Get Started with Amazon SageMaker

You can use the SageMaker Unified Studio query editor to perform analysis using SQL. It provides a place to write and run queries, view results, and share your work with your team. You can also import and query data sets in your existing Glue Data Catalog resources.

SageMaker lakehouse architecture provides a unified environment for accessing, discovering, preparing, and analyzing data from various sources for machine learning (ML) and analytics workloads. Use lakehouse access controls to:

• Streamlining the creation of connections to diverse data sources through a unified interface
• Centralizing access control management through AWS Lake Formation
• Enabling in-place querying through federated catalogs without data movement
• Providing fine-grained permissions at the catalog, database, table, and column levels
• Exploring data for ad hoc reporting and proof of concept before setting up new zero-ETL pipelines

Amazon SageMaker Unified Studio provides a large collection of state-of-the-art foundation models. These models support use cases such as content writing, code generation, question answering, copywriting, summarization, classification, information retrieval, and more. You can find, customize, and deploy these foundation models in the JumpStart model catalog. You can use the foundation models to build your own generative AI solutions for a wide range of applications.

Amazon Bedrock in SageMaker Unified Studio offers multiple playgrounds that allow you to easily access and experiment with Amazon Bedrock models. With the chat playground, you can chat with a model through text and image prompts. With the image and video playground, you can use a compatible model to generate and edit images and videos. In addition to the playgrounds, you can also use Amazon Bedrock in SageMaker Unified Studio to create chat agent apps and flows apps.