Closing on the post-build catch up

Author: HeidiSteen

articles/search/TOC.yml

@@ -332,7 +332,7 @@
     items:
     - name: Create a vector index
       href: vector-search-how-to-create-index.md
-    - name: Index binary data for vector search
+    - name: Index binary data for vector search (preview)
       href: vector-search-how-to-index-binary-data.md
     - name: Query vectors
       href: vector-search-how-to-query.md

articles/search/media/vector-search-how-to-query/check-vectorizer.png

@@ -10,7 +10,7 @@ ms.service: cognitive-search
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 05/06/2024
+ms.date: 06/19/2024
 ---
 
 # Estimate and manage capacity of a search service
@@ -28,6 +28,9 @@ When scaling a search service, you can choose from the following tools and appro
 + [Azure CLI](/cli/azure/search/service#az-search-service-create-optional-parameters)
 + [Management REST API](/rest/api/searchmanagement/services/create-or-update)
 
+> [!NOTE]
+> Higher capacity partitions are available at the same billing rate on newer services created after April and May 2024. For more information, see [Service limits](search-limits-quotas-capacity.md#service-limits) for partition size upgrades.
+
 ## Concepts: search units, replicas, partitions
 
 Capacity is expressed in *search units* that can be allocated in combinations of *partitions* and *replicas*.  

articles/search/search-capacity-planning.md

@@ -10,7 +10,7 @@ ms.service: cognitive-search
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 04/01/2024
+ms.date: 06/19/2024
 ---
 
 # Plan and manage costs of an Azure AI Search service
@@ -21,6 +21,9 @@ As a first step, estimate your baseline costs by using the Azure pricing calcula
 
 Azure provides built-in cost management that cuts across service boundaries to provide inclusive cost monitoring and the ability to set budgets and define alerts. The costs of running a search service will vary depending on capacity and which features you use. After you create your search service, optimize capacity so that you pay only for what you need. 
 
+> [!NOTE]
+> Higher capacity partitions are available at the same billing rate on newer services created after April and May 2024. For more information, see [Service limits](search-limits-quotas-capacity.md#service-limits) for partition size upgrades.
+
 <a name="billable-events"></a>
 
 ## Understand the billing model

articles/search/search-sku-manage-costs.md

@@ -14,6 +14,9 @@ ms.date: 05/30/2024
 
 # Index binary vectors for vector search
 
+> [!IMPORTANT]
+> Binary data types are in public preview under [Supplemental Terms of Use](https://azure.microsoft.com/support/legal/preview-supplemental-terms/). The [2024-05-01-preview REST API](/rest/api/searchservice/operation-groups?view=rest-searchservice-2024-03-01-preview&preserve-view=true) and later preview APIs provide the new data type.
+
 Beginning with the 2024-05-01-preview REST API, Azure AI Search supports a packed binary type of `Collection(Edm.Byte)` for further reducing the storage and memory footprint of vector data. You can use this data type for output from models such as [Cohere's Embed v3 binary embedding models](https://cohere.com/blog/introducing-embed-v3).
 
 There are three steps to configuring an index for binary vectors:
@@ -23,7 +26,7 @@ There are three steps to configuring an index for binary vectors:
 > + Add a vector profile that points to the algorithm
 > + Add the vector profile to your binary field definition
 
-This article assumes you're familiar with [creating an index in Azure AI Search](search-how-to-create-search-index.md). It uses the REST APIs to illustrate each step. You can also add a binary field type to an index in the Azure portal.
+This article assumes you're familiar with [creating an index in Azure AI Search](search-how-to-create-search-index.md). It uses the REST APIs to illustrate each step, but you could also add a binary field to an index in the Azure portal.
 
 ## Prerequisites
 

articles/search/vector-search-how-to-configure-compression-storage.md

@@ -470,9 +470,11 @@ Search results would include a combination of text and images, assuming your sea
 
 ## Query with integrated vectorization (preview)
 
-This section shows a vector query that invokes the new [integrated vectorization](vector-search-integrated-vectorization.md) preview feature that converts a text query into a vector. Use [**2023-10-01-Preview** REST API](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2023-10-01-preview&preserve-view=true) or an updated beta Azure SDK package.
+This section shows a vector query that invokes the new [integrated vectorization](vector-search-integrated-vectorization.md) preview feature that converts a text query into a vector. Use [**2023-10-01-Preview** REST API](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2023-10-01-preview&preserve-view=true) and newer preview REST APIs or an updated beta Azure SDK package.
 
-A prerequisite is a search index having a [vectorizer configured and assigned](vector-search-how-to-configure-vectorizer.md) to a vector field. The vectorizer provides connection information to an embedding model used at query time.
+A prerequisite is a search index having a [vectorizer configured and assigned](vector-search-how-to-configure-vectorizer.md) to a vector field. The vectorizer provides connection information to an embedding model used at query time. Check the index definition for a vectorizers specification. 
+
+:::image type="content" source="media/vector-search-how-to-query/check-vectorizer.png" alt-text="Screenshot of a vectorizer setting in a search index.":::
 
 Queries provide text strings instead of vectors:
 
@@ -483,7 +485,7 @@ Queries provide text strings instead of vectors:
 Here's a simple example of a query that's vectorized at query time. The text string is vectorized and then used to query the descriptionVector field.
 
 ```http
-POST https://{{search-service}}.search.windows.net/indexes/{{index}}/docs/search?api-version=2023-10-01-preview
+POST https://{{search-service}}.search.windows.net/indexes/{{index}}/docs/search?api-version=2024-05-01-preview
 {
     "select": "title, genre, description",
     "vectorQueries": [
@@ -502,7 +504,7 @@ Here's a [hybrid query](hybrid-search-how-to-query.md) using integrated vectoriz
 In this example, the search engine makes three vectorization calls to the vectorizers assigned to `descriptionVector`, `synopsisVector`, and `authorBioVector` in the index. The resulting vectors are used to retrieve documents against their respective fields. The search engine also executes a keyword search on the `search` query, "mystery novel set in London". 
 
 ```http
-POST https://{{search-service}}.search.windows.net/indexes/{{index}}/docs/search?api-version=2023-10-01-preview
+POST https://{{search-service}}.search.windows.net/indexes/{{index}}/docs/search?api-version=2024-05-01-preview
 Content-Type: application/json
 api-key: {{admin-api-key}}
 {
@@ -571,9 +573,11 @@ During query execution, a vector query can only target one internal vector index
 
 ## Set thresholds to exclude low-scoring results (preview)
 
-Because nearest neighbor search always returns the requested `k` neighbors, it's possible to get low scoring matches as part of meeting the `k` number requirement on search results.
+Because nearest neighbor search always returns the requested `k` neighbors, it's possible to get multiple low scoring matches as part of meeting the `k` number requirement on search results.
+
+Using the 2024-05-01-preview REST APIs, you can now add a `threshold` query parameter to exclude low-scoring search results based on a minimum score. Filtering occurs before [fusing results](hybrid-search-ranking.md) from different recall sets. 
 
-Using the 2024-05-01-preview REST APIs, you can now add a `threshold` query parameter to exclude low-scoring search results.
+In this example, all matches that score below 0.8 are excluded from vector search results, even if the number of results fall below `k`.
 
 ```http
 POST https://[service-name].search.windows.net/indexes/[index-name]/docs/search?api-version=2024-05-01-Preview 
@@ -595,8 +599,6 @@ POST https://[service-name].search.windows.net/indexes/[index-name]/docs/search?
     }
 ```
 
-Filtering occurs before [fusing results](hybrid-search-ranking.md) from different recall sets. 
-
  <!-- Keep H2 as-is. Direct link from a blog post. Bulk of maxtextsizerecall has moved to hybrid query doc-->
 ## MaxTextSizeRecall for hybrid search (preview)
 
@@ -608,7 +610,7 @@ For more information, see [Set maxTextRecallSize - Create a hybrid query](hybrid
 
 ## Vector weighting (preview)
 
-Add a `weight` query parameter to specify the relative weight of each vector included in search operations. This value is used when combining the results of multiple ranking lists produced by two or more vector queries in the same request, or from the vector portion of a hybrid query.
+Add a `weight` query parameter to specify the relative weight of each vector query included in search operations. This value is used when combining the results of multiple ranking lists produced by two or more vector queries in the same request, or from the vector portion of a hybrid query.
 
 The default is 1.0 and the value must be a positive number larger than zero.