Microsoft Fabric is getting new tools and features to streamline the development of artificial intelligence applications, improve data integration and improve security in a series of announcements made today at Microsoft Corp.’s Ignite conference.

Fabric is an integrated analytics platform that unifies data integration, engineering, warehousing, science and business intelligence on top of a unified data lake. The updates aim to improve the productivity of developers, analysts and data scientists and simplify access to data via a catalog.

The new Fabric Databases, now in preview, are intended to provide simpler database provisioning with autonomous features. The first volume available, SQL Databases in Fabric, allows data to be automatically replicated to Fabric’s built-in OneLake data lake for immediate use by Fabric’s analytical tools. Native vector search functionality combined with Azure AI integration templates supports advanced artificial intelligence functions such as retrieval-augmented generation.

Native vector search is a technique in which data is represented as high-dimensional vectors and the search is performed by finding items whose vectors are closest to a query vector, rather than necessarily being a exact match. Vector data is an essential element in training machine learning models and semantic search.

Self-optimizing and scaling databases deliver faster application performance through intelligent indexing, Microsoft said. Developers can leverage a Fabric Copilot to translate natural language queries into SQL, as well as complete code and provide inline explanations.

Integration with GitHub and Visual Studio Code, a lightweight, open-source code editor developed by Microsoft, supports continuous integration and deployment and simplifies database updates and source control. A common data asset guarantees coherent governance policies.

Simpler generative AI

Microsoft is also expanding AI capabilities within Fabric to make generative AI more accessible. AI Functions in Fabric is a new feature that allows users to perform text-related tasks such as summarization, translation, and sentiment analysis with minimal coding. Simplified application programming interfaces reduce the complexity of AI enrichment. Azure AI Agent service integration enables simplified connection to enterprise data sources, including SharePoint, to automate tasks.

A new Open Mirroring feature, now in preview, makes it easier for applications and data providers to import external data farms into OneLake. Mirroring simplifies data replication by creating an exact copy of data from one system to another to ensure that the primary and secondary systems have identical data at any given time.

The OneLake Catalog, now available to everyone, provides a unified platform for exploring, managing, and governing Microsoft Fabric data. It provides a central interface for discovering data, including filters for domains, owners and tags. New features coming next year will help with data quality, labeling, and compliance with actionable recommendations.

Image: Microsoft