMPORTANT]
-> Due to high demand, Azure AI Search is currently unavailable for new instances in some regions.
+> Region and tier availability can change over time. Check [Azure AI Search regional availability](search-region-support.md) during service creation.
 
 If you use multiple Azure services, putting all of them in the same region minimizes or voids bandwidth charges. There are no charges for data egress among same-region services.
 
@@ -143,7 +144,7 @@ The Basic and Standard tiers are the most common for production workloads, but m
 :::image type="content" source="media/search-create-service-portal/select-pricing-tier.png" lightbox="media/search-create-service-portal/select-pricing-tier.png" alt-text="Screenshot of the Select Pricing Tier page in the Azure portal." border="true":::
 
 > [!NOTE]
-> Services created after April 3, 2024 have larger partitions and higher vector quotas at every billable tier.
+> Newer services have larger partitions and higher vector quotas at every billable tier. For current details, see [Service limits in Azure AI Search](search-limits-quotas-capacity.md).
 
 ## Choose a compute type
 
@@ -167,26 +168,26 @@ Your service is deployed within minutes, and you can monitor its progress with A
 
 ## Configure authentication
 
-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.
+When you create a search service, key-based authentication is the default, but it's not the most secure option. Replace it with role-based access.
 
 To enable role-based access for your service:
 
 1. Go to your search service in the [Azure portal](https://portal.azure.com).
 
-1. From the left pane, select **Settings** > **Keys**. You can connect to your service using [API keys](search-security-api-keys.md), [Azure roles](search-security-rbac.md), or both. Select **Both** until you assign roles, after which you can select **Role-based access control**.
+1. From the left pane, select **Settings** > **Keys**. You can connect to your service by using [API keys](search-security-api-keys.md), [Azure roles](search-security-rbac.md), or both. Select **Both** until you assign roles, after which you can select **Role-based access control**.
 
    :::image type="content" source="media/search-create-service-portal/authentication-options.png" lightbox="media/search-create-service-portal/authentication-options.png" alt-text="Screenshot of the Keys tab with authentication options." border="true":::
 
 ## Scale your service
 
-After deploying your search service, you can [scale it to meet your needs](search-limits-quotas-capacity.md). Azure AI Search offers two scaling dimensions: *replicas* and *partitions*. Replicas allow your service to handle a higher load of search queries, while partitions allow your service to store and search through more documents.
+After deploying your search service, you can [scale it to meet your needs](search-limits-quotas-capacity.md). Azure AI Search offers two scaling dimensions: *replicas* and *partitions*. Replicas increase your service's capacity to handle more search query traffic. Partitions increase your service's capacity to store and search through more documents.
 
-Scaling is available only on billable tiers. On the Free tier, you can't scale your service or configure replicas and partitions.
+You can scale your service only on billable tiers. On the Free tier, you can't scale your service or configure replicas and partitions.
 
 > [!IMPORTANT]
 > Your service must have [two replicas for read-only SLA and three replicas for read/write SLA](https://azure.microsoft.com/support/legal/sla/search/v1_0/).
 
-Adding resources will increase your monthly bill. Use the [pricing calculator](https://azure.microsoft.com/pricing/calculator/) to understand the billing implications. You can adjust resources based on load, such as increasing resources for initial indexing and decreasing them later for incremental indexing.
+Adding resources increases your monthly bill. Use the [pricing calculator](https://azure.microsoft.com/pricing/calculator/) to understand the billing implications. You can adjust resources based on load, such as increasing resources for initial indexing and decreasing them later for incremental indexing.
 
 To scale your service:
 
@@ -231,21 +232,21 @@ To request more subscription quota:
 
    :::image type="content" source="media/search-create-service-portal/quota-overview-page.png" lightbox="media/search-create-service-portal/quota-overview-page.png" alt-text="Screenshot of the Search tile on the Overview page.":::
 
-1. Set filters to review the existing quota for search services in your current subscription. We recommend filtering by usage.
+1. Set filters to review the existing quota for search services in your current subscription. Filter by usage.
 
     :::image type="content" source="media/search-create-service-portal/usage-filter.png" lightbox="media/search-create-service-portal/usage-filter.png" alt-text="Screenshot of the Usage filter for search services in your current subscription.":::
 
 1. Next to the tier and region that need more quotas, select **Request adjustment** <img src=media/search-create-service-portal/request-adjustment-icon.png alt="Screenshot of the Request Adjustment icon, which is the outline of a pencil." width="14">.
 
-1. In **New Quota Request**, enter a new limit for your subscription quota. The new limit must be greater than your current limit. If regional capacity is constrained, your request won't be automatically approved, and an incident report will be generated on your behalf for investigation and resolution.
+1. In **New Quota Request**, enter a new limit for your subscription quota. The new limit must be greater than your current limit. If regional capacity is constrained, your request isn't automatically approved, and an incident report is generated on your behalf for investigation and resolution.
 
 1. Submit your request.
 
 1. Monitor notifications in the Azure portal for updates on the new limit. Most requests are approved within 24 hours.
 
 ## Next steps
 
-Now that you've deployed your search service, continue in the Azure portal to create your first index:
+Now that you deployed your search service, continue in the Azure portal to create your first index:
 
 > [!div class="nextstepaction"]
 > [Quickstart: Create an Azure AI Search index in the Azure portal](search-get-started-portal.md)

@@ -5,7 +5,7 @@ author: mattwojo
 ms.author: mattwoj
 ms.service: azure-ai-search
 ms.topic: quickstart
-ms.date: 02/23/2026
+ms.date: 07/20/2026
 ms.custom: dev-focus
 ai-usage: ai-assisted
 zone_pivot_groups: search-sdks-rest

@@ -10,19 +10,20 @@ ms.custom:
   - mode-arm
   - devx-track-arm-template
   - ignite-2023
-ms.date: 06/10/2026
+ms.date: 07/20/2026
 ms.update-cycle: 365-days
+ai-usage: ai-assisted
 ---
 
 # Quickstart: Deploy Azure AI Search using an Azure Resource Manager template
 
 [!INCLUDE [search-fiq-banner](./includes/search-fiq-banner.md)]
 
-In this quickstart, you use an Azure Resource Manager (ARM) template to deploy an Azure AI Search service in the Azure portal.
+In this quickstart, use an Azure Resource Manager template to deploy an Azure AI Search service in the Azure portal.
 
 [!INCLUDE [About Azure Resource Manager](~/reusable-content/ce-skilling/azure/includes/resource-manager-quickstart-introduction.md)]
 
-Only those properties included in the template are used in the deployment. If more customization is required, such as [setting up network security](search-security-best-practices.md#configure-network-security), you can update the service as a post-deployment task. To customize an existing service with the fewest steps, use [Azure CLI](search-manage-azure-cli.md) or [Azure PowerShell](search-manage-powershell.md). If you're evaluating preview features, use the [Management REST API](search-manage-rest.md).
+The deployment uses only the properties included in the template. If you need more customization, such as [setting up network security](search-security-best-practices.md#configure-network-security), you can update the service as a post-deployment task. To customize an existing service with the fewest steps, use [Azure CLI](search-manage-azure-cli.md) or [Azure PowerShell](search-manage-powershell.md). If you're evaluating preview features, use the [Management REST API](search-manage-rest.md).
 
 Assuming your environment meets the prerequisites and you're familiar with using ARM templates, select the **Deploy to Azure** button. The template will open in the Azure portal.
 
@@ -34,11 +35,11 @@ If you don't have an Azure subscription, create a [free account](https://azure.m
 
 ## Review the template
 
-The template used in this quickstart is from [Azure Quickstart Templates](https://azure.microsoft.com/resources/templates/azure-search-create/).
+This quickstart uses a template from [Azure Quickstart Templates](https://azure.microsoft.com/resources/templates/azure-search-create/).
 
 :::code language="json" source="~/quickstart-templates/quickstarts/microsoft.search/azure-search-create/azuredeploy.json":::
 
-The Azure resource defined in this template:
+The template defines the following Azure resource:
 
 - [Microsoft.Search/searchServices](/azure/templates/Microsoft.Search/searchServices): create an Azure AI Search service
 
@@ -48,7 +49,7 @@ Select the following image to sign in to Azure and open a template. The template
 
 :::image type="content" source="~/reusable-content/ce-skilling/azure/media/template-deployments/deploy-to-azure-button.svg" alt-text="Button to deploy the Resource Manager template to Azure." border="false" link="https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2Fazure%2Fazure-quickstart-templates%2Fmaster%2Fquickstarts%2Fmicrosoft.search%2Fazure-search-create%2Fazuredeploy.json":::
 
-The Azure portal displays a form that allows you to easily provide parameter values. Some parameters are prefilled with the default values from the template. Provide your subscription, resource group, location, and service name. If you want to use Foundry Tools in an [AI enrichment](cognitive-search-concept-intro.md) pipeline, such as analyzing binary image files for text, choose a location that offers both Azure AI Search and Foundry Tools. Unless you use a keyless connection (preview), your Azure AI Search service and Microsoft Foundry resource must be in the same region for AI enrichment workloads. After you complete the form, agree to the terms and conditions, and then select the purchase button to complete your deployment.
+The Azure portal displays a form that you can use to easily provide parameter values. Some parameters are prefilled with the default values from the template. Provide your subscription, resource group, location, and service name. If you want to use Microsoft Foundry in an [AI enrichment](cognitive-search-concept-intro.md) pipeline, such as for analyzing binary image files for text, choose a location that offers both Azure AI Search and Microsoft Foundry. Unless you use a keyless connection (preview), your Azure AI Search service and Microsoft Foundry resource must be in the same region for AI enrichment workloads. After you complete the form, agree to the terms and conditions, and then select the purchase button to complete your deployment.
 
 > [!div class="mx-imgBorder"]
 > ![Azure portal display of template](./media/search-get-started-arm/arm-portalscrnsht.png)
@@ -59,11 +60,11 @@ When your deployment is complete, you can access your new resource group and new
 
 ## Clean up resources
 
-Other Azure AI Search quickstarts and tutorials build upon this quickstart. If you plan to continue on to work with subsequent quickstarts and tutorials, you may wish to leave this resource in place. When no longer needed, you can delete the resource group, which deletes the Azure AI Search service and related resources.
+Other Azure AI Search quickstarts and tutorials build upon this quickstart. If you plan to continue to work with subsequent quickstarts and tutorials, you might want to leave this resource in place. When you no longer need the resources, you can delete the resource group. Deleting the resource group deletes the Azure AI Search service and related resources.
 
 ## Related content
 
-In this quickstart, you created an Azure AI Search service using an ARM template and then validated the deployment. To learn more about Azure AI Search and Azure Resource Manager, see the following articles:
+In this quickstart, you created an Azure AI Search service by using an ARM template and then validated the deployment. To learn more about Azure AI Search and Azure Resource Manager, see the following articles:
 
 - [What is Azure AI Search?](search-what-is-azure-search.md)
 - [Quickstart: Full-text search in the Azure portal](search-get-started-portal.md)

@@ -10,41 +10,41 @@ ms.custom:
   - mode-arm
   - devx-track-bicep
   - ignite-2023
-ms.date: 06/10/2026
+ms.date: 07/20/2026
 ms.update-cycle: 365-days
 ---
 
 # Quickstart: Deploy Azure AI Search using Bicep
 
 [!INCLUDE [search-fiq-banner](./includes/search-fiq-banner.md)]
 
-In this quickstart, you use a Bicep file to deploy an Azure AI Search service in the Azure portal.
+In this quickstart, use a Bicep file to deploy an Azure AI Search service in the Azure portal.
 
 [!INCLUDE [About Bicep](~/reusable-content/ce-skilling/azure/includes/resource-manager-quickstart-bicep-introduction.md)]
 
-Only those properties included in the template are used in the deployment. If more customization is required, such as [setting up network security](search-security-best-practices.md#configure-network-security), you can update the service as a post-deployment task. To customize an existing service with the fewest steps, use [Azure CLI](search-manage-azure-cli.md) or [Azure PowerShell](search-manage-powershell.md). If you're evaluating preview features, use the [Management REST API](search-manage-rest.md).
+The deployment uses only the properties included in the template. If you need more customization, such as [setting up network security](search-security-best-practices.md#configure-network-security), you can update the service as a post-deployment task. To customize an existing service with the fewest steps, use [Azure CLI](search-manage-azure-cli.md) or [Azure PowerShell](search-manage-powershell.md). If you're evaluating preview features, use the [Management REST API](search-manage-rest.md).
 
 > [!TIP]
-> For an alternative Bicep template that deploys Azure AI Search with a pre-configured indexer to Cosmos DB for NoSQL, see [Bicep deployment of Azure AI Search](https://github.com/Azure-Samples/azure-search-deployment-template). There's no bicep template support for Azure AI Search data plane operations like creating an index, but you can add a module that calls REST APIs. The sample includes a module that creates an index, data source connector, and an indexer that refreshes from Cosmos DB at 5-minute intervals.
+> For an alternative Bicep template that deploys Azure AI Search with a preconfigured indexer to Cosmos DB for NoSQL, see [Bicep deployment of Azure AI Search](https://github.com/Azure-Samples/azure-search-deployment-template). There's no Bicep template support for Azure AI Search data plane operations like creating an index, but you can add a module that calls REST APIs. The sample includes a module that creates an index, data source connector, and an indexer that refreshes from Cosmos DB at 5-minute intervals.
 
 ## Prerequisites
 
 If you don't have an Azure subscription, create a [free account](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn) before you begin.
 
 ## Review the Bicep file
 
-The Bicep file used in this quickstart is from [Azure Quickstart Templates](https://azure.microsoft.com/resources/templates/azure-search-create/).
+This quickstart uses a Bicep file from [Azure Quickstart Templates](https://azure.microsoft.com/resources/templates/azure-search-create/).
 
 :::code language="bicep" source="~/quickstart-templates/quickstarts/microsoft.search/azure-search-create/main.bicep":::
 
-The Azure resource defined in this Bicep file:
+The Bicep file defines the following Azure resource:
 
 - [Microsoft.Search/searchServices](/azure/templates/Microsoft.Search/searchServices): create an Azure AI Search service
 
 ## Deploy the Bicep file
 
-1. Save the Bicep file as **main.bicep** to your local computer.
-1. Deploy the Bicep file using either Azure CLI or Azure PowerShell.
+1. Save the Bicep file as **main.bicep** on your local computer.
+1. Deploy the Bicep file by using either Azure CLI or Azure PowerShell.
 
     # [CLI](#tab/CLI)
 
@@ -65,7 +65,7 @@ The Azure resource defined in this Bicep file:
     > [!NOTE]
     > Replace **\<service-name\>** with the name of the Search service. The service name must only contain lowercase letters, digits, or dashes. You can't use a dash as the first two characters or the last character. The name has a minimum length of 2 characters and a maximum length of 60 characters.
 
-    When the deployment finishes, you should see a message indicating the deployment succeeded.
+    When the deployment finishes, you see a message indicating the deployment succeeded.
 
 ## Review deployed resources
 
@@ -87,7 +87,7 @@ Get-AzResource -ResourceGroupName exampleRG
 
 ## Clean up resources
 
-Azure AI Search is a billable resource. If it's no longer needed, delete it from your subscription to avoid charges. You can use the Azure portal, Azure CLI, or Azure PowerShell to delete the resource group and its resources.
+Azure AI Search is a billable resource. If you no longer need it, delete it from your subscription to avoid charges. You can use the Azure portal, Azure CLI, or Azure PowerShell to delete the resource group and its resources.
 
 # [CLI](#tab/CLI)
 

@@ -5,7 +5,8 @@ author: mattwojo
 ms.author: mattwoj
 ms.service: azure-ai-search
 ms.topic: quickstart
-ms.date: 03/13/2026
+ms.date: 07/20/2026
+ai-usage: ai-assisted
 ---
 
 # Quickstart: Multimodal search in the Azure portal
@@ -69,6 +70,8 @@ The portal supports the following models for each method. Deployment instruction
 
 <sup>4</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Microsoft Foundry portal](https://ai.azure.com/?cid=learnDocs) aren't supported. You must create an Azure OpenAI resource in the Azure portal.
 
+For the latest model lifecycle guidance, including deprecations, see [Model retirement and deprecation](/azure/ai-foundry/openai/concepts/model-retirements).
+
 ### Public endpoint requirements
 
 All of the preceding resources must have public access enabled so that the wizard can access them. Otherwise, the wizard fails. After the wizard runs, you can enable firewalls and private endpoints on the integration components for security. For more information, see [Secure connections in the import wizard](search-import-data-portal.md#secure-connections).

@@ -8,7 +8,8 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: quickstart
-ms.date: 03/13/2026
+ms.date: 07/20/2026
+ai-usage: ai-assisted
 ---
 
 # Quickstart: Vector search in the Azure portal
@@ -63,6 +64,8 @@ The portal supports the following embedding models for integrated vectorization.
 
 <sup>4</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Microsoft Foundry portal](https://ai.azure.com/?cid=learnDocs) aren't supported. You must create an Azure OpenAI resource in the Azure portal.
 
+For the latest model lifecycle guidance, including deprecations, see [Model retirement and deprecation](/azure/ai-foundry/openai/concepts/model-retirements).
+
 ### Public endpoint requirements
 
 All of the preceding resources must have public access enabled so that the wizard can access them. Otherwise, the wizard fails. After the wizard runs, you can enable firewalls and private endpoints on the integration components for security. For more information, see [Secure connections in the import wizard](search-import-data-portal.md#secure-connections).

@@ -5,11 +5,12 @@ author: mattwojo
 ms.author: mattwoj
 ms.service: azure-ai-search
 ms.topic: quickstart
-ms.date: 03/13/2026
+ms.date: 07/21/2026
 ms.custom:
   - mode-ui
   - ignite-2023
   - ignite-2024
+ai-usage: ai-assisted
 ---
 
 # Quickstart: Full-text search in the Azure portal
@@ -24,7 +25,7 @@ The wizard creates multiple objects on your search service, including a searchab
 
 + An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn).
 
-+ An [Azure AI Search service](search-create-service-portal.md). This quickstart requires the Basic tier or higher for managed identity support.
++ An [Azure AI Search service](search-create-service-portal.md). This quickstart requires the Basic tier or higher for managed identity support. Managed identity is used for secure, keyless authentication between Azure AI Search and indexer data sources.
 
 + An [Azure Storage account](/azure/storage/common/storage-account-create). Use Azure Blob Storage or Azure Data Lake Storage Gen2 (storage account with a hierarchical namespace) on a standard performance (general-purpose v2) account. To avoid bandwidth charges, use the same region as Azure AI Search.
 

@@ -5,7 +5,8 @@ author: mattwojo
 ms.author: mattwoj
 ms.service: azure-ai-search
 ms.topic: quickstart
-ms.date: 03/25/2026
+ms.date: 07/21/2026
+ai-usage: ai-assisted
 zone_pivot_groups: search-python-rest
 ---
 

@@ -9,14 +9,17 @@ ms.custom:
   - devx-track-python
   - ignite-2023
 ms.topic: quickstart
-ms.date: 03/25/2026
+ms.date: 07/14/2026
+ai-usage: ai-assisted
 zone_pivot_groups: search-sdks-rest
 ---
 
 # Quickstart: Semantic ranking
 
 [!INCLUDE [search-fiq-banner](./includes/search-fiq-banner.md)]
 
+In this quickstart, you add semantic ranking to an existing Azure AI Search index and run semantic queries to improve result relevance. Use the language tabs to choose your preferred SDK or REST workflow.
+
 ::: zone pivot="csharp"
 
 [!INCLUDE [C#](includes/quickstarts/semantic-ranker-csharp.md)]

@@ -2,7 +2,7 @@
 title: 'Quickstart: Deploy Using Terraform'
 description: 'In this article, you create an Azure AI Search service using Terraform.'
 ms.topic: quickstart
-ms.date: 06/10/2026
+ms.date: 07/20/2026
 ms.update-cycle: 365-days
 ms.custom:
   - devx-track-terraform
@@ -19,17 +19,17 @@ ai-usage: ai-assisted
 
 [!INCLUDE [search-fiq-banner](./includes/search-fiq-banner.md)]
 
-This article shows how to use Terraform to create an [Azure AI Search service](./search-what-is-azure-search.md) using [Terraform](/azure/developer/terraform/quickstart-configure).
+This article shows how to use Terraform to create an [Azure AI Search service](./search-what-is-azure-search.md) by using [Terraform](/azure/developer/terraform/quickstart-configure).
 
 [!INCLUDE [Terraform abstract](~/azure-dev-docs-pr/articles/terraform/includes/abstract.md)]
 
 In this article, you learn how to:
 
 > [!div class="checklist"]
-> * Create a random pet name for the Azure resource group name using [random_pet](https://registry.terraform.io/providers/hashicorp/random/latest/docs/resources/pet)
-> * Create an Azure resource group using [azurerm_resource_group](https://registry.terraform.io/providers/hashicorp/azurerm/latest/docs/resources/resource_group)
-> * Create a random string using [random_string](https://registry.terraform.io/providers/hashicorp/random/latest/docs/resources/string)
-> * Create an Azure AI Search service using [azurerm_search_service](https://registry.terraform.io/providers/hashicorp/azurerm/latest/docs/resources/search_service)
+> * Create a random pet name for the Azure resource group name by using [random_pet](https://registry.terraform.io/providers/hashicorp/random/latest/docs/resources/pet)
+> * Create an Azure resource group by using [azurerm_resource_group](https://registry.terraform.io/providers/hashicorp/azurerm/latest/docs/resources/resource_group)
+> * Create a random string by using [random_string](https://registry.terraform.io/providers/hashicorp/random/latest/docs/resources/string)
+> * Create an Azure AI Search service by using [azurerm_search_service](https://registry.terraform.io/providers/hashicorp/azurerm/latest/docs/resources/search_service)
 
 ## Prerequisites
 
@@ -38,9 +38,9 @@ In this article, you learn how to:
 ## Implement the Terraform code
 
 > [!NOTE]
-> See more [articles and sample code showing how to use Terraform to manage Azure resources](/azure/terraform)
+> For more information, see [articles and sample code showing how to use Terraform to manage Azure resources](/azure/terraform).
 
-1. Create a directory in which to test and run the sample Terraform code and make it the current directory.
+1. Create a directory to test and run the sample Terraform code. Make it the current directory.
 
 1. Create a file named `main.tf` and insert the following code:
 
@@ -72,7 +72,7 @@ In this article, you learn how to:
 
 ## Verify the results
 
-1. Get the Azure resource name in which the Azure AI Search service was created.
+1. Get the Azure resource name where you created the Azure AI Search service.
 
     ```console
     resource_group_name=$(terraform output -raw resource_group_name)

@@ -13,7 +13,8 @@ ms.custom:
   - ignite-2023
 ms.topic: quickstart
 zone_pivot_groups: search-sdks-rest-powershell
-ms.date: 02/02/2026
+ms.date: 07/20/2026
+ai-usage: ai-assisted
 ---
 
 # Quickstart: Full-text search

@@ -8,7 +8,7 @@ ms.custom:
   - ignite-2023
   - dev-focus
 ms.topic: quickstart
-ms.date: 01/14/2026
+ms.date: 07/21/2026
 ai-usage: ai-assisted
 zone_pivot_groups: search-sdks-rest
 ---
@@ -17,6 +17,9 @@ zone_pivot_groups: search-sdks-rest
 
 [!INCLUDE [search-fiq-banner](./includes/search-fiq-banner.md)]
 
+> [!NOTE]
+> For embedding models in vector search workflows, Azure AI Search supports `text-embedding-ada-002`, `text-embedding-3-small`, and `text-embedding-3-large` from Azure OpenAI. For AI-enriched workflows using chat completion models, see [Model retirement schedules](/azure/foundry/openai/concepts/model-retirement-schedule) to check deprecation status of GPT-4 family models.
+
 ::: zone pivot="csharp"
 
 [!INCLUDE [C#](includes/quickstarts/search-get-started-vector-csharp.md)]

@@ -8,8 +8,9 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 06/10/2026
+ms.date: 07/21/2026
 ms.update-cycle: 365-days
+ai-usage: ai-assisted
 ---
 
 # Visualize Azure AI Search logs and metrics with Power BI
@@ -19,7 +20,7 @@ ms.update-cycle: 365-days
 Azure AI Search can send operation logs and service metrics to an Azure Storage account, which can then be visualized in Power BI. This article explains the steps and how to use a Power BI template app to visualize the data. The template covers information about queries, indexing, operations, and service metrics.
 
 > [!NOTE]
-> The Power BI template currently uses a former product name, Azure Cognitive Search. The product name will be updated on the next template refresh.
+> The Power BI template is currently listed with the legacy product name Azure Cognitive Search in AppSource and in-app report labels.
 
 ## Set up logging and install the template
 
@@ -32,7 +33,7 @@ Azure AI Search can send operation logs and service metrics to an Azure Storage
     1. Check **Archive to a storage account**, provide your storage account information, and check **OperationLogs** and **AllMetrics**.
     1. Select **Save**.
 
-1. Once logging is enabled, logs and metrics are generated as you use the search service. It can take up to an hour before logged events show up in Azure Storage. Look for a **insights-logs-operationlogs** container for operations and a **insights-metrics-pt1m** container for metrics. Check your storage account for these containers to make sure you have data to visualize.
+1. Once logging is enabled, logs and metrics are generated as you use the search service. It can take up to an hour before logged events show up in Azure Storage. Look for an **insights-logs-operationlogs** container for operations and an **insights-metrics-pt1m** container for metrics. Check your storage account for these containers to make sure you have data to visualize.
 
 1. Find the Power BI app template in the [Power BI Apps marketplace](https://appsource.microsoft.com/en-us/product/power-bi/azurecognitivesearch.azurecognitivesearchlogsandmetrics?tab=Overview) and install it into a new workspace or an existing workspace. The template is listed as **Azure Cognitive Search: Analyze Logs and Metrics**.
 
@@ -66,7 +67,7 @@ Azure AI Search can send operation logs and service metrics to an Azure Storage
 
 ## Modify app parameters
 
-If you would like to visualize data from a different storage account or change the number of days of data to query, follow the below steps to change the **Days** and **StorageAccount** parameters.
+If you want to visualize data from a different storage account or change the number of days of data to query, follow these steps to change the **Days** and **StorageAccount** parameters.
 
 1. Navigate to your Power BI apps, find your search app, and select the **Edit** action to continue to the workspace.
 
@@ -90,7 +91,7 @@ If you can't see your data, try these troubleshooting steps:
 
 1. Ensure the storage account name and access key you provided are correct. The storage account name should correspond to the account configured with your search service logs.
 
-1. Confirm that your storage account contains the  containers **insights-logs-operationlogs** and **insights-metrics-pt1m** and each container has data. The logs and metrics will be within a couple layers of folders.
+1. Confirm that your storage account contains the containers **insights-logs-operationlogs** and **insights-metrics-pt1m**, and that each container has data. The logs and metrics are nested in multiple folder levels.
 
 1. Check to see if the dataset is still refreshing. The refresh status indicator is shown in step 8 above. If it's still refreshing, wait until the refresh is complete to open and refresh the report.
 

@@ -4,9 +4,10 @@ description: Learn how to handle a regional capacity constraint that effects you
 author: mattwojo
 ms.author: mattwoj
 ms.reviewer: angiesi
-ms.date: 04/22/2026
+ms.date: 07/21/2026
 ms.service: azure-ai-search
 ms.topic: concept-article
+ai-usage: ai-assisted
 ---
 
 # How to handle regional capacity constraints in Azure AI Search
@@ -70,7 +71,7 @@ For the current list of regions that support Availability Zones for Azure AI Sea
 
 ## Feature and model availability
 
-Not all Azure AI Search features and AI models are available in every region. Before selecting an alternative region, verify availability for the specific capabilities your workload depends on, including any Azure OpenAI or Azure AI Foundry models used in retrieval-augmented generation (RAG), semantic ranking, or AI enrichment pipelines.
+Not all Azure AI Search features and AI models are available in every region. Before selecting an alternative region, verify availability for the specific capabilities your workload depends on, including any Azure OpenAI or Azure AI Foundry models used in retrieval-augmented generation (RAG), semantic ranking, agentic retrieval, or AI enrichment pipelines.
 
 When selecting an alternative region for Azure AI Search, verify model availability in the same region. Co-locating Azure AI Search with Azure OpenAI or Azure AI Foundry in the same region eliminates cross-service latency and simplifies compliance and data residency requirements.
 

@@ -5,7 +5,7 @@ author: mattwojo
 ms.author: mattwoj
 ms.service: azure-ai-search
 ms.topic: troubleshooting-general
-ms.date: 04/01/2026
+ms.date: 07/21/2026
 ai-usage: ai-assisted
 ---