Skip to main content

Implement unified text and image search application with analytics and ML (Level 200)

While text and semantic search engines has enabled many organizations to search for information quickly, organizations that offer unified text and image search engines can provide competitive advantage and revenue streams by offering their customers the flexibility to show physical examples or images to describe the items in the search engines. This session showcases how to build a ML-powered search engine to easily retrieve and recommend products based on text or image queries. Learn how to use Amazon SageMaker to host and manage the pre-trained Contrastive Language–Image Pre-training (CLIP) model, and run visual search from a query image. We also share how to use easy to deploy, operate, and scale OpenSearch clusters and the other AWS services to build this end-to-end application. Download slides »
Speaker: Kevin Du, Senior ML Data Lab Solutions Architect, AWS
Duration: 30mins