You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
|[**Text Split skill**](cognitive-search-skill-textsplit.md)| Applied AI (skills) | This skill has new parameters that improve data chunking for embedding models. 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). |
28
+
|[**Optionally lower the dimension requirements on retrained text embedding models on Azure OpenAI**](vector-search-how-to-configure-compression-storage.md)| Feature | Text-embedding-3-small and Text-embedding-3-large are retrained using the Matryoshka Representation Learning (MRL) technique, allowing you to specify a lower dimension limit, saving on vector storage. A new `truncationDimension` provides the MRL behaviors. |[Create or Update Index (preview)](/rest/api/searchservice/indexes/create-or-update?view=rest-searchservice-2024-09-01-preview&preserve-view=true). |
29
+
|[**Unpack `@search.score` to view subscores in hybrid search results**](hybrid-search-ranking.md)| Feature | 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). |
30
+
|[**Target filters in a hybrid search to just the vector queries**](hybrid-search-how-to-query.md)| Feature | 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). |
31
+
|[**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). |
29
32
|[**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). |
30
33
|[**Azure Machine Learning (AML) skill**](cognitive-search-aml-skill.md)| Applied AI (skills) | AML skill integrates an inferencing endpoint from Azure Machine Learning. |[Create or Update Skillset (preview)](/rest/api/searchservice/skillsets/create-or-update?view=rest-searchservice-2024-05-01-preview&preserve-view=true). 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 Studio model catalog. It's also available in the portal, in skillset design, assuming Azure AI Search and Azure Machine Learning services are deployed in the same subscription. |
31
34
|[**Incremental enrichment cache**](cognitive-search-incremental-indexing-conceptual.md)| Applied AI (skills) | Adds caching to an enrichment pipeline, allowing you to reuse existing output if a targeted modification, such as an update to a skillset or another object, doesn't change the content. Caching applies only to enriched documents produced by a skillset.|[Create or Update Indexer (preview)](/rest/api/searchservice/indexers/create-or-update?view=rest-searchservice-2024-05-01-preview&preserve-view=true). |
|[**Text Split skill**](cognitive-search-skill-textsplit.md)| Feature | New in the [2024-09-01-preview](/rest/api/searchservice/skillsets/create-or-update?view=rest-searchservice-2024-09-01-preview&preserve-view=true) release, this skill adds parameters that improve data chunking for embedding models. You can now chunk by token length, setting the length to a value that makes sense for your embedding model. You can also use the Azure portal to set these parameters. For Azure SDK support, refer to the change log of the package you're using for version updates. |
27
-
|[**2024-09-01-preview**](/rest/api/searchservice/search-service-api-versions?view=rest-searchservice-2024-09-01-preview&preserve-view=true)| API | Preview release of REST APIs for Matryoshka Representation Learning (MRL) compression for text-embedding-3 models, targeted vector filtering for hybrid queries, vector subscore details for debugging, and token chunking for Text Split skill.|
26
+
|[**Optionally lower the dimension requirements on retrained text embedding models on Azure OpenAI**](vector-search-how-to-configure-compression-storage.md)| Feature | Text-embedding-3-small and Text-embedding-3-large are retrained using the Matryoshka Representation Learning (MRL) technique, allowing you to specify a lower dimension limit, saving on vector storage. A new `truncationDimension` provides the MRL behaviors in the [2024-09-01-preview](/rest/api/searchservice/indexes/create-or-update?view=rest-searchservice-2024-09-01-preview&preserve-view=true) API version. |
27
+
|[**Unpack `@search.score` to view subscores in hybrid search results**](hybrid-search-ranking.md)| Feature | 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) API version. |
28
+
|[**Target filters in a hybrid search to just the vector queries**](hybrid-search-how-to-query.md)| Feature | 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) API version. |
29
+
|[**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). |
30
+
|[**2024-09-01-preview**](/rest/api/searchservice/search-service-api-versions?view=rest-searchservice-2024-09-01-preview&preserve-view=true)| API | 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.|
28
31
29
32
## August 2024
30
33
31
34
| Item | Type | Description |
|[Debug session improvements](cognitive-search-debug-session.md)| feature | There are two important improvements. First, you can now debug integrated vectorization and data chunking workloads. Second, debug sessions is redesigned for a more streamlined presentation of skills and mappings. You can select an object in the flow, and view or edit its details off to the side. The previous tabbed layout is fully replaced with more context-sensitive information on the page. |
36
+
|[Debug Session improvements](cognitive-search-debug-session.md)| feature | There are two important improvements. First, you can now debug integrated vectorization and data chunking workloads. Second, Debug Sessions is redesigned for a more streamlined presentation of skills and mappings. You can select an object in the flow, and view or edit its details in a side panel. The previous tabbed layout is fully replaced with more context-sensitive information on the page. |
34
37
|[2024-07-01](/rest/api/searchservice/search-service-api-versions?view=rest-searchservice-2024-07-01&preserve-view=true)| API | Stable release of REST APIs for generally available vector data types, vector compression, and integrated vectorization during indexing and queries. |
35
38
|[Integrated vectorization](vector-search-integrated-vectorization.md)| Feature | Announcing general availability. Skills-driven data chunking and embedding during indexing. |
36
39
|[Vectorizers](vector-search-how-to-configure-vectorizer.md)| Feature | Announcing general availability. Text-to-vector conversion during query execution. Both [Azure OpenAI vectorizer](vector-search-vectorizer-azure-open-ai.md) and [custom Web API vectorizer](vector-search-vectorizer-custom-web-api.md) are generally available. |
0 commit comments