This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact AWS Training and Certification Customer Support.
Learners can gain an understanding of how Amazon Nova Multimodal Embeddings maps text, images, and document pages into a shared vector space -- enabling retrieval across modalities. The course demonstrates building a multimodal retrieval system for aerospace manufacturing documents using Amazon Bedrock and Amazon S3 Vectors. Participants learn why text-only retrieval fails when answers are locked in engineering diagrams, thermal plots, or inspection photographs, and how multimodal search addresses this gap. The course also covers evaluating retrieval quality by comparing text-only and multimodal pipelines across real manufacturing queries.
