Chunks no preview

Author: JetterMcTedder

docs/includes/paragraph-content/preview-features.md

@@ -1,7 +1,8 @@
 ---
 author: MikeRayMSFT
 ms.author: mikeray
-ms.date: 08/14/2025
+ms.reviewer: randolphwest
+ms.date: 10/06/2025
 ms.service: sql
 ms.topic: include
 ---
@@ -10,7 +11,6 @@ The following table identifies features originally released as preview their cur
 
 | Feature | Current status | Version of latest update | Description |
 | --- | --- | --- | --- |
-| [AI_GENERATE_CHUNKS](../../t-sql/functions/ai-generate-chunks-transact-sql.md) | Preview | RC 1 | Generate chunks of text from a given input text using an AI model. |
 | [Change event streaming](../../relational-databases/track-changes/change-event-streaming/overview.md) | Preview | RC 1 | Stream changes from SQL Server to Azure Event Hubs. |
 | [CREATE EXTERNAL MODEL](../../t-sql/statements/create-external-model-transact-sql.md) | Preview | RC 1 | Supports local ONNX models hosted directly on the SQL Server file system. |
 | [CREATE VECTOR INDEX](../../t-sql/statements/create-vector-index-transact-sql.md) | Preview | RC 1 | Create an approximate index on a vector column to improve performances of nearest neighbors search. |

docs/sql-server/what-s-new-in-sql-server-2025.md

@@ -4,7 +4,7 @@ description: Learn about new features for SQL Server 2025 (17.x), which gives yo
 author: MikeRayMSFT
 ms.author: mikeray
 ms.reviewer: wiassaf, randolphwest
-ms.date: 09/16/2025
+ms.date: 10/06/2025
 ms.service: sql
 ms.subservice: release-landing
 ms.topic: whats-new
@@ -88,7 +88,7 @@ The following sections identify features that are improved or introduced in [!IN
 | [Copilot in SQL Server Management Studio](/ssms/copilot/copilot-in-ssms-overview) | Ask questions. Get answers from your data. |
 | [Vector data type](../t-sql/data-types/vector-data-type.md) | Store vector data optimized for operations such as similarity search and machine learning applications. Vectors are stored in an optimized binary format but are exposed as JSON arrays for convenience. Each element of the vector can be stored either using a single-precision (4-byte) or half-precision (2-byte) floating-point value. |
 | [Vector functions](../t-sql/functions/vector-functions-transact-sql.md) | New scalar functions perform operations on vectors in binary format, allowing applications to store and manipulate vectors in the SQL Database Engine. |
-| [Vector index](../sql-server/ai/vectors.md#vector-search) | Create and manage approximate vector indexes to quickly and efficiently find similar vectors to a given reference vector.<br /><br />Query vector indexes from [sys.vector_indexes](../relational-databases/system-catalog-views/sys-vector-indexes-transact-sql.md). Requires [PREVIEW_FEATURES database scoped configuration](../t-sql/statements/alter-database-scoped-configuration-transact-sql.md#preview-features). |
+| [Vector index](ai/vectors.md#vector-search) | Create and manage approximate vector indexes to quickly and efficiently find similar vectors to a given reference vector.<br /><br />Query vector indexes from [sys.vector_indexes](../relational-databases/system-catalog-views/sys-vector-indexes-transact-sql.md). Requires [PREVIEW_FEATURES database scoped configuration](../t-sql/statements/alter-database-scoped-configuration-transact-sql.md#preview-features). |
 | [Manage external AI models](../t-sql/statements/create-external-model-transact-sql.md) | Manage external AI model objects for embedding tasks (creating vector arrays) accessing REST AI inference endpoints. |
 
 ## Developer
@@ -223,7 +223,7 @@ The [intelligent query processing (IQP)](../relational-databases/performance/int
 | [CREATE EXTERNAL MODEL](../t-sql/statements/create-external-model-transact-sql.md) | Creates an external model object that contains the location, authentication method, and purpose of an AI model inference endpoint. Requires [PREVIEW_FEATURES database scoped configuration](../t-sql/statements/alter-database-scoped-configuration-transact-sql.md#preview-features). |
 | [ALTER EXTERNAL MODEL](../t-sql/statements/alter-external-model-transact-sql.md) | Alters an external model object. |
 | [DROP EXTERNAL MODEL](../t-sql/statements/drop-external-model-transact-sql.md) | Drops an external model object. |
-| [AI_GENERATE_CHUNKS](../t-sql/functions/ai-generate-chunks-transact-sql.md) | Creates *chunks*, or fragments of text based on a type, size, and source expression. Requires [PREVIEW_FEATURES database scoped configuration](../t-sql/statements/alter-database-scoped-configuration-transact-sql.md#preview-features). |
+| [AI_GENERATE_CHUNKS](../t-sql/functions/ai-generate-chunks-transact-sql.md) | Creates *chunks*, or fragments of text based on a type, size, and source expression. |
 | [AI_GENERATE_EMBEDDINGS](../t-sql/functions/ai-generate-embeddings-transact-sql.md) | Creates embeddings (vector arrays) using a precreated AI model definition stored in the database. |
 | **Regular expressions** | |
 | [REGEXP_LIKE](../t-sql/functions/regexp-like-transact-sql.md) | Indicates if the regular expression pattern matches in a string. |
@@ -243,7 +243,7 @@ The [intelligent query processing (IQP)](../relational-databases/performance/int
 | [PRODUCT](../t-sql/functions/product-aggregate-transact-sql.md) | The `PRODUCT()` aggregate function calculates the product of a set of values. |
 | [CURRENT_DATE](../t-sql/functions/current-date-transact-sql.md) | Returns the current database system date as a date value. |
 | [EDIT_DISTANCE](../t-sql/functions/edit-distance-transact-sql.md) | Calculates the number of insertions, deletions, substitutions, and transpositions needed to transform one string to another. |
-| [EDIT_DISTANCE_SIMILARITY](../t-sql/functions/edit-distance-similarity-transact-sql.md) | Calculates a similarity value ranging from 0 (indicating no match) to 100 (indicating full match).|
+| [EDIT_DISTANCE_SIMILARITY](../t-sql/functions/edit-distance-similarity-transact-sql.md) | Calculates a similarity value ranging from 0 (indicating no match) to 100 (indicating full match). |
 | [JARO_WINKLER_DISTANCE](../t-sql/functions/jaro-winkler-distance-transact-sql.md) | Calculates the edit distance between two strings giving preference to strings that match from the beginning for a set prefix length. Returns **float**. |
 | [JARO_WINKLER_SIMILARITY](../t-sql/functions/jaro-winkler-similarity-transact-sql.md) | Calculates a similarity value ranging from 0 (indicating no match) to 100 (indicating full match). Returns **int**. |
 | - [BASE64_ENCODE](../t-sql/functions/base64-encode-transact-sql.md)<br />- [BASE64_DECODE](../t-sql/functions/base64-decode-transact-sql.md) | Convert binary data into a text format that's safe for transmission across various systems. It can be used in diverse ways as it ensures that your binary data, such as images or files, remains intact during transfer, even when passing through text-only systems. |

docs/t-sql/functions/ai-generate-chunks-transact-sql.md

@@ -4,10 +4,10 @@ description: The ai_generate_chunks table-valued function creates text chunks.
 author: jettermctedder
 ms.author: bspendolini
 ms.reviewer: randolphwest
-ms.date: 08/11/2025
+ms.date: 10/06/2025
 ms.service: sql
 ms.subservice: t-sql
-ms.topic: "reference"
+ms.topic: reference
 ms.custom:
   - sql-ai
   - build-2025
@@ -17,7 +17,7 @@ f1_keywords:
 helpviewer_keywords:
   - "ai_generate_chunks"
 dev_langs:
-  - "TSQL"
+  - TSQL
 monikerRange: "=azuresqldb-current || >=sql-server-ver17 || >=sql-server-linux-ver17"
 ---
 # AI_GENERATE_CHUNKS (Transact-SQL) (Preview)
@@ -26,9 +26,6 @@ monikerRange: "=azuresqldb-current || >=sql-server-ver17 || >=sql-server-linux-v
 
 `AI_GENERATE_CHUNKS` is a table-valued function that creates "chunks", or fragments of text based on a type, size, and source expression.
 
-> [!NOTE]
-> `AI_GENERATE_CHUNKS` in SQL Server 2025 is currently in **preview**. In order to use this feature, you must enable the `PREVIEW_FEATURES` [database scoped configuration](../statements/alter-database-scoped-configuration-transact-sql.md#preview-features).
-
 #### Compatibility level 170
 
 `AI_GENERATE_CHUNKS` requires the compatibility level to be at least 170. When the level is less than 170, the [!INCLUDE [ssde-md](../../includes/ssde-md.md)] is unable to find the `AI_GENERATE_CHUNKS` function.
@@ -153,41 +150,34 @@ CROSS APPLY
 The following example uses `AI_GENERATE_CHUNKS` to chunk a text column. It uses a `chunk_type` of `FIXED` and a `chunk_size` of 100 characters.
 
 ```sql
-SELECT
-    c.chunk
-FROM
-   docs_table t
+SELECT c.chunk
+FROM docs_table AS t
 CROSS APPLY
-   AI_GENERATE_CHUNKS(source = text_column, chunk_type = FIXED, chunk_size = 100) c
+    AI_GENERATE_CHUNKS (SOURCE = text_column, CHUNK_TYPE = FIXED, CHUNK_SIZE = 100) AS c;
 ```
 
 ### B. Chunk a text column with overlap
 
 The following example uses `AI_GENERATE_CHUNKS` to chunk a text column using overlap. It uses the chunk_type of FIXED, a chunk_size of 100 characters, and an overlap of 10 percent.
 
 ```sql
-SELECT
-    c.chunk
-FROM
-   docs_table t
+SELECT c.chunk
+FROM docs_table AS t
 CROSS APPLY
-   AI_GENERATE_CHUNKS(source = text_column, chunk_type = FIXED, chunk_size = 100, overlap = 10) c
+    AI_GENERATE_CHUNKS (SOURCE = text_column, CHUNK_TYPE = FIXED, CHUNK_SIZE = 100, OVERLAP = 10) AS c;
 ```
 
 ### C. Use AI_GENERATE_EMBEDDINGS with AI_GENERATE_CHUNKS
 
 This example uses `AI_GENERATE_EMBEDDINGS` with `AI_GENERATE_CHUNKS` to create embeddings from text chunks and then inserts the returned vector arrays from the AI model inferencing endpoint into a table.
 
 ```sql
-INSERT INTO
-    my_embeddings (chunked_text, vector_embeddings)
-SELECT
-    c.chunk,
-    AI_GENERATE_EMBEDDINGS(c.chunk USE MODEL MyAzureOpenAiModel)
-FROM
-    table_with_text t
+INSERT INTO my_embeddings (chunked_text, vector_embeddings)
+SELECT c.chunk,
+       AI_GENERATE_EMBEDDINGS(c.chunk USE MODEL MyAzureOpenAiModel)
+FROM table_with_text AS t
 CROSS APPLY
-    AI_GENERATE_CHUNKS(source = t.text_to_chunk, chunk_type = FIXED, chunk_size = 100) c
+    AI_GENERATE_CHUNKS (SOURCE = t.text_to_chunk, CHUNK_TYPE = FIXED, CHUNK_SIZE = 100) AS c;
 ```
 
 ## Related content