In this workshop you will learn how to integrate Generative AI capabilities into your Amazon Aurora PostgreSQL-Compatible Edition database using the pgvector extension . This workshop focuses on utilizing foundation models from Amazon Bedrock and Hugging Face to create, store, and query vector embeddings within Aurora PostgreSQL, leveraging the pgvector extension.

Target Audience

• Application Developers and DBA/Data Engineers
• AI/ML Engineers and Data Scientists interested in Generative AI and vector databases
• Technical or Solution Architects, Infrastructure and Platform Engineers

Use Cases

Each use case module should take less than an hour once the prerequisites are run and resources created. Each of the modules are independent and can be run in any order.

Product Recommendations

• Retrieval Augmented Generation (RAG)
• Questions Answering using Bedrock LLMs
• Question Answering using Open Source LLMs
• Response Streaming
• Semantic Search and Sentiment Analysis
• Knowledge Bases for Amazon Bedrock with Aurora PostgreSQL
• Movie Recommendations using Aurora Machine Learning (ML) and Amazon Bedrock