Building and scaling generative AI applications with foundational models (FMs) can be challenging, so understanding which development environments can help is a project priority. If an enterprise wants to use a FM to answer questions about its private data stored in an Amazon Aurora PostgreSQL-Compatible Edition database, it needs a technique called Retrieval Augmented Generation – RAG – to provide relevant answers to the questions customers are asking.

Amazon Bedrock is a fully-managed RAG capability that allows the customization of FM responses with contextual and relevant company data. Amazon Bedrock works by automating the end-to-end RAG workflow, eliminating the need to write custom code to integrate data sources and manage queries. Integrating Amazon Bedrock with Amazon Aurora PostgreSQL lets you utilize features that help accelerate performance of vector similarity search for RAG. Learning best practices for vector search will help the delivery of a high-performance experience for your business teams and your customers.

In this instructive webinar The Register’s James Hayes is joined by AWS Principal Product Manager and AI expert Jonathan Katz who will explain how Aurora PostgreSQL makes it easier to store and query vector data for AI and Machine Learning use-cases with the ‘pgvector’ extension. Key learnings from this webinar will include:

• How to store data from Amazon Bedrock in an Amazon Aurora PostgreSQL.
• What SQL queries and tuning parameters optimize the performance of your application when working with AI/ML data.
• What SQL queries and tuning parameters optimize the performance of your application when working with vector data types, exact and approximate nearest neighbour search algorithms, and vector-optimized indexing.