Deploy a Hugging Face (PyAnnote) speaker diarization model on Amazon SageMaker as an asynchronous endpoint

Enhance conversational AI with advanced routing techniques with Amazon Bedrock

Improve accuracy of Amazon Rekognition Face Search with user vectors

Use Kubernetes Operators for new inference capabilities in Amazon SageMaker that reduce LLM deployment costs by 50% on average

Cost-effective document classification using the Amazon Titan Multimodal Embeddings Model

Improving Content Moderation with Amazon Rekognition Bulk Analysis and Custom Moderation

Understanding and predicting urban heat islands at Gramener using Amazon SageMaker geospatial capabilities

Build a news recommender application with Amazon Personalize

Build a contextual text and image search engine for product recommendations using Amazon Bedrock and Amazon OpenSearch Serverless

Gradient makes LLM benchmarking cost-effective and effortless with AWS Inferentia