Enhance image search experiences with Amazon Personalize, Amazon OpenSearch Service, and Amazon Titan Multimodal Embeddings in Amazon Bedrock
Machine Learning Blog
This article discusses how to enhance image search experiences by combining Amazon Personalize, Amazon OpenSearch Service, and Amazon Titan Multimodal Embeddings. It provides a solution for personalizing image search results based on users' preferences and past interactions.
Specifically, the article covers:
- Solution overview explaining the need for personalizing image search results
- Prerequisites for implementing the solution
- Creating embeddings for images using Amazon Titan Multimodal Embeddings
- Clustering image embeddings using SageMaker K-Means
- Storing embeddings and clusters in an OpenSearch Service vector index
- Updating the image interactions dataset with cluster IDs
- Creating an Amazon Personalize personalized ranking campaign
- Serving personalized search requests by combining OpenSearch and Personalize scores
- Cleanup steps to delete the created resources
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Nov 13
2024
2024
Build a reverse image search engine with Amazon Titan Multimodal Embeddings in Amazon Bedrock and AWS managed services
Apr 3
2024
2024
Build a contextual text and image search engine for product recommendations using Amazon Bedrock and Amazon OpenSearch Serverless
Apr 24
2025
2025
Combine keyword and semantic search for text and images using Amazon Bedrock and Amazon OpenSearch Service
Aug 29
2024
2024
Provide a personalized experience for news readers using Amazon Personalize and Amazon Titan Text Embeddings on Amazon Bedrock
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.