Posted On: Dec 21, 2023
Today, AWS announces two methods to integrate HAQM Aurora PostgreSQL databases with HAQM Bedrock to power generative AI applications. First, HAQM Aurora ML now provides access to foundation models available through HAQM Bedrock directly through SQL. Second, Knowledge Bases for HAQM Bedrock now supports HAQM Aurora as a vector store for Retrieval Augmented Generation (RAG).
HAQM Aurora ML exposes ML models as SQL functions, allowing you to use standard SQL to pass data to models and return model output as query results. As an example, Aurora ML and Bedrock together can enable real-time summarization of customer support notes in Aurora to accelerate case resolution. HAQM Aurora is also now a vector database option for Knowledge Bases for HAQM Bedrock, letting you securely connect your organization’s private data sources to foundation models for RAG. Through Knowledge Bases, you can also choose to add HAQM Aurora to Agents for HAQM Bedrock to execute multistep actions for your generative AI applications.
The Aurora ML integration with HAQM Bedrock is available in the US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Asia Pacific (Tokyo), and Europe (Frankfurt) regions. Knowledge Bases for HAQM Bedrock with HAQM Aurora PostgreSQL is available in the US East (N. Virginia) and US West (Oregon) regions.
To get started with Aurora ML, customers should install the Aurora ML extension and follow these instructions. To get started with HAQM Bedrock, customers should navigate to HAQM Bedrock in the AWS console. To learn more, visit the HAQM Aurora webpage or HAQM Bedrock webpage.