A media streaming company wants to enable natural language image search and filtering. They need a vector-capable database that supports similarity searches and nearest-neighbor queries. Which AWS service fits this need?

Amazon OpenSearch Service (formerly Amazon Elasticsearch Service) is the correct choice because it offers vector search capabilities, including k-nearest neighbor (k-NN) search, which is essential for similarity searches and nearest-neighbor queries on image embeddings. This allows the media streaming company to store vector representations of images and find semantically similar images based on natural language queries. Amazon Comprehend is incorrect because it is a natural language processing (NLP) service for text analysis, not a vector database for image search. Amazon Personalize is incorrect as it is a machine learning service for building recommendation systems, not a general-purpose vector database. Amazon Polly is incorrect because it is a text-to-speech service.