Merge pull request #246894 from HeidiSteen/heidist-vectors

[azure search] semantic search basic tier support

Author: prmerger-automator[bot]

articles/search/search-get-started-semantic.md

@@ -27,7 +27,7 @@ This quickstart walks you through the query modifications that invoke semantic s
 
 + An Azure account with an active subscription. [Create an account for free](https://azure.microsoft.com/free/).
 
-+ Azure Cognitive Search, at Standard one (S1) tier or higher, with [semantic search enabled](semantic-search-overview.md#enable-semantic-search).
++ Azure Cognitive Search, at Basic tier or higher, with [semantic search enabled](semantic-search-overview.md#enable-semantic-search).
 
 + An API key and search endpoint:
 

articles/search/search-sku-tier.md

@@ -66,7 +66,7 @@ Most features are available on all tiers, including the free tier. In a few case
 | [IP firewall access](service-configure-firewall.md) | Not available on the Free tier. |
 | [Private endpoint (integration with Azure Private Link)](service-create-private-endpoint.md) | For inbound connections to a search service, not available on the Free tier. For outbound connections by indexers to other Azure resources, not available on Free or S3 HD. For indexers that use skillsets, not available on Free, Basic, S1, or S3 HD.| 
 | [Availability Zones](search-reliability.md) | Not available on the Free or Basic tier. |
-| [Semantic search (preview)](semantic-search-overview.md) | Not available on the Free or Basic tier. |
+| [Semantic search (preview)](semantic-search-overview.md) | Not available on the Free tier. |
 
 Resource-intensive features might not work well unless you give it sufficient capacity. For example, [AI enrichment](cognitive-search-concept-intro.md) has long-running skills that time out on a Free service unless the dataset is small.
 

articles/search/semantic-how-to-query-request.md

@@ -25,9 +25,9 @@ There are two main activities to perform:
 
 ## Prerequisites
 
-+ A search service on Standard tier (S1, S2, S3) or Storage Optimized tier (L1, L2), subject to [region availability](https://azure.microsoft.com/global-infrastructure/services/?products=search).
++ A search service on Basic, Standard tier (S1, S2, S3), or Storage Optimized tier (L1, L2), subject to [region availability](https://azure.microsoft.com/global-infrastructure/services/?products=search).
 
-  If you have an existing S1 or greater service in a supported region, you can enable semantic search without having to create a new service.
+  If you have an existing Basic or greater service in a supported region, you can enable semantic search without having to create a new service.
 
 + Semantic search [enabled on your search service](semantic-search-overview.md#enable-semantic-search).
 

articles/search/semantic-ranking.md

@@ -69,7 +69,7 @@ A [semantic answer](semantic-answers.md) will also be returned if you specified
 
 ## Next steps
 
-Semantic ranking is offered on Standard tiers, in specific regions. For more information about availability and sign-up, see [Availability and pricing](semantic-search-overview.md#availability-and-pricing). A new query type enables the ranking and response structures of semantic search. To get started, [Configure semantic ranking](semantic-how-to-query-request.md).
+Semantic ranking is offered on Basic tiers and higher, in specific regions. For more information about availability and sign-up, see [Availability and pricing](semantic-search-overview.md#availability-and-pricing). A new query type enables the ranking and response structures of semantic search. To get started, [Configure semantic ranking](semantic-how-to-query-request.md).
 
 Alternatively, review the following articles about default ranking. Semantic ranking depends on the similarity ranker to return the initial results. Knowing about query execution and ranking will give you a broad understanding of how the entire process works.
 

articles/search/vector-search-how-to-create-index.md

@@ -71,23 +71,25 @@ If the index doesn't have a vector configuration, you're prompted to create one
    + Name the field (no spaces).
    + Choose type `Collection(Edm.Single)`.
    + Select "Retrievable" if you want the query to return the vector data in search results. If you have other fields with human readable content that you can return as a proxy for the match, you should set "Retrievable" to false to save space.
-   + "Searchable" is mandatory for a vector field and can't be set.
-   + "Dimensions" is the length of the vector returned by the model. Set this value to specify `1536` for **text-embeddding-ada-002**, where the input text that you provide is described numerically using 1536 dimension.
+   + "Searchable" is mandatory for a vector field and can't be changed.
+   + "Dimensions" is the length of the vector returned by the model. Set this value to specify `1536` for **text-embeddding-ada-002**, where the input text that you provide is numerically described using 1536 dimensions.
 
-1. Select or create a vector configuration used for similarity search. Currently, only Hierarchical Navigation Small World (HNSW) is supported. If there's no configuration in the index, select **Create**.
+1. Select or create a vector configuration used for similarity search. If the index doesn't have a vector configuration, you must select **Create**.
 
    :::image type="content" source="media/vector-search-how-to-create-index/portal-add-vector-configuration.png" alt-text="Screenshot of the vector configuration properties." border="true":::
 
    **Key points**:
 
-   + Name the configuration(no spaces). The name must be unique within the index.
-   + "hnsw" is the Approximate Nearest Neighbors (ANN) algorithm used to find similar vectors. 
-   + "Bi-directional link count" default is 4. The range is 2 to 100. Lower values should return less noise in the results. 
+   + Name the configuration. The name must be unique within the index.
+   + "hnsw" is the Approximate Nearest Neighbors (ANN) algorithm used to find similar vectors. Currently, only Hierarchical Navigable Small World (HNSW) is supported. 
+   + "Bi-directional link count" default is 4. The range is 2 to 100. Lower values (lower recall) should return less noise in the results. 
    + "efConstruction" default is 400. It's the number of nearest neighbors used during indexing.
    + "efSearch default is 500. It's the number of nearest neighbors used during search.
    + "Similarity metric" should be "cosine" if you're using Azure OpenAI, otherwise use the similarity metric of the embedding model. Supported values are `cosine`, `dotProduct`, `euclidean`.
 
-If you're familiar with HNSW parameters, you might be wondering about "k" number of nearest neighbors to return in the result. In Cognitive Search, that value is set on the query request.
+   If you're familiar with HNSW parameters, you might be wondering about "k" number of nearest neighbors to return in the result. In Cognitive Search, that value is set on the query request.
+
+1. Select **Save** to save the vector configuration and the field definition.
 
 ### [**REST API**](#tab/rest-add-field)
 

articles/search/whats-new.md

@@ -7,7 +7,7 @@ author: HeidiSteen
 ms.author: heidist
 ms.service: cognitive-search
 ms.topic: overview
-ms.date: 06/29/2023
+ms.date: 07/31/2023
 ms.custom: references_regions
 ---
 
@@ -24,6 +24,7 @@ Learn about the latest updates to Azure Cognitive Search functionality, docs, an
 |-----------------------------|------|--------------|
 | [**Vector search public preview**](vector-search-overview.md) | Feature | Adds vector fields to a search index for similarity search over vector representations of data. |
 | [**2023-07-01-Preview Search REST API**](/rest/api/searchservice/index-preview) | API | New preview version of the Search REST APIs that adds support for vector search. This API version is inclusive of all preview features. If you're using earlier previews, switch to **2023-07-01-preview** with no loss of functionality.  |
+| [**Semantic search availability**](semantic-search-overview.md) | Feature | Semantic search is now available on the Basic tier. |
 
 ## May 2023