Since its launch in July 2024, Unity Catalog has rapidly grown with key features like external authentication, MLflow model support, Apache Spark integration, and a new UI, making it a powerful tool for unified data and AI governance.
Using Unity Catalog with LlamaIndex helps you organize and use your data with AI. You can build LLM-powered systems while keeping your data safe and easy to manage.
This article explains how you can use Unity Catalog with OpenAI to build faster and safer AI workflows.
This article explains the difference between managed and external tables and shows you how to work with both types of tables in Unity Catalog (UC).
This article explains how you can use Unity Catalog for AI use cases. Unity Catalog integrates with popular GenAI tools like LangChain, LlamaIndex, OpenAI, Anthropic, and many others to make it easy to manage data, functions, and access control across AI platforms.
The Unity Catalog AI library is built to integrate Unity Catalog with popular GenAI tools like LangChain, LlamaIndex, OpenAI, Anthropic, and many others to make it easy to manage data, functions, and access control across AI platforms.
As part of our continued steadfast commitment to build a robust, flexible, and developer-friendly data catalog platform, we are excited to announce the release of Unity Catalog AI 0.3.0.
This article explains what metadata is and how it is handled by a data catalog to make your data storage and queries more efficient and secure. The article gives an overview of metadata management and explains why a modern data catalog like Unity Catalog is better than legacy metadata management techniques.
Unity Catalog uses a universal namespace for consistent data access, offers secure access control, and supports both managed and external volumes. It integrates with Spark, MLflow, and other AI tools for seamless data and experiment management.
This article explains authentication and authorization in Unity Catalog, emphasizing their role in secure data governance. It provides a step-by-step guide to configuring Unity Catalog with external identity providers like Google Auth, ensuring centralized identity management, enhanced security, and scalability for modern data pipelines.
We are excited to announce that we are open sourcing Unity Catalog, the industry’s first open source catalog for data and AI governance across clouds, data formats, and data platforms.