@@ -9,22 +9,19 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 05/08/2025
+ms.date: 07/21/2025
 ---
 
 # Create a hybrid query in Azure AI Search
 
-[Hybrid search](hybrid-search-overview.md) combines text (keyword) and vector queries in a single search request. All subqueries in the request execute in parallel. The results are merged and reordered by new search scores, using [Reciprocal Rank Fusion (RRF)](hybrid-search-ranking.md) to return a unified result set. In many cases, [per benchmark tests](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/azure-ai-search-outperforming-vector-search-with-hybrid/ba-p/3929167), hybrid queries with semantic ranking return the most relevant results.
+[Hybrid search](hybrid-search-overview.md) combines text (keyword) and vector queries in a single search request. Both queries execute in parallel. The results are merged and reordered by new search scores, using [Reciprocal Rank Fusion (RRF)](hybrid-search-ranking.md) to return a unified result set. In many cases, [per benchmark tests](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/azure-ai-search-outperforming-vector-search-with-hybrid/ba-p/3929167), hybrid queries with semantic ranking return the most relevant results.
 
 In this article, learn how to:
 
-+ Set up a basic request
++ Set up a basic hybrid request
 + Add parameters and filters
 + Improve relevance using semantic ranking or vector weights
-+ Optimize query behaviors by controlling text and vector inputs
-
-> [!NOTE]
-> New in [**2024-09-01-preview**](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true) is the ability to target filters to just the vector subqueries in a hybrid request. This gives you more precision over how filters are applied. For more information, see [targeting filters to vector subqueries](#hybrid-search-with-filters-targeting-vector-subqueries-preview) in this article.
++ Optimize query behaviors by controlling inputs (`maxTextRecallSize`)
 
 ## Prerequisites
 
@@ -38,30 +35,33 @@ In this article, learn how to:
 
 + Search Explorer in the Azure portal (supports both stable and preview API search syntax) has a JSON view that lets you paste in a hybrid request.
 
-+ [**2024-07-01**](/rest/api/searchservice/documents/search-post) stable version or a recent preview API version if you're using preview features like [maxTextRecallSize and countAndFacetMode(preview)](#set-maxtextrecallsize-and-countandfacetmode).
++ Newer stable or preview packages of the Azure SDKs (see change logs for SDK feature support).
+
++ [Stable REST APIs](/rest/api/searchservice/documents/search-post) or a recent preview API version if you're using preview features like [maxTextRecallSize and countAndFacetMode(preview)](#set-maxtextrecallsize-and-countandfacetmode).
 
-  For readability, we use REST examples to explain how the APIs work. You can use a REST client like Visual Studio Code with the REST extension to build hybrid queries. For more information, see [Quickstart: Vector search using REST APIs](search-get-started-vector.md).
+  For readability, we use REST examples to explain how the APIs work. You can use a REST client like Visual Studio Code with the REST extension to build hybrid queries. You can also use the Azure SDKs. For more information, see [Quickstart: Vector search](search-get-started-vector.md).
 
-+ Newer stable or beta packages of the Azure SDKs (see change logs for SDK feature support).
+## Set up a hybrid query
+
+This section explains the basic structure of a hybrid query and how to set one up in either Search Explorer or for execution in a REST client.
+
+Results are returned in plain text, including vectors in fields marked as `retrievable`. Because numeric vectors aren't useful in search results, choose other fields in the index as a proxy for the vector match. For example, if an index has "descriptionVector" and "descriptionText" fields, the query can match on "descriptionVector" but the search result can show "descriptionText". Use the `select` parameter to specify only human-readable fields in the results.
 
-## Set up a hybrid query in Search Explorer
+### [**Azure portal**](#tab/portal)
 
-1. In [Search Explorer](search-explorer.md), make sure the API version is **2024-07-01** or a newer preview API version.
+1. Sign in to the [Azure portal](https://portal.azure.com) and find your search service.
 
-1. Under **View**, select **JSON view** so that you can paste in a vector query. 
+1. Under **Search management** > **Indexes**, select an index that has vectors and non-vector content. [Search Explorer](search-explorer.md) is the first tab.
 
-1. Replace the default query template with a hybrid query, such as the "Run a hybrid query" example starting on line 539 in the [vector quickstart](https://raw.githubusercontent.com/Azure-Samples/azure-search-rest-samples/refs/heads/main/Quickstart-vectors/az-search-quickstart-vectors.rest). For brevity, the vector is truncated in this article. 
+1. Under **View**, switch to **JSON view** so that you can paste in a vector query. 
 
-   A hybrid query has a text query specified in `search`, and a vector query specified under `vectorQueries.vector`.
+1. Replace the default query template with a hybrid query. A basic hybrid query has a text query specified in `search`, and a vector query specified under `vectorQueries.vector`. The text query and vector query can be equivalent or divergent, but it's common for them to share the same intent.
 
-   The text query and vector query can be equivalent or divergent, but it's common for them to share the same intent.
+   This example is from the [vector quickstart](https://raw.githubusercontent.com/Azure-Samples/azure-search-rest-samples/refs/heads/main/Quickstart-vectors/az-search-quickstart-vectors.rest) that has vector and nonvector content, and several query examples. For brevity, the vector is truncated in this article. 
 
     ```json
     {
-        "count": true,
         "search": "historic hotel walk to restaurants and shopping",
-        "select": "HotelId, HotelName, Category, Tags, Description",
-        "top": 7,
         "vectorQueries": [
             {
                 "vector": [0.01944167, 0.0040178085, -0.007816401 ... <remaining values omitted> ], 
@@ -76,16 +76,34 @@ In this article, learn how to:
 
 1. Select **Search**.
 
-> [!TIP]
-> Search results are easier to read if you hide the vectors. In **Query Options**, turn on **Hide vector values in search results**.
+   > [!TIP]
+   > Search results are easier to read if you hide the vectors. In **Query Options**, turn on **Hide vector values in search results**.
+
+1. Here's another version of the query. This one adds a `count` for the number of matches found, a `select` parameter for choosing specific fields, and a `top` parameter to return the top seven results.
 
-## Hybrid query request (REST API)
+   ```json
+    {
+        "count": true,
+        "search": "historic hotel walk to restaurants and shopping",
+        "select": "HotelId, HotelName, Category, Tags, Description",
+        "top": 7,
+        "vectorQueries": [
+            {
+                "vector": [0.01944167, 0.0040178085, -0.007816401 ... <remaining values omitted> ], 
+                "k": 7,
+                "fields": "DescriptionVector",
+                "kind": "vector",
+                "exhaustive": true
+            }
+        ]
+    }
+    ```
 
-A hybrid query combines text search and vector search, where the `search` parameter takes a query string and `vectorQueries.vector` takes the vector query. The search engine runs full text and vector queries in parallel. The union of all matches is evaluated for relevance using Reciprocal Rank Fusion (RRF) and a single result set is returned in the response.
+### [**REST**](#tab/hybrid-rest)
 
-Results are returned in plain text, including vectors in fields marked as `retrievable`. Because numeric vectors aren't useful in search results, choose other fields in the index as a proxy for the vector match. For example, if an index has "descriptionVector" and "descriptionText" fields, the query can match on "descriptionVector" but the search result can show "descriptionText". Use the `select` parameter to specify only human-readable fields in the results.
+The following example shows a hybrid query request using the REST API.
 
-The following example shows a hybrid query configuration.
+This example is from the [vector quickstart](https://raw.githubusercontent.com/Azure-Samples/azure-search-rest-samples/refs/heads/main/Quickstart-vectors/az-search-quickstart-vectors.rest) that has vector and nonvector content, and several query examples. For brevity, the vector is truncated in this article. 
 
 ```http
 POST https://{{search-service-name}}.search.windows.net/indexes/{{index-name}}/docs/search?api-version=2024-07-01
@@ -136,7 +154,89 @@ api-key: {{admin-api-key}}
 
 + `top` determines how many matches are returned in the response all-up. In this example, the response includes 10 results, assuming there are at least 10 matches in the merged results.
 
-## Hybrid search with filter
+---
+
+## Set maxTextRecallSize and countAndFacetMode
+
+[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
+
+A hybrid query can be tuned to control how much of each subquery contributes to the combined results. Setting `maxTextRecallSize` specifies how many BM25-ranked results are passed to the hybrid ranking model.
+
+If you use `maxTextRecallSize`, you might also want to set `CountAndFacetMode`. This parameter determines whether the `count` and `facets` should include all documents that matched the search query, or only those documents retrieved within the `maxTextRecallSize` window. The default value is "countAllResults".
+
+We recommend the latest preview REST API version [2025-05-01-preview](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-05-01-preview&preserve-view=true) for setting these options.
+
+> [!TIP]
+> Another approach for hybrid query tuning is [vector weighting](vector-search-how-to-query.md#vector-weighting), used to increase the importance of vector queries in the request.
+
+1. Use [Search - POST (preview)](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-05-01-preview&preserve-view=true) or [Search - GET (preview)](/rest/api/searchservice/documents/search-get?view=rest-searchservice-2025-05-01-preview&preserve-view=true) to specify preview parameters.
+
+1. Add a `hybridSearch` query parameter object to set the maximum number of documents recalled through the BM25-ranked results of a hybrid query. It has two properties:
+
+   + `maxTextRecallSize` specifies the number of BM25-ranked results to provide to the Reciprocal Rank Fusion (RRF) ranker used in hybrid queries. The default is 1,000. The maximum is 10,000.
+
+   + `countAndFacetMode` reports the counts for the BM25-ranked results (and for facets if you're using them). The default is all documents that match the query. Optionally, you can scope "count" to the `maxTextRecallSize`.
+
+1. Set `maxTextRecallSize`:
+
+   + Decrease `maxTextRecallSize` if vector similarity search is generally outperforming the text-side of the hybrid query.
+
+   + Increase `maxTextRecallSize` if you have a large index, and the default isn't capturing a sufficient number of results. With a larger BM25-ranked result set, you can also set `top`, `skip`, and `next` to retrieve portions of those results.
+
+The following REST examples show two use-cases for setting `maxTextRecallSize`. 
+
+The first example reduces `maxTextRecallSize` to 100, limiting the text side of the hybrid query to just 100 document. It also sets `countAndFacetMode` to include only those results from `maxTextRecallSize`.
+
+```http
+POST https://[service-name].search.windows.net/indexes/[index-name]/docs/search?api-version=2024-05-01-Preview 
+
+    { 
+      "vectorQueries": [ 
+        { 
+          "kind": "vector", 
+          "vector": [1.0, 2.0, 3.0], 
+          "fields": "my_vector_field", 
+          "k": 10 
+        } 
+      ], 
+      "search": "hello world", 
+      "hybridSearch": { 
+        "maxTextRecallSize": 100, 
+        "countAndFacetMode": "countRetrievableResults" 
+      } 
+    } 
+```
+
+The second example raises `maxTextRecallSize` to 5,000. It also uses top, skip, and next to pull results from large result sets. In this case, the request pulls in BM25-ranked results starting at position 1,500 through 2,000 as the text query contribution to the RRF composite result set.
+
+```http
+POST https://[service-name].search.windows.net/indexes/[index-name]/docs/search?api-version=2024-05-01-Preview 
+
+    { 
+      "vectorQueries": [ 
+        { 
+          "kind": "vector", 
+          "vector": [1.0, 2.0, 3.0], 
+          "fields": "my_vector_field", 
+          "k": 10 
+        } 
+      ], 
+      "search": "hello world",
+      "top": 500,
+      "skip": 1500,
+      "next": 500,
+      "hybridSearch": { 
+        "maxTextRecallSize": 5000, 
+        "countAndFacetMode": "countRetrievableResults" 
+      } 
+    } 
+```
+
+## Examples of hybrid queries
+
+This section has multiple query examples that illustrate hybrid query patterns.
+
+### Example: Hybrid search with filter
 
 This example adds a filter, which is applied to the `filterable` nonvector fields of the search index.
 
@@ -174,24 +274,24 @@ api-key: {{admin-api-key}}
 
 + When you postfilter query results, the number of results might be less than top-n.
 
-## Hybrid search with filters targeting vector subqueries (preview)
+### Example: Hybrid search with filters targeting vector subqueries (preview)
 
-Using [**2024-09-01-preview**](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true), you can override a global filter on the search request by applying a secondary filter that targets just the vector subqueries in a hybrid request.
+Using a [preview API](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-05-01-preview&preserve-view=true), you can override a global filter on the search request by applying a secondary filter that targets just the vector subqueries in a hybrid request.
 
 This feature provides fine-grained control by ensuring that filters only influence the vector search results, leaving keyword-based search results unaffected. 
 
 The targeted filter fully overrides the global filter, including any filters used for [security trimming](search-security-trimming-for-azure-search.md) or geospatial search.  In cases where global filters are required, such as security trimming, you must explicitly include these filters in both the top-level filter and in each vector-level filter to ensure security and other constraints are consistently enforced.
 
 To apply targeted vector filters:
 
-+ Use the [latest preview Search Documents REST API](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true#request-body) or an Azure SDK beta package that provides the feature.
++ Use the [latest preview Search Documents REST API](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-05-01-preview&preserve-view=true#request-body) or an Azure SDK beta package that provides the feature.
 
 + Modify a query request, adding a new `vectorQueries.filterOverride` parameter set to an [OData filter expression](search-query-odata-filter.md).
 
-Here's an example of hybrid query that adds a filter override. The global filter "Rating gt 3" is replaced at run time by the filterOvrride.
+Here's an example of hybrid query that adds a filter override. The global filter "Rating gt 3" is replaced at run time by the `filterOverride`.
 
 ```http
-POST https://{{search-service-name}}.search.windows.net/indexes/{{index-name}}/docs/search?api-version=2024-09-01=preview
+POST https://{{search-service-name}}.search.windows.net/indexes/{{index-name}}/docs/search?api-version=2025-05-01=preview
 
 {
     "vectorQueries": [
@@ -218,7 +318,7 @@ POST https://{{search-service-name}}.search.windows.net/indexes/{{index-name}}/d
 }
 ```
 
-## Semantic hybrid search
+### Example: Semantic hybrid search
 
 Assuming that you [have semantic ranker](semantic-how-to-enable-disable.md) and your index definition includes a [semantic configuration](semantic-how-to-query-request.md), you can formulate a query that includes vector search and keyword search, with semantic ranking over the merged result set. Optionally, you can add captions and answers. 
 
@@ -261,7 +361,7 @@ api-key: {{admin-api-key}}
 
 + "captions" and "answers" are optional. Values are extracted from verbatim text in the results. An answer is only returned if the results include content having the characteristics of an answer to the query.
 
-## Semantic hybrid search with filter
+### Example: Semantic hybrid search with filter
 
 Here's the last query in the collection. It's the same semantic hybrid query as the previous example, but with a filter.
 
@@ -304,90 +404,18 @@ api-key: {{admin-api-key}}
 
 + Postfilter is applied after query execution. If k=50 returns 50 matches on the vector query side, followed by a post-filter applied to the 50 matches, your results are reduced by the number of documents that meet filter criteria. This leaves you with fewer than 50 documents to pass to semantic ranker. Keep this in mind if you're using semantic ranking. The semantic ranker works best if it has 50 documents as input.
 
-## Set maxTextRecallSize and countAndFacetMode
-
-[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
-
-This section explains how to adjust the inputs to a hybrid query by controlling the amount BM25-ranked results that flow to the hybrid ranking model. Controlling over the BM25-ranked input gives you more options for relevance tuning in hybrid scenarios.
-
-We recommend preview REST API version [2024-05-01-preview](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-05-01-preview&preserve-view=true).
-
-> [!TIP]
-> Another option to consider is a supplemental or replacement technique, is [vector weighting](vector-search-how-to-query.md#vector-weighting), which increases the importance of vector queries in the request.
-
-1. Use [Search - POST](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-05-01-preview&preserve-view=true) or [Search - GET](/rest/api/searchservice/documents/search-get?view=rest-searchservice-2024-05-01-preview&preserve-view=true) in 2024-05-01-preview to specify these parameters.
-
-1. Add a `hybridSearch` query parameter object to set the maximum number of documents recalled through the BM25-ranked results of a hybrid query. It has two properties:
-
-   + `maxTextRecallSize` specifies the number of BM25-ranked results to provide to the Reciprocal Rank Fusion (RRF) ranker used in hybrid queries. The default is 1,000. The maximum is 10,000.
-
-   + `countAndFacetMode` reports the counts for the BM25-ranked results (and for facets if you're using them). The default is all documents that match the query. Optionally, you can scope "count" to the `maxTextRecallSize`.
-
-1. Reduce `maxTextRecallSize` if vector similarity search is generally outperforming the text-side of the hybrid query.
-
-1. Raise `maxTextRecallSize` if you have a large index, and the default isn't capturing a sufficient number of results. With a larger BM25-ranked result set, you can also set `top`, `skip`, and `next` to retrieve portions of those results.
-
-The following REST examples show two use-cases for setting `maxTextRecallSize`. 
-
-The first example reduces `maxTextRecallSize` to 100, limiting the text side of the hybrid query to just 100 document. It also sets `countAndFacetMode` to include only those results from `maxTextRecallSize`.
-
-```http
-POST https://[service-name].search.windows.net/indexes/[index-name]/docs/search?api-version=2024-05-01-Preview 
-
-    { 
-      "vectorQueries": [ 
-        { 
-          "kind": "vector", 
-          "vector": [1.0, 2.0, 3.0], 
-          "fields": "my_vector_field", 
-          "k": 10 
-        } 
-      ], 
-      "search": "hello world", 
-      "hybridSearch": { 
-        "maxTextRecallSize": 100, 
-        "countAndFacetMode": "countRetrievableResults" 
-      } 
-    } 
-```
-
-The second example raises `maxTextRecallSize` to 5,000. It also uses top, skip, and next to pull results from large result sets. In this case, the request pulls in BM25-ranked results starting at position 1,500 through 2,000 as the text query contribution to the RRF composite result set.
-
-```http
-POST https://[service-name].search.windows.net/indexes/[index-name]/docs/search?api-version=2024-05-01-Preview 
-
-    { 
-      "vectorQueries": [ 
-        { 
-          "kind": "vector", 
-          "vector": [1.0, 2.0, 3.0], 
-          "fields": "my_vector_field", 
-          "k": 10 
-        } 
-      ], 
-      "search": "hello world",
-      "top": 500,
-      "skip": 1500,
-      "next": 500,
-      "hybridSearch": { 
-        "maxTextRecallSize": 5000, 
-        "countAndFacetMode": "countRetrievableResults" 
-      } 
-    } 
-```
-
 ## Configure a query response
 
-When you're setting up the hybrid query, think about the response structure. The response is a flattened rowset. Parameters on the query determine which fields are in each row and how many rows are in the response. The search engine ranks the matching documents and returns the most relevant results.
+When you're setting up the hybrid query, think about the response structure. The search engine ranks the matching documents and returns the most relevant results. The response is a flattened rowset. Parameters on the query determine which fields are in each row and how many rows are in the response. 
 
 ### Fields in a response
 
 Search results are composed of `retrievable` fields from your search index. A result is either:
 
 + All `retrievable` fields (a REST API default).
-+ Fields explicitly listed in a "select" parameter on the query. 
++ Fields explicitly listed in a `select` parameter on the query. 
 
-The examples in this article used a "select" statement to specify text (nonvector) fields in the response.
+The examples in this article used a `select` statement to specify text (nonvector) fields in the response.
 
 > [!NOTE]
 > Vectors aren't reverse engineered into human readable text, so avoid returning them in the response. Instead, choose nonvector fields that are representative of the search document. For example, if the query targets a "DescriptionVector" field, return an equivalent text field if you have one ("Description") in the response.
@@ -400,22 +428,22 @@ A query might match to any number of documents, as many as all of them if the se
 + `"k": n` results for vector-only queries
 + `"top": n` results for hybrid queries (with or without semantic) that include a "search" parameter
 
-Both "k" and "top" are optional. Unspecified, the default number of results in a response is 50. You can set "top" and "skip" to [page through more results](search-pagination-page-layout.md#paging-results) or change the default.
+Both `k` and `top` are optional. Unspecified, the default number of results in a response is 50. You can set `top` and `skip` to [page through more results](search-pagination-page-layout.md#paging-results) or change the default.
 
 > [!NOTE]
-> If you're using hybrid search in 2024-05-01-preview API, you can control the number of results from the keyword query using [maxTextRecallSize](#set-maxtextrecallsize-and-countandfacetmode). Combine this with a setting for "k" to control the representation from each search subsystem (keyword and vector).
+> If you're using hybrid search in 2024-05-01-preview API, you can control the number of results from the keyword query using [maxTextRecallSize](#set-maxtextrecallsize-and-countandfacetmode). Combine this with a setting for `k` to control the representation from each search subsystem (keyword and vector).
 
-#### Semantic ranker results
+### Semantic ranker results
 
 > [!NOTE]
 > The semantic ranker can take up to 50 results. 
 
-If you're using semantic ranker in 2024-05-01-preview API, it's a best practice to set "k" and "maxTextRecallSize" to sum to at least 50 total.  You can then restrict the results returned to the user with the "top" parameter. 
+If you're using semantic ranker in 2024-05-01-preview or later, it's a best practice to set `k` and `maxTextRecallSize` to sum to at least 50 total.  You can then restrict the results returned to the user with the `top` parameter. 
 
 If you're using semantic ranker in previous APIs do the following:
 
-+ if doing keyword-only search (no vector) set "top" to 50
-+ if doing hybrid search set "k" to 50, to ensure that the semantic ranker gets at least 50 results. 
++ For keyword-only search (no vectors) set `top` to 50
++ For hybrid search set `k` to 50, to ensure that the semantic ranker gets at least 50 results. 
 
 ### Ranking
 
@@ -453,6 +481,6 @@ In this section, compare the responses between single vector search and simple h
 }
 ```
 
-## Next steps
+## Next step
 
-As a next step, we recommend reviewing the demo code for [Python](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-python), [C#](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-dotnet) or [JavaScript](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-javascript).
+We recommend reviewing vector demo code for [Python](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-python), [C#](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-dotnet) or [JavaScript](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-javascript).

@@ -9,22 +9,22 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 05/27/2025
+ms.date: 07/21/2025
 ---
 
 # Hybrid search using vectors and full text in Azure AI Search
 
-Hybrid search is a single query request, configured for full text and vector search, that executes against a search index containing both searchable plain text content and generated embeddings. For query purposes, hybrid search is:
+Hybrid search is a single query request, configured for full text and vector queries, that executes against a search index containing both searchable plain text content and generated embeddings. For query purposes, hybrid search is:
 
 + A single query request that includes both `search` and `vectors` query parameters
 + Executing in parallel
-+ With merged results in the query response, scored using [Reciprocal Rank Fusion (RRF)](hybrid-search-ranking.md)
++ Merging results from each query using [Reciprocal Rank Fusion (RRF)](hybrid-search-ranking.md)
 
-This article explains the concepts, benefits, and limitations of hybrid search. Links at the end provide instructions and next steps. You can also watch this [embedded video](#why-choose-hybrid-search) for an explanation of how hybrid retrieval contributes to high quality RAG apps.
+This article explains the concepts, benefits, and limitations of hybrid search. Links at the end provide instructions and next steps. You can also watch this [embedded video](#why-choose-hybrid-search) for an explanation of how hybrid retrieval contributes to high quality generative search applications.
 
 ## How does hybrid search work?
 
-In Azure AI Search, vector fields containing embeddings can live alongside textual and numerical fields, allowing you to formulate hybrid queries that execute in parallel. Hybrid queries can take advantage of existing text-based functionality like filtering, faceting, sorting, scoring profiles, and [semantic ranking](semantic-search-overview.md) on your text fields, while executing a similarity search against vectors, all in a single search request.
+In a search index, vector fields containing embeddings coexist with textual and numerical fields, allowing you to formulate hybrid queries that execute in parallel. Hybrid queries can take advantage of existing text-based functionality like filtering, faceting, sorting, scoring profiles, and [semantic ranking](semantic-search-overview.md) on your text fields, while executing a similarity search against vectors, all in a single search request.
 
 Hybrid search combines results from both full text and vector queries, which use different ranking functions such as BM25 for text, and Hierarchical Navigable Small World (HNSW) and exhaustive K Nearest Neighbors (eKNN) for vectors. A [Reciprocal Rank Fusion (RRF)](hybrid-search-ranking.md) algorithm merges the results. The query response provides just one result set, using RRF to rank the unified results.
 

@@ -9,17 +9,17 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: conceptual
-ms.date: 03/11/2025
+ms.date: 07/21/2025
 ---
 
 # Relevance scoring in hybrid search using Reciprocal Rank Fusion (RRF)
 
-Reciprocal Rank Fusion (RRF) is an algorithm that evaluates the search scores from multiple, previously ranked results to produce a unified result set. In Azure AI Search, RRF is used whenever there are two or more queries that execute in parallel. Each query produces a ranked result set, and RRF merges and homogenizes the rankings into a single result set for the query response. Examples of scenarios where RRF is always used include [*hybrid search*](hybrid-search-overview.md) and multiple vector queries executing concurrently. 
+Reciprocal Rank Fusion (RRF) is an algorithm that evaluates the search scores from multiple, previously ranked results to produce a unified result set. In Azure AI Search, RRF is used when two or more queries execute in parallel. Namely, for [hybrid queries](hybrid-search-overview.md) and for [multiple vector queries](vector-search-overview.md). Each individual query produces a ranked result set, and RRF merges and homogenizes the rankings into a single result set for the query response. 
 
 RRF is based on the concept of *reciprocal rank*, which is the inverse of the rank of the first relevant document in a list of search results. The goal of the technique is to take into account the position of the items in the original rankings, and give higher importance to items that are ranked higher in multiple lists. This can help improve the overall quality and reliability of the final ranking, making it more useful for the task of fusing multiple ordered search results.
 
 > [!NOTE]
-> New in [**2024-09-01-preview**](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true) is the ability to deconstruct an RRF-ranked search score into its component subscores. This gives you transparency into all-up score composition. For more information, see [unpack search scores (preview)](#unpack-a-search-score-into-subscores-preview) in this article.
+> [Preview APIs](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-05-01-preview&preserve-view=true) can deconstruct an RRF-ranked search score into its component subscores. This gives you transparency into all-up score composition. For more information, see [unpack search scores (preview)](#unpack-a-search-score-into-subscores-preview) in this article.
 
 ## How RRF ranking works
 
@@ -62,20 +62,20 @@ Semantic ranking occurs after RRF merging of results. Its score (`@search.rerank
 
 ## Unpack a search score into subscores (preview)
 
-Using [**2024-09-01-preview**](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true), you can deconstruct a search score to view its subscores.
+Using the [latest preview API version](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-05-01-preview&preserve-view=true), you can deconstruct a search score to view its subscores.
 
 For vector queries, this information can help you determine an appropriate value for [vector weighting](vector-search-how-to-query.md#vector-weighting) or [setting minimum thresholds](vector-search-how-to-query.md#set-thresholds-to-exclude-low-scoring-results-preview).
 
 To get subscores:
 
-+ Use the [latest preview Search Documents REST API](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true#request-body) or an Azure SDK beta package that provides the feature.
++ Use the [latest preview Search Documents REST API](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2025-05-01-preview&preserve-view=true#request-body) or an Azure SDK beta package that provides the feature.
 
 + Modify a query request, adding a new `debug` parameter set to either `vector`, `semantic` if using semantic ranker, or `all`.
 
 Here's an example of hybrid query that returns subscores in debug mode:
 
 ```http
-POST https://{{search-service-name}}.search.windows.net/indexes/{{index-name}}/docs/search?api-version=2024-09-01=preview
+POST https://{{search-service-name}}.search.windows.net/indexes/{{index-name}}/docs/search?api-version=2025-05-01=preview
 
 {
     "vectorQueries": [
@@ -115,7 +115,7 @@ POST https://{{search-service-name}}.search.windows.net/indexes/{{index-name}}/d
 
 ## Weighted scores
 
-Using [**2024-07-01**](/rest/api/searchservice/documents/search-post) and newer preview API versions, you can [weight vector queries](vector-search-how-to-query.md#vector-weighting) to increase or decrease their importance in a hybrid query.
+Using the [stable REST API version](/rest/api/searchservice/documents/search-post) and newer preview API versions, you can [weight vector queries](vector-search-how-to-query.md#vector-weighting) to increase or decrease their importance in a hybrid query.
 
 Recall that when computing RRF for a certain document, the search engine looks at the rank of that document for each result set where it shows up. Assume a document shows up in three separate search results, where the results are from two vector queries and one text BM25-ranked query. The position of the document varies in each result.
 

@@ -148,7 +148,7 @@ Here are some tips for maximizing relevance and recall:
 
   + [Semantic ranker](semantic-ranking.md) that re-ranks an initial results set, using semantic models from Bing to reorder results for a better semantic fit to the original query.
 
-  + Query parameters for fine-tuning. You can [bump up the importance of vector queries](vector-search-how-to-query.md#vector-weighting) or [adjust the amount of BM25-ranked results](vector-search-how-to-query.md#maxtextsizerecall-for-hybrid-search-preview) in a hybrid query. You can also [set minimum thresholds to exclude low scoring results](vector-search-how-to-query.md#set-thresholds-to-exclude-low-scoring-results-preview) from a vector query.
+  + Query parameters for fine-tuning. You can [boost the importance of vector queries](vector-search-how-to-query.md#vector-weighting) or [adjust the amount of BM25-ranked results](hybrid-search-how-to-query.md#set-maxtextrecallsize-and-countandfacetmode) in a hybrid query response. You can also [set minimum thresholds to exclude low scoring results](vector-search-how-to-query.md#set-thresholds-to-exclude-low-scoring-results-preview) from a vector query.
 
 In comparison and benchmark testing, hybrid queries with text and vector fields, supplemented with semantic ranking, produce the most relevant results.
 

@@ -44,7 +44,7 @@ Preview features are removed from this list if they're retired or transition to
 | [**Rescoring options for compressed vectors**](vector-search-how-to-quantization.md) | Relevance (scoring) | You can set options to rescore with original vectors instead of compressed vectors. Applies to HNSW and exhaustive KNN vector algorithms, using binary and scalar compression. | [Create or Update Index (preview)](/rest/api/searchservice/indexes/create-or-update?view=rest-searchservice-2024-09-01-preview&preserve-view=true).|
 | [**Lower the dimension requirements for MRL-trained text embedding models on Azure OpenAI**](vector-search-how-to-truncate-dimensions.md) | Index | Text-embedding-3-small and Text-embedding-3-large are trained using Matryoshka Representation Learning (MRL). This allows you to truncate the embedding vectors to fewer dimensions, and adjust the balance between vector index size usage and retrieval quality. A new `truncationDimension` provides the MRL behaviors as an extra parameter in a vector compression configuration. This can only be configured for new vector fields. | [Create or Update Index (preview)](/rest/api/searchservice/indexes/create-or-update?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
 | [**Unpack `@search.score` to view subscores in hybrid search results**](hybrid-search-ranking.md#unpack-a-search-score-into-subscores-preview) | Relevance (scoring) | You can investigate Reciprocal Rank Fusion (RRF) ranked results by viewing the individual query subscores of the final merged and scored result. A new `debug` property unpacks the search score. `QueryResultDocumentSubscores`, `QueryResultDocumentRerankerInput`, and `QueryResultDocumentSemanticField` provide the extra detail. | [Search Documents (preview)](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
-| [**Target filters in a hybrid search to just the vector queries**](hybrid-search-how-to-query.md#hybrid-search-with-filters-targeting-vector-subqueries-preview) | Query | A filter on a hybrid query involves all subqueries on the request, regardless of type. You can override the global filter to scope the filter to a specific subquery. A new `filterOverride` parameter provides the behaviors. | [Search Documents (preview)](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
+| [**Target filters in a hybrid search to just the vector queries**](hybrid-search-how-to-query.md#example-hybrid-search-with-filters-targeting-vector-subqueries-preview) | Query | A filter on a hybrid query involves all subqueries on the request, regardless of type. You can override the global filter to scope the filter to a specific subquery. A new `filterOverride` parameter provides the behaviors. | [Search Documents (preview)](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
 | [**Text Split skill (token chunking)**](cognitive-search-skill-textsplit.md) | Applied AI (skills) | This skill has new parameters that improve data chunking for embedding models. A new `unit` parameter lets you specify token chunking. You can now chunk by token length, setting the length to a value that makes sense for your embedding model. You can also specify the tokenizer and any tokens that shouldn't be split during data chunking. | [Create or Update Skillset (preview)](/rest/api/searchservice/skillsets/create-or-update?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
 | [**Azure AI Vision multimodal embedding skill**](cognitive-search-skill-vision-vectorize.md) | Applied AI (skills) | A new skill type that calls Azure AI Vision multimodal API to generate embeddings for text or images during indexing. | [Create or Update Skillset (preview)](/rest/api/searchservice/skillsets/create-or-update?view=rest-searchservice-2024-05-01-preview&preserve-view=true). |
 | [**Azure Machine Learning (AML) skill**](cognitive-search-aml-skill.md) | Applied AI (skills) | AML skill integrates an inferencing endpoint from Azure Machine Learning. In previous preview APIs, it supports connections to deployed custom models in an AML workspace. Starting in the 2024-05-01-preview, you can use this skill in workflows that connect to embedding models in the Azure AI Foundry model catalog. It's also available in the Azure portal, in skillset design, assuming Azure AI Search and Azure Machine Learning services are deployed in the same subscription. | [Create or Update Skillset (preview)](/rest/api/searchservice/skillsets/create-or-update?view=rest-searchservice-2024-05-01-preview&preserve-view=true). |

@@ -7,7 +7,7 @@ ms.author: haileytapia
 ms.service: azure-ai-search
 ms.update-cycle: 90-days
 ms.topic: quickstart
-ms.date: 07/16/2025
+ms.date: 07/22/2025
 ms.custom:
   - references_regions
 ---
@@ -52,7 +52,7 @@ For content embedding, you can choose either image verbalization (followed by te
 | Method | Description | Supported models |
 |--|--|--|
 | Image verbalization | Uses an LLM to generate natural-language descriptions of images, and then uses an embedding model to vectorize plain text and verbalized images.<br><br>Requires an [Azure OpenAI resource](/azure/ai-services/openai/how-to/create-resource) <sup>1, 2</sup> or [Azure AI Foundry project](/azure/ai-foundry/how-to/create-projects).<br><br>For text vectorization, you can also use an [Azure AI services multi-service resource](/azure/ai-services/multi-service-resource#azure-ai-multi-services-resource-for-azure-ai-search-skills) <sup>3</sup> in a [supported region](cognitive-search-skill-vision-vectorize.md). | LLMs:<br>GPT-4o<br>GPT-4o-mini<br>phi-4 <sup>4</sup><br><br>Embedding models:<br>text-embedding-ada-002<br>text-embedding-3-small<br>text-embedding-3-large |
-| Multimodal embeddings | Uses an embedding model to directly vectorize both text and images.<br><br>Requires an [Azure AI Foundry project](/azure/ai-foundry/how-to/create-projects) or [Azure AI services multi-service resource](/azure/ai-services/multi-service-resource#azure-ai-multi-services-resource-for-azure-ai-search-skills) <sup>3</sup> in a [supported region](cognitive-search-skill-vision-vectorize.md). | Cohere-embed-v3-english<br>Cohere-embed-v3-multilingual<br>Cohere-embed-v4 <sup>5</sup> |
+| Multimodal embeddings | Uses an embedding model to directly vectorize both text and images.<br><br>Requires an [Azure AI Foundry hub-based project](/azure/ai-foundry/how-to/create-projects) or [Azure AI services multi-service resource](/azure/ai-services/multi-service-resource#azure-ai-multi-services-resource-for-azure-ai-search-skills) <sup>3</sup> in a [supported region](cognitive-search-skill-vision-vectorize.md). | Cohere-embed-v3-english<br>Cohere-embed-v3-multilingual<br>Cohere-embed-v4 <sup>5</sup> |
 
 <sup>1</sup> The endpoint of your Azure OpenAI resource must have a [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains), such as `https://my-unique-name.openai.azure.com`. If you created your resource in the [Azure portal](https://portal.azure.com/), this subdomain was automatically generated during resource setup.
 
@@ -128,6 +128,9 @@ On your Azure OpenAI resource:
 
 The Azure AI Foundry model catalog provides LLMs for image verbalization and embedding models for text and image vectorization. Your search service requires access to call the [GenAI Prompt skill](cognitive-search-skill-genai-prompt.md) and [AML skill](cognitive-search-aml-skill.md).
 
+> [!NOTE]
+> If you're using a hub-based project for multimodal embeddings, skip this step. The wizard requires key-based authentication in this scenario.
+
 On your Azure AI Foundry project:
 
 + Assign **Azure AI Project Manager** to your [search service identity](search-howto-managed-identities-data-sources.md#create-a-system-managed-identity).
@@ -197,7 +200,7 @@ Azure AI Search requires a connection to a data source for content ingestion and
 
 To connect to your data:
 
-1. On the **Connect to your data** page, specify your Azure subscription.
+1. On the **Connect to your data** page, select your Azure subscription.
 
 1. Select the storage account and container to which you uploaded the sample data.
 
@@ -233,7 +236,7 @@ To use the Document Layout skill:
 
    :::image type="content" source="media/search-get-started-portal-images/extract-your-content-doc-intelligence.png" alt-text="Screenshot of the wizard page with Azure AI Document Intelligence selected for content extraction." border="true" lightbox="media/search-get-started-portal-images/extract-your-content-doc-intelligence.png":::
 
-1. Specify your Azure subscription and multi-service resource.
+1. Select your Azure subscription and multi-service resource.
 
 1. For the authentication type, select **System assigned identity**.
 
@@ -267,7 +270,7 @@ To use the skills for image verbalization:
 
    1. For the kind, select your LLM provider: **Azure OpenAI** or **AI Foundry Hub catalog models**.
 
-   1. Specify your Azure subscription, resource, and LLM deployment.
+   1. Select your Azure subscription, resource, and LLM deployment.
 
    1. For the authentication type, select **System assigned identity**.
 
@@ -279,7 +282,7 @@ To use the skills for image verbalization:
 
    1. For the kind, select your model provider: **Azure OpenAI**, **AI Foundry Hub catalog models**, or **AI Vision vectorization**.
 
-   1. Specify your Azure subscription, resource, and embedding model deployment.
+   1. Select your Azure subscription, resource, and embedding model deployment (if applicable).
 
    1. For the authentication type, select **System assigned identity**.
 
@@ -305,7 +308,9 @@ To use the skills for multimodal embeddings:
 
    If Azure AI Vision is unavailable, make sure your search service and multi-service resource are both in a [region that supports the Azure AI Vision multimodal APIs](/azure/ai-services/computer-vision/how-to/image-retrieval).
 
-1. Specify your Azure subscription, resource, and embedding model deployment.
+1. Select your Azure subscription, resource, and embedding model deployment (if applicable).
+
+1. If you're using Azure AI Vision, select **System assigned identity** for the authentication type. Otherwise, leave it as **API key**.
 
 1. Select the checkbox that acknowledges the billing effects of using this resource.
 
@@ -321,7 +326,7 @@ The next step is to send images extracted from your documents to Azure Storage.
 
 To store the extracted images:
 
-1. On the **Image output** page, specify your Azure subscription.
+1. On the **Image output** page, select your Azure subscription.
 
 1. Select the storage account and blob container you created to store the images.
 

@@ -10,7 +10,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: quickstart
-ms.date: 07/17/2025
+ms.date: 07/22/2025
 ---
 
 # Quickstart: Vectorize text in the Azure portal
@@ -185,16 +185,16 @@ This section points you to the content that works for this quickstart. Before yo
 
 ## Prepare embedding model
 
-The wizard can use embedding models deployed from Azure OpenAI, Azure AI Vision, or from the model catalog in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs). Before you proceed, make sure you completed the prerequisites for [role-based access](#role-based-access).
+The wizard can use embedding models deployed from Azure OpenAI, Azure AI Vision, or the Azure AI Foundry model catalog. Before you proceed, make sure you completed the prerequisites for [role-based access](#role-based-access).
 
 ### [Azure OpenAI](#tab/model-aoai)
 
 The wizard supports text-embedding-ada-002, text-embedding-3-large, and text-embedding-3-small. Internally, the wizard calls the [AzureOpenAIEmbedding skill](cognitive-search-skill-azure-openai-embedding.md) to connect to Azure OpenAI.
 
-1. Sign in to the [Azure portal](https://portal.azure.com/) and select your Azure OpenAI resource.
-
 1. To assign roles:
 
+   1. Sign in to the [Azure portal](https://portal.azure.com/) and select your Azure OpenAI resource.
+
    1. From the left pane, select **Access control (IAM)**.
 
    1. Select **Add** > **Add role assignment**.
@@ -215,54 +215,37 @@ The wizard supports text-embedding-ada-002, text-embedding-3-large, and text-emb
 
 ### [Azure AI Vision](#tab/model-ai-vision)
 
-The wizard supports Azure AI Vision image retrieval through multimodal embeddings (version 4.0). Internally, the wizard calls the [multimodal embeddings skill](cognitive-search-skill-vision-vectorize.md) to connect to Azure AI Vision.
+The wizard supports text and image retrieval through the Azure AI Vision multimodal APIs, which are built into your Azure AI multi-service resource. Internally, the wizard calls the [Azure AI Vision multimodal embeddings skill](cognitive-search-skill-vision-vectorize.md) to make the connection.
 
-1. Sign in to the [Azure portal](https://portal.azure.com/) and select your Azure AI multi-service resource.
-
-1. To assign roles:
+Since no model deployment is required, you only need to assign roles to your search service identity.
 
-   1. From the left pane, select **Access control (IAM)**.
+To assign roles:
 
-   1. Select **Add** > **Add role assignment**.
+1. Sign in to the [Azure portal](https://portal.azure.com/) and select your multi-service resource.
 
-   1. Under **Job function roles**, select **Cognitive Services User**, and then select **Next**.
+1. From the left pane, select **Access control (IAM)**.
 
-   1. Under **Members**, select **Managed identity**, and then select **Select members**.
+1. Select **Add** > **Add role assignment**.
 
-   1. Select your subscription and the managed identity of your search service.
+1. Under **Job function roles**, select **Cognitive Services User**, and then select **Next**.
 
-The multimodal embeddings are built into your Azure AI multi-service resource, so there's no model deployment step. You should now be able to select the Azure AI Vision vectorizer in the **Import and vectorize data wizard**.
+1. Under **Members**, select **Managed identity**, and then select **Select members**.
 
-> [!NOTE]
-> If you can't select the Azure AI Vision vectorizer, make sure you have an Azure AI Vision resource in a supported region. Also make sure the managed identity of your search service has **Cognitive Services User** permissions.
+1. Select your subscription and the managed identity of your search service.
 
 ### [Azure AI Foundry model catalog](#tab/model-catalog)
 
 The wizard supports Azure, Cohere, and Facebook embedding models in the Azure AI Foundry model catalog, but it doesn't currently support the OpenAI CLIP models. Internally, the wizard calls the [AML skill](cognitive-search-aml-skill.md) to connect to the catalog.
 
-For the model catalog, you should have an [Azure AI Foundry project](/azure/ai-foundry/how-to/create-projects) with a [hub that's connected to an Azure OpenAI resource and an Azure AI Search service](/azure/ai-foundry/how-to/create-projects#create-a-project).
-
-1. Sign in to the [Azure portal](https://portal.azure.com/) and select your Azure OpenAI resource.
-
-1. To assign roles:
+To complete these steps, you must have a [hub-based project](/azure/ai-foundry/how-to/create-projects) in Azure AI Foundry. Currently, hub-based projects support API keys instead of managed identities for authentication, so there's no role assignment step. You only need to deploy a model from the catalog.
 
-   1. From the left pane, select **Access control (IAM)**.
+To deploy an embedding model:
 
-   1. Select **Add** > **Add role assignment**.
+1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) and select your hub-based project.
 
-   1. Under **Job function roles**, select **Cognitive Services User**, and then select **Next**.
+1. From the left pane, select **Model catalog**.
 
-   1. Under **Members**, select **Managed identity**, and then select **Select members**.
-
-   1. Select your subscription and the managed identity of your search service.
-
-1. To deploy an embedding model:
-
-   1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) and select your project.
-
-   1. From the left pane, select **Model catalog**.
-
-   1. Deploy a [supported embedding model](#supported-embedding-models).
+1. Deploy a [supported embedding model](#supported-embedding-models).
 
 ---
 
@@ -284,39 +267,33 @@ To start the wizard for vector search:
 
 ## Connect to your data
 
-The next step is to connect to a data source to use for the search index.
+In this step, you connect Azure AI Search to a [supported data source](#supported-data-sources) for content ingestion and indexing.
 
 ### [Azure Blob Storage](#tab/connect-data-storage)
 
-1. On the **Connect to your data** page, specify the Azure subscription.
+1. On the **Connect to your data** page, select your Azure subscription.
 
 1. Select the storage account and container that provide the sample data.
 
-1. If you enabled soft delete and optionally added custom metadata in [Prepare sample data](#prepare-sample-data), select the **Enable deletion tracking** checkbox.
+1. If you enabled soft delete and added custom metadata in [Prepare sample data](#prepare-sample-data), select the **Enable deletion tracking** checkbox.
 
    + On subsequent indexing runs, the search index is updated to remove any search documents based on soft-deleted blobs on Azure Storage.
 
    + Blobs support either **Native blob soft delete** or **Soft delete using custom metadata**.
 
    + If you configured your blobs for soft delete, provide the metadata property name-value pair. We recommend **IsDeleted**. If **IsDeleted** is set to **true** on a blob, the indexer drops the corresponding search document on the next indexer run.
 
-   The wizard doesn't check Azure Storage for valid settings or throw an error if the requirements aren't met. Instead, deletion detection doesn't work, and your search index is likely to collect orphaned documents over time.
-
-   :::image type="content" source="media/search-get-started-portal-import-vectors/data-source-blob.png" alt-text="Screenshot of the data source page with deletion detection options.":::
-
-1. Select the **Authenticate using managed identity** checkbox.
-
-   + For the type of managed identity, select **System-assigned**.
+   + The wizard doesn't check Azure Storage for valid settings or throw an error if the requirements aren't met. Instead, deletion detection doesn't work, and your search index is likely to collect orphaned documents over time.
 
-   + The identity should have a **Storage Blob Data Reader** role on Azure Storage.
+1. Select the **Authenticate using managed identity** checkbox. Leave the identity type as **System-assigned**.
 
-   + Don't skip this step. A connection error occurs during indexing if the wizard can't connect to Azure Storage.
+   :::image type="content" source="media/search-get-started-portal-import-vectors/data-source-blob.png" alt-text="Screenshot of the data source page with deletion detection options." lightbox="media/search-get-started-portal-import-vectors/data-source-blob.png":::
 
 1. Select **Next**.
 
 ### [ADLS Gen2](#tab/connect-data-adlsgen2)
 
-1. On the **connect to your data** page, specify the Azure subscription.
+1. On the **Connect to your data** page, select your Azure subscription.
 
 1. Select the storage account and container that provide the sample data.
 
@@ -328,23 +305,17 @@ The next step is to connect to a data source to use for the search index.
 
    + Provide the metadata property you created for deletion detection. We recommend **IsDeleted**. If **IsDeleted** is set to **true** on a blob, the indexer drops the corresponding search document on the next indexer run.
 
-   The wizard doesn't check Azure Storage for valid settings or throw an error if the requirements aren't met. Instead, deletion detection doesn't work, and your search index is likely to collect orphaned documents over time.
-
-   :::image type="content" source="media/search-get-started-portal-import-vectors/data-source-data-lake-storage.png" alt-text="Screenshot of the data source page with deletion detection options.":::
-
-1. Select the **Authenticate using managed identity** checkbox.
-
-   + For the type of managed identity, select **System-assigned**.
+      The wizard doesn't check Azure Storage for valid settings or throw an error if the requirements aren't met. Instead, deletion detection doesn't work, and your search index is likely to collect orphaned documents over time.
 
-   + The identity should have a **Storage Blob Data Reader** role on Azure Storage.
+1. Select the **Authenticate using managed identity** checkbox. Leave the identity type as **System-assigned**.
 
-   + Don't skip this step. A connection error occurs during indexing if the wizard can't connect to Azure Storage.
+   :::image type="content" source="media/search-get-started-portal-import-vectors/data-source-data-lake-storage.png" alt-text="Screenshot of the data source page with deletion detection options." lightbox="media/search-get-started-portal-import-vectors/data-source-data-lake-storage.png":::
 
 1. Select **Next**.
 
 ### [OneLake](#tab/connect-data-onelake)
 
-1. On the **connect to your data** page, select **Lakehouse URL** for the connection type.
+1. On the **Connect to your data** page, select **Lakehouse URL** for the connection type.
 
 1. Paste the URL you copied in [Prepare sample data](#prepare-sample-data).
 
@@ -354,15 +325,13 @@ The next step is to connect to a data source to use for the search index.
 
 ### [Logic Apps](#tab/connect-logic-apps)
 
-The current preview adds support for Logic Apps connectors. For a list of supported connectors and operations:
-
-+ [Use a Logic Apps connector for indexer-based indexing](search-how-to-index-logic-apps-indexers.md)
+The current preview adds support for Logic Apps connectors. For a list of supported connectors and operations, see [Use a Logic Apps connector for indexer-based indexing](search-how-to-index-logic-apps-indexers.md).
 
 ---
 
 ## Vectorize your text
 
-In this step, you specify an embedding model to vectorize chunked data. Chunking is built in and nonconfigurable. The effective settings are:
+During this step, the wizard uses your chosen [embedding model](#supported-embedding-models) to vectorize chunked data. Chunking is built in and nonconfigurable. The effective settings are:
 
 ```json
 "textSplitMode": "pages",
@@ -372,60 +341,98 @@ In this step, you specify an embedding model to vectorize chunked data. Chunking
 "unit": "characters"
 ```
 
-1. On the **Vectorize your text** page, select the source of your embedding model:
+### [Azure OpenAI](#tab/vectorize-text-aoai)
+
+1. On the **Vectorize your text** page, select **Azure OpenAI** for the kind.
 
-   + Azure OpenAI
+1. Select your Azure subscription.
 
-   + Azure AI Foundry model catalog
+1. Select your Azure OpenAI resource, and then select the model you deployed in [Prepare embedding model](#prepare-embedding-model).
+
+1. For the authentication type, select **System assigned identity**.
 
-   + Azure AI Vision (via an [Azure AI services multi-service resource](/azure/ai-services/multi-service-resource#azure-ai-multi-services-resource-for-azure-ai-search-skills) in the same region as Azure AI Search)
+1. Select the checkbox that acknowledges the billing effects of using these resources.
 
-1. Specify the Azure subscription.
+   :::image type="content" source="media/search-get-started-portal-import-vectors/vectorize-text-aoai.png" alt-text="Screenshot of the Vectorize your text page with Azure OpenAI in the wizard." lightbox="media/search-get-started-portal-import-vectors/vectorize-text-aoai.png":::
 
-1. Depending on your resource, make the following selection:
+1. Select **Next**.
 
-   + For Azure OpenAI, select the model you deployed in [Prepare embedding model](#prepare-embedding-model).
+### [Azure AI Vision](#tab/vectorize-text-ai-vision)
 
-   + For AI Foundry model catalog, select the model you deployed in [Prepare embedding model](#prepare-embedding-model).
+1. On the **Vectorize your text** page, select **AI Vision vectorization** for the kind.
 
-   + For AI Vision multimodal embeddings, select your multi-service resource.
+1. Select your Azure subscription and Azure AI multi-service resource.
 
 1. For the authentication type, select **System assigned identity**.
 
-   + The identity should have a **Cognitive Services User** role on the Azure AI services multi-service resource.
+1. Select the checkbox that acknowledges the billing effects of using these resources.
+
+   :::image type="content" source="media/search-get-started-portal-import-vectors/vectorize-text-ai-vision.png" alt-text="Screenshot of the Vectorize your text page with Azure AI Vision in the wizard." lightbox="media/search-get-started-portal-import-vectors/vectorize-text-ai-vision.png":::
+
+1. Select **Next**.
+
+### [Azure AI Foundry model catalog](#tab/vectorize-text-catalog)
+
+1. On the **Vectorize your text** page, select **AI Foundry Hub catalog models** for the kind.
+
+1. Select your Azure subscription.
+
+1. Select your hub-based project, and then select the model you deployed in [Prepare embedding model](#prepare-embedding-model).
+
+1. Leave the authentication type as **API key**.
 
 1. Select the checkbox that acknowledges the billing effects of using these resources.
 
-   :::image type="content" source="media/search-get-started-portal-import-vectors/vectorize-text.png" alt-text="Screenshot of the Vectorize your text page in the wizard.":::
+   :::image type="content" source="media/search-get-started-portal-import-vectors/vectorize-text-catalog.png" alt-text="Screenshot of the Vectorize your text page with the Azure AI Foundry model catalog in the wizard." lightbox="media/search-get-started-portal-import-vectors/vectorize-text-catalog.png":::
 
 1. Select **Next**.
 
+---
+
 ## Vectorize and enrich your images
 
 The health-plan PDFs include a corporate logo, but otherwise, there are no images. You can skip this step if you're using the sample documents.
 
-However, if you work with content that includes useful images, you can apply AI in two ways:
+However, if your content includes useful images, you can apply AI in one or both of the following ways:
 
-+ Use a supported image embedding model from the catalog or the Azure AI Vision multimodal embeddings API to vectorize images.
++ Use a supported image embedding model from the Azure AI Foundry model catalog or the Azure AI Vision multimodal embeddings API (via an Azure AI multi-service resource) to vectorize images.
 
-+ Use optical character recognition (OCR) to recognize text in images. This option invokes the [OCR skill](cognitive-search-skill-ocr.md) to read text from images.
++ Use optical character recognition (OCR) to extract text from images. This option invokes the [OCR skill](cognitive-search-skill-ocr.md).
 
-Azure AI Search and your Azure AI resource must be in the same region or configured for [keyless billing connections](cognitive-search-attach-cognitive-services.md).
+### [Vectorize images](#tab/vectorize-images)
 
-1. On the **Vectorize your images** page, specify the kind of connection the wizard should make. For image vectorization, the wizard can connect to embedding models in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) or Azure AI Vision.
+1. On the **Vectorize and enrich your images** page, select the **Vectorize images** checkbox.
 
-1. Specify the subscription.
+1. For the kind, select your model provider: **AI Foundry Hub catalog models** or **AI Vision vectorization**.
 
-1. For the Azure AI Foundry model catalog, specify the project and deployment. For more information, see [Prepare embedding models](#prepare-embedding-model).
+   If Azure AI Vision is unavailable, make sure your search service and multi-service resource are both in a [region that supports the Azure AI Vision multimodal APIs](/azure/ai-services/computer-vision/how-to/image-retrieval).
 
-1. (Optional) Crack binary images, such as scanned document files, and use [OCR](cognitive-search-skill-ocr.md) to recognize text.
+1. Select your Azure subscription, resource, and embedding model deployment (if applicable).
+
+1. If you're using Azure AI Vision, select **System assigned identity** for the authentication type. Otherwise, leave it as **API key**.
 
 1. Select the checkbox that acknowledges the billing effects of using these resources.
 
-   :::image type="content" source="media/search-get-started-portal-import-vectors/vectorize-images.png" alt-text="Screenshot of the Vectorize your images page in the wizard.":::
+   :::image type="content" source="media/search-get-started-portal-import-vectors/vectorize-images.png" alt-text="Screenshot of the Vectorize and enrich your images page in the wizard." lightbox="media/search-get-started-portal-import-vectors/vectorize-images.png":::
 
 1. Select **Next**.
 
+### [Extract text from images](#tab/extract-text-images)
+
+1. On the **Vectorize and enrich your images** page, select the **Extract text from images** checkbox.
+
+1. Select your Azure subscription and multi-service resource.
+
+1. For the authentication type, select **System assigned identity**.
+
+1. Select the checkbox that acknowledges the billing effects of using these resources.
+
+   :::image type="content" source="media/search-get-started-portal-import-vectors/extract-text-images.png" alt-text="Screenshot of the Extract text from images page in the wizard." lightbox="media/search-get-started-portal-import-vectors/extract-text-images.png":::
+
+1. Select **Next**.
+
+---
+
 ## Add semantic ranking
 
 On the **Advanced settings** page, you can optionally add [semantic ranking](semantic-search-overview.md) to rerank results at the end of query execution. Reranking promotes the most semantically relevant matches to the top.
@@ -492,11 +499,11 @@ Search Explorer accepts text strings as input and then vectorizes the text for v
 
 1. Select **Query options**, and then select **Hide vector values in search results**. This step makes the results more readable.
 
-   :::image type="content" source="media/search-get-started-portal-import-vectors/query-options.png" alt-text="Screenshot of the button for query options.":::
+   :::image type="content" source="media/search-get-started-portal-import-vectors/query-options.png" alt-text="Screenshot of the button for query options." lightbox="media/search-get-started-portal-import-vectors/query-options.png":::
 
 1. From the **View** menu, select **JSON view** so you can enter text for your vector query in the `text` vector query parameter.
 
-   :::image type="content" source="media/search-get-started-portal-import-vectors/select-json-view.png" alt-text="Screenshot of the menu command for opening the JSON view.":::
+   :::image type="content" source="media/search-get-started-portal-import-vectors/select-json-view.png" alt-text="Screenshot of the menu command for opening the JSON view." lightbox="media/search-get-started-portal-import-vectors/select-json-view.png":::
 
    The default query is an empty search (`"*"`) but includes parameters for returning the number matches. It's a hybrid query that runs text and vector queries in parallel. It also includes semantic ranking and specifies which fields to return in the results through the `select` statement.
 
@@ -544,7 +551,7 @@ Search Explorer accepts text strings as input and then vectorizes the text for v
 
 1. To run the query, select **Search**.
 
-   :::image type="content" source="media/search-get-started-portal-import-vectors/search-results.png" alt-text="Screenshot of search results.":::
+   :::image type="content" source="media/search-get-started-portal-import-vectors/search-results.png" alt-text="Screenshot of search results." lightbox="media/search-get-started-portal-import-vectors/search-results.png":::
 
    Each document is a chunk of the original PDF. The `title` field shows which PDF the chunk comes from. Each `chunk` is long. You can copy and paste one into a text editor to read the entire value.
 
@@ -566,9 +573,9 @@ Search Explorer accepts text strings as input and then vectorizes the text for v
    }
    ```
 
-## Clean up
+## Clean up resource
 
-Azure AI Search is a billable resource. If you no longer need it, delete it from your subscription to avoid charges.
+This quickstart uses billable Azure resources. If you no longer need the resources, delete them from your subscription to avoid charges.
 
 ## Next step
 

@@ -45,8 +45,8 @@ You can create an Azure AI Search service in any of the following Azure public r
 | Canada Central​​ | ✅ | ✅ | ✅ | ✅ | ✅ |
 | Canada East​​ ​|  |  | ✅ | ✅ |  |
 | ​Central US​​ | ✅ | ✅ | ✅ | ✅ | ✅ |
-| East US​ | ✅ | ✅ | ✅ | ✅ |  |
-| East US 2 ​<sup>1</sup>  | ✅ | ✅ | ✅ | ✅ | ✅ |
+| East US​ <sup>1</sup> | ✅ | ✅ | ✅ | ✅ |  |
+| East US 2 | ✅ | ✅ | ✅ | ✅ | ✅ |
 | Mexico Central |  | ✅ |  |  |  |
 | North Central US​ ​| ✅ |  | ✅ | ✅ | ✅ |
 | South Central US​ | ✅ | ✅ | ✅ | ✅ | ✅ |
@@ -55,8 +55,7 @@ You can create an Azure AI Search service in any of the following Azure public r
 | West US 3​ | ✅ | ✅ | ✅ | ✅ | ✅ |
 | West Central US​ ​ | ✅ |  | ✅ | ✅ |  |
 
-<sup>1</sup> This region has capacity constraints on the following tiers: S2, S3, L1, and L2.
-
+<sup>1</sup> This region has capacity constraints in all tiers.
 ### Europe
 
 | Region | AI enrichment | Availability zones | Agentic retrieval | Semantic ranker | Query rewrite |

@@ -20,18 +20,18 @@ Azure AI Search is a scalable search infrastructure that indexes heterogeneous c
 
 The service handles both traditional search workloads and modern RAG (retrieval-augmented generation) patterns for conversational AI applications. This makes it suitable for enterprise search scenarios as well as AI-powered customer experiences that require dynamic content generation through chat completion models.
 
-<!-- Azure AI Search is a knowledge retrieval platform that consolidates and organizes information across different types of content. You add your content to a search index. Users, agents, and bots retrieve your content through queries and apps.
-Indexing and query workloads support native integration with AI models from Azure OpenAI, Azure AI Foundry, and Azure Machine Learning. By leveraging an extensibility layer, you can connect workloads to third-party and open-source AI models and tools.
-
-You can use Azure AI Search for regular search needs (like searching through catalogs or documents) or for AI-powered search that can have conversations with users and generate answers based on your content. -->
-
 <!-- Azure AI Search ([formerly known as "Azure Cognitive Search"](whats-new.md#new-service-name)) is an enterprise-ready information retrieval system for your heterogeneous content that you ingest into a search index, and surface to users through queries and apps. It comes with a comprehensive set of advanced search technologies, built for high-performance applications at any scale.
 
 Azure AI Search is the recommended retrieval system for building agent-to-agent (A2A) and RAG-based applications on Azure, with native LLM integrations between Azure OpenAI in Azure AI Foundry Models and Azure Machine Learning, with mechanisms for integrating third-party and open-source models and processes.
 
 Azure AI Search can be used for both traditional search as well as modern information retrieval. Common use cases include catalog or document search, information discovery (data exploration), and  retrieval-augmented generation (RAG) for conversational search.  
  -->
 
+<!-- Azure AI Search is a knowledge retrieval platform that consolidates and organizes information across different types of content. You add your content to a search index. Users, agents, and bots retrieve your content through queries and apps.
+Indexing and query workloads support native integration with AI models from Azure OpenAI, Azure AI Foundry, and Azure Machine Learning. By leveraging an extensibility layer, you can connect workloads to third-party and open-source AI models and tools.
+
+You can use Azure AI Search for regular search needs (like searching through catalogs or documents) or for AI-powered search that can have conversations with users and generate answers based on your content. -->
+
 When you create a search service, you work with the following capabilities:
 
 + A search engine for [agentic search](search-agentic-retrieval-concept.md), [vector search](vector-search-overview.md), [full text](search-lucene-query-architecture.md), [multimodal search](multimodal-search-overview.md), or [hybrid search](hybrid-search-overview.md).

@@ -357,4 +357,4 @@ If you anticipate consistent throughput requirements near, at, or higher than th
 Semantic ranking can be used in hybrid queries that combine keyword search and vector search into a single request and a unified response.
 
 > [!div class="nextstepaction"]
-> [Hybrid query with semantic ranker](hybrid-search-how-to-query.md#semantic-hybrid-search)
+> [Hybrid query with semantic ranker](hybrid-search-how-to-query.md#example-semantic-hybrid-search)

@@ -262,4 +262,4 @@ In the preceding example:
 Semantic ranking can be used in hybrid queries that combine keyword search and vector search into a single request and a unified response.
 
 > [!div class="nextstepaction"]
-> [Hybrid query with semantic ranker](hybrid-search-how-to-query.md#semantic-hybrid-search)
+> [Hybrid query with semantic ranker](hybrid-search-how-to-query.md#example-semantic-hybrid-search)

@@ -177,6 +177,7 @@ api-key: {{admin-api-key}}
 
         }
     ]
+}
 ```
 
 ### [**Azure portal**](#tab/portal-vector-query)
@@ -526,17 +527,6 @@ POST https://[service-name].search.windows.net/indexes/[index-name]/docs/search?
     }
 ```
 
- <!-- Keep H2 as-is. Direct link from a blog post. Bulk of maxtextsizerecall has moved to hybrid query doc-->
-## MaxTextSizeRecall for hybrid search (preview)
-
-Vector queries are often used in hybrid constructs that include nonvector fields. If you discover that BM25-ranked results are over or under represented in a hybrid query results, you can [set `maxTextRecallSize`](hybrid-search-how-to-query.md#set-maxtextrecallsize-and-countandfacetmode) to increase or decrease the BM25-ranked results provided for hybrid ranking.
-
-You can only set this property in hybrid requests that include both `search` and `vectorQueries` components.
-
-This parameter is in preview. We recommend the  [2024-05-01-preview](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-05-01-preview&preserve-view=true) REST API version.
-
-For more information, see [Set maxTextRecallSize - Create a hybrid query](hybrid-search-how-to-query.md#set-maxtextrecallsize-and-countandfacetmode).
-
 ## Next steps
 
 As a next step, review vector query code examples in [Python](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-python), [C#](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-dotnet) or [JavaScript](https://github.com/Azure/azure-search-vector-samples/tree/main/demo-javascript).

@@ -78,7 +78,7 @@ Learn about the latest updates to Azure AI Search functionality, docs, and sampl
 | November | Feature | [Portal support for structured data](search-get-started-portal-import-vectors.md). The **Import and vectorize data** wizard now supports Azure SQL, Azure Cosmos DB, and Azure Table Storage. |
 | October | Feature | [Lower the dimension requirements for MRL-trained text embedding models on Azure OpenAI](vector-search-how-to-truncate-dimensions.md). Text-embedding-3-small and Text-embedding-3-large are trained using Matryoshka Representation Learning (MRL). This allows you to truncate the embedding vectors to fewer dimensions, and adjust the balance between vector index size usage and retrieval quality. A new `truncationDimension` in the [2024-09-01-preview](/rest/api/searchservice/indexes/create-or-update?view=rest-searchservice-2024-09-01-preview&preserve-view=true) enables access to MRL compression in text embedding models. This can only be configured for new vector fields. |
 | October | Feature | [Unpack `@search.score` to view subscores in hybrid search results](hybrid-search-ranking.md#unpack-a-search-score-into-subscores-preview). You can investigate Reciprocal Rank Fusion (RRF) ranked results by viewing the individual query subscores of the final merged and scored result. A new `debug` property unpacks the search score. `QueryResultDocumentSubscores`, `QueryResultDocumentRerankerInput`, and `QueryResultDocumentSemanticField` provide the extra detail. These definitions are available in the [2024-09-01-preview](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
-| October | Feature | [Target filters in a hybrid search to just the vector queries](hybrid-search-how-to-query.md#hybrid-search-with-filters-targeting-vector-subqueries-preview). A filter on a hybrid query involves all subqueries on the request, regardless of type. You can override the global filter to scope the filter to a specific subquery. The new `filterOverride` parameter is available on hybrid queries using the [2024-09-01-preview](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
+| October | Feature | [Target filters in a hybrid search to just the vector queries](hybrid-search-how-to-query.md#example-hybrid-search-with-filters-targeting-vector-subqueries-preview). A filter on a hybrid query involves all subqueries on the request, regardless of type. You can override the global filter to scope the filter to a specific subquery. The new `filterOverride` parameter is available on hybrid queries using the [2024-09-01-preview](/rest/api/searchservice/documents/search-post?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
 | October | Applied AI (skills) | [Text Split skill (token chunking)](cognitive-search-skill-textsplit.md). This skill has new parameters that improve data chunking for embedding models. A new `unit` parameter lets you specify token chunking. You can now chunk by token length, setting the length to a value that makes sense for your embedding model. You can also specify the tokenizer and any tokens that shouldn't be split during data chunking. The new `unit` parameter and query subscore definitions are found in the [2024-09-01-preview](/rest/api/searchservice/skillsets/create-or-update?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
 | October | API | [2024-09-01-preview](/rest/api/searchservice/search-service-api-versions?view=rest-searchservice-2024-09-01-preview&preserve-view=true). Preview release of REST APIs for truncated dimensions in text-embedding-3 models, targeted vector filtering for hybrid queries, RRF subscore details for debugging, and token chunking for Text Split skill.|
 | October | Feature | [Portal support for customer-managed key encryption (CMK)](search-security-manage-encryption-keys.md#step-4-encrypt-content). When you create new objects in the Azure portal, you can now specify CMK-encryption and select an Azure Key Vault to provide the key. |