Transforming AI storage with Amazon S3 Vectors and Amazon OpenSearch

Arik Porat, Senior Solutions Architect, AWS | Liat Iusim, Solutions Architect, AWS

AWS Summit Tel Aviv 2026 · AWS For Data and Analytics · 40 min · 16 pages

Vector embeddings and vector search are transforming how organizations build and scale AI, from semantic search to generative applications. This session shows how Amazon S3 Vectors complements Amazon OpenSearch to dramatically reduce storage and query costs by up to 90% while maintaining high relevance and performance. You'll learn about S3 Vectors and its integration with Amazon Bedrock Knowledge Bases and Amazon OpenSearch Service to power RAG and semantic search with lower cost and complexity. We'll also highlight the latest OpenSearch innovations, including GPU-accelerated vector indexing, with real customer use cases.

Generated automatically from the recording's transcript. It's meant to replace re-watching, not the recording itself — verify against the video at the timestamp before quoting formally. Slides belong to the speakers and organisers. Produced with recording-to-pdf.