AWS Machine Learning Blog
Tag: HAQM OpenSearch Service
Implement semantic video search using open source large vision models on HAQM SageMaker and HAQM OpenSearch Serverless
In this post, we demonstrate how to use large vision models (LVMs) for semantic video search using natural language and image queries. We introduce some use case-specific methods, such as temporal frame smoothing and clustering, to enhance the video search performance. Furthermore, we demonstrate the end-to-end functionality of this approach by using both asynchronous and real-time hosting options on HAQM SageMaker AI to perform video, image, and text processing using publicly available LVMs on the Hugging Face Model Hub. Finally, we use HAQM OpenSearch Serverless with its vector engine for low-latency semantic video search.
Build a reverse image search engine with HAQM Titan Multimodal Embeddings in HAQM Bedrock and AWS managed services
In this post, you will learn how to extract key objects from image queries using HAQM Rekognition and build a reverse image search engine using HAQM Titan Multimodal Embeddings from HAQM Bedrock in combination with HAQM OpenSearch Serverless Service.
Create a generative AI-based application builder assistant using HAQM Bedrock Agents
Agentic workflows are a fresh new perspective in building dynamic and complex business use- case based workflows with the help of large language models (LLM) as their reasoning engine or brain. In this post, we set up an agent using HAQM Bedrock Agents to act as a software application builder assistant.