Architecture Explained: Generative AI-Based Complex Data Processing

Explore the architecture of generative AI-based complex data processing in this 36-minute conference talk sponsored by AWS. Learn about Databricks' end-to-end offerings for ingesting data and building large language model (LLM) applications, as well as AWS's resilient infrastructure and intelligent document processing capabilities. Discover how to leverage Amazon Textract, Amazon Transcribe, Amazon Comprehend, and Amazon Bedrock for generative AI applications. Gain insights into the interoperability between Databricks and AWS, including Databricks Auto Loader, Vector Store, and AI Gateway configuration with Amazon Bedrock. Understand multiple patterns for real-time and batch processing, and watch a demonstration of these concepts in action. Presented by Mayur Rajdev from The Baldwin Group and Venkatavaradhan Viswanathan from Amazon Web Services, this talk provides valuable knowledge for enterprises looking to build innovative applications for improved customer experience using generative AI technologies.

Sponsored by: AWS | Architecture Explained: generative AI based complex data processing