Note
Access to this page requires authorization. You can try signing in or changing directories.
Access to this page requires authorization. You can try changing directories.
Learn about the latest updates to Azure AI Search functionality, docs, and samples.
Note
Preview features are announced here, but we also maintain a preview features list so you can find them in one place.
March 2025
| Item | Type | Description |
|---|---|---|
| Service upgrade (preview) | Service | Upgrade your search service to higher storage limits in your region. With a one-time upgrade, you no longer need to recreate your service. Available in Upgrade Service (2025-02-01-preview) and the Azure portal. |
| Pricing tier change (preview) | Service | Change the pricing tier of your search service. This provides flexibility to scale storage, increase request throughput, and decrease latency based on your needs. In this preview, you can only change between Basic and Standard (S1, S2, and S3) tiers. Available in Update Service (2025-02-01-preview) and the Azure portal. |
| Facet hierarchies, aggregations, and facet filters (preview) | Queries | New facet query parameters support nested facets. For numeric facetable fields, you can sum the values of each field. You can also specify filters on a facet to add inclusion or exclusion criteria. Available in Search Documents (2025-03-01-preview) and the Azure portal. |
| Rescore vector queries over binary quantization using full precision vectors (preview) | Queries | For vector indexes that contain binary quantization, you can rescore query results using a full precision vector query. The query engine uses the dot product of the binary embeddings and the vector query for rescoring, which improves the quality of search results. Set enableRescoring and discardOriginals to use this feature, and call the latest preview API version on the request. |
| Semantic ranker pre-release models (preview) | Index | Opt in to use pre-release semantic ranker models if one happens to be available in your region. Available in Create or Update Index (2025-03-01-preview). |
| Search Service REST 2025-03-01-preview | REST | Public preview release of REST APIs for data plane operations. Adds support for multi-vector embeddings, hierarchical facets, facet aggregation, and facet filters. |
| Search Management 2025-02-01-preview | REST | Public review release of REST APIs for control plane operations. Adds support for in-place upgrade to higher capacity partitions, in-place upgrade to higher tiers, and Azure Confidential Compute. |
February 2025
| Item | Type | Description |
|---|---|---|
| Customer-managed keys support for Managed HSM | Security | Use either Azure Key Vault or Azure Key Vault Managed HSM (Hardware Security Module) to store customer-managed keys for extra encryption of sensitive content. |
2024 announcements
| Month | Type | Announcement |
|---|---|---|
| December | Template | RAG chat with Azure AI Search + Python. An AI application template for building a RAG solution using Azure AI Search and Python. |
| November | Security | Network security perimeter. Join a search service to a network security perimeter to control network access to your search service. The Azure portal and the Management REST APIs in the 2024-06-01-preview can be used to view and reconcile network security perimeter configurations. |
| November | Security | Shared private link support for Azure AI service connections. Connections to Azure AI for built-in skills processing can now be private using a shared private link on the connection. |
| November | Relevance | Rescoring options for compressed vectors. 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. Available in the Create or Update Index (2024-11-01-preview), the Azure portal, and in the Azure SDK beta packages that provide this feature. |
| November | Vector search | Store fewer vector instances. In vector compression scenarios, you can omit storage of full precision vectors if you don't need them for rescoring. Available in the Create or Update Index (2024-11-01-preview), the Azure portal, and in the Azure SDK beta packages that provide this feature. |
| November | Relevance | Query rewrite in the semantic reranker. You can set options on a semantic query to rewrite the query input into a revised or expanded query that generates more relevant results from the L2 ranker. Available in the Search Documents (2024-11-01-preview), the Azure portal, and in the Azure SDK beta packages that provide this feature. |
| November | Relevance | New semantic ranker models. Semantic ranker runs with improved models in all supported regions. There's no change to APIs or the Azure portal experience. |
| November | Applied AI (skills) | Document Layout skill. A new skill used to analyze a document for structure and provide structure-aware (paragraph) chunking. This skill calls Document Intelligence and uses the Document Intelligence layout model. Available in selected regions through the Create or Update Skillset (2024-11-01-preview), the Azure portal, and in the Azure SDK beta packages that provide this feature. |
| November | Applied AI (skills) | Keyless billing for Azure AI skills processing. You can now use a managed identity and roles for a keyless connection to Azure AI services for built-in skills processing. This capability removes restrictions for having both search and AI services in the same region. Available in the Create or Update Skillset (2024-11-01-preview), the Azure portal, and in the Azure SDK beta packages that provide this feature. |
| November | Indexer data source | Markdown parsing mode. With this parsing mode, indexers can generate one-to-one or one-to-many search documents from Markdown files in Azure Storage and OneLake. Available in the Create or Update Indexer (2024-11-01-preview), the Azure portal, and in the Azure SDK beta packages that provide this feature. |
| November | API | 2024-11-01-preview. Preview release of REST APIs for query rewrite, Document Layout skill, keyless billing for skills processing, Markdown parsing mode, and rescoring options for compressed vectors. |
| November | Feature | Portal support for structured data. 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. 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 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. 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. |
| October | Feature | Target filters in a hybrid search to just the vector queries. 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. |
| October | Applied AI (skills) | Text Split skill (token chunking). 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. |
| October | API | 2024-09-01-preview. 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). 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. |
| August | Feature | Debug Session improvements. 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. |
| August | API | 2024-07-01. Stable release of REST APIs for generally available vector data types, vector compression, and integrated vectorization during indexing and queries. |
| August | Feature | Integrated vectorization, Announcing general availability. Skills-driven data chunking and embedding during indexing. |
| August | Feature | Vectorizers. Announcing general availability. Text-to-vector conversion during query execution. Both Azure OpenAI vectorizer and custom Web API vectorizer are generally available. |
| August | Feature | AzureOpenAIEmbedding skill. Announcing general availability. A skill type that calls an Azure OpenAI embedding model to generate embeddings during indexing. |
| August | Feature | Index projections. Announcing general availability. A component of a skillset definition that defines the shape of a secondary index, supporting a one-to-many index pattern, where content from an enrichment pipeline can target multiple indexes. |
| August | Feature | Binary and Scalar quantization. Announcing general availability. Compress vector index size in memory and on disk using built-in quantization. |
| August | Feature | Narrow data types. Announcing general availability. Assign a smaller data type on vector fields, assuming incoming data is of that data type. |
| August | Feature | Import and vectorize data wizard. Announcing general availability. A wizard that creates a full indexing pipeline that includes data chunking and vectorization. The wizard creates all necessary objects and configurations. This release adds wizard support for Azure Data Lake in Azure Storage. |
| August | Feature | stored property. Announcing general availability. Boolean that reduces storage of vector indexes by not storing retrievable vectors. |
| August | Feature | vectorQueries.Weight property. Announcing general availability. Specify the relative weight of each vector query in a search operation. |
| July | Accelerator | Chat with your data. A solution accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to create conversational search experiences. The code with sample data is available for use case scenarios such as financial advisor and contract review and summarization. |
| July | Accelerator | Conversational Knowledge Mining. A solution accelerator built on top of Azure AI Search, Azure Speech and Azure OpenAI services that allows customers to extract actionable insights from post-contact center conversations. |
| July | Accelerator | Build your own copilot. Create your own custom copilot solution that empowers Client Advisor to harness the power of generative AI across both structured and unstructured data. Help our customers to optimize daily tasks and foster better interactions with more clients. |
| June | Feature | Image search in the Azure portal. Search explorer now supports image search. In a vector index that contains vectorized image content, you can drop images into Search Explorer to query for a match. |
| May | Service limits | Higher capacity and more vector quota at every tier (same billing rate). For most regions, partition sizes are now even larger for Standard 2 (S2), Standard 3 (S3), and Standard 3 High Density (S3 HD) for services created after April 3, 2024. To get the larger partitions, create a new service in a region that provides newer infrastructure. Storage Optimized tiers (L1 and L2) also have more capacity. L1 and L2 customers must create a new service to benefit from the higher capacity. There's no in-place upgrade at this time. Extra capacity is now available in more regions: Germany North, Germany West Central, South Africa North, Switzerland West, and Azure Government (Texas, Arizona, and Virginia). |
| May | Feature | OneLake integration (preview). New indexer for OneLake files and OneLake shortcuts. If you use Microsoft Fabric and OneLake for data access to Amazon Web Services (AWS) and Google data sources, use this indexer to import external data into a search index. This indexer is available through the Azure portal, the 2024-05-01-preview REST API, and Azure SDK beta packages. |
| May | Feature | Vector relevance hybrid query relevance. Four enhancements improve vector and hybrid search relevance. First, you can now set thresholds on vector search results to exclude low-scoring results. Second, changes in the query architecture apply scoring profiles at the end of the query pipeline for every query type. Document boosting is a common scoring profile, and it now works as expected on vector and hybrid queries. Third, you can set MaxTextRecallSize and countAndFacetMode in hybrid queries to control the quantity of BM25-ranked search results that flow into the hybrid ranking model. Fourth, for vector and hybrid search, you can weight a vector query to have boost or diminish its importance in a multiquery request. |
| May | Feature | Binary vectors support. Collection(Edm.Byte) is a new supported data type. This data type opens up integration with the Cohere v3 binary embedding models and custom binary quantization. Narrow data types lower the cost of large vector datasets. See Index binary data for vector search for more information. |
| May | Skill | Azure AI Vision multimodal embeddings skill (preview). New skill that's bound to the multimodal embeddings API of Azure AI Vision. You can generate embeddings for text or images during indexing. This skill is available through the Azure portal and the 2024-05-01-preview REST API. |
| May | Vectorizer | Azure AI Vision vectorizer (preview). New vectorizer connects to an Azure AI Vision resource using the multimodal embeddings API to generate embeddings at query time. This vectorizer is available through the Azure portal and the 2024-05-01-preview REST API. |
| May | Vectorizer | Azure AI Foundry model catalog vectorizer (preview). New vectorizer connects to an embedding model deployed from the Azure AI Foundry model catalog. This vectorizer is available through the Azure portal and the 2024-05-01-preview REST API. How to implement integrated vectorization using models from Azure AI Foundry. |
| May | Skill | AzureOpenAIEmbedding skill (preview) supports more models on Azure OpenAI. Now supports text-embedding-3-large and text-embedding-3-small, along with text-embedding-ada-002 from the previous update. New dimensions and modelName properties make it possible to specify the various embedding models on Azure OpenAI. Previously, the dimensions limits were fixed at 1,536 dimensions, applicable to text-embedding-ada-002 only. The updated skill is available through the Azure portal and the 2024-05-01-preview REST API. |
| May | Portal | Import and vectorize data wizard now supports OneLake indexers as a data source. For embeddings, it also supports connections to Azure AI Vision multimodal, Azure AI Foundry model catalog, and more embedding models on Azure OpenAI. When adding a field to an index, you can choose a binary data type. Search explorer now defaults to 2024-05-01-preview and supports the new preview features for vector and hybrid queries. |
| May | API | 2024-05-01-preview. New preview version of the Search REST APIs provides new skills and vectorizers, new binary data type, OneLake files indexer, and new query parameters for more relevant results. See Upgrade REST APIs if you have existing code written against the 2023-07-01-preview and need to migrate to this version. |
| May | API | Azure SDK beta packages. Review the changelogs of the following Azure SDK beta packages for new feature support: Azure SDK for Python, Azure SDK for .NET, Azure SDK for Java |
| May | Samples | Python code samples. New end-to-end samples demonstrate integration with Cohere Embed v3, integration with OneLake and cloud data platforms on Google and AWS, and integration with Azure AI Vision multimodal APIs. |
| April | API | Security update addressing information disclosure. GET responses no longer return connection strings or keys. Applies to GET Skillset, GET Index, and GET Indexer. This change helps protect your Azure assets integrated with AI Search from unauthorized access. |
| April | API | 2024-03-01-preview Search REST API |
| April | API | 2024-03-01-preview Management REST API |
| April | API | 2023-07-01-preview deprecation announcement. This version is no longer supported as of July 8, 2024. Newer API versions have a different vector configuration. You should migrate to a newer version as soon as possible. |
| April | Service limits | Basic and Standard tiers offer more storage per partition, at the same per-partition billing rate. Extra capacity is subject to regional availability and applies to new search services created after April 3, 2024. Basic now supports up to three partitions and three replicas. |
| April | Service limits | Vector quotas are higher on new services created after April 3, 2024 in selected regions. |
| April | Feature | Vector quantization, narrow vector data types, and a new stored property (preview). Collectively, these three features minimize storage and costs. |
| February | Feature | New dimension limits on vector fields. Maximum dimension limits are now 3072, up from 2048. |
Previous year's announcements
Service rebrand
This service has had multiple names over the years. Here they are in reverse chronological order:
- Azure AI Search (November 2023) Renamed to align with Azure AI services and customer expectations.
- Azure Cognitive Search (October 2019) Renamed to reflect the expanded (yet optional) use of cognitive skills and AI processing in service operations.
- Azure Search (March 2015) The original name.
Service updates
Service update announcements for Azure AI Search can be found on the Azure web site.
Feature rename
Semantic search was renamed to semantic ranker in November 2023 to better describe the feature, which provides L2 ranking of an existing result set.