Building a Multi-Vector Semantic Video Search System with Amazon Nova Multimodal Embeddings ModelIntroduction3d ago3d ago
Naïve Novices, Complexity Oversimplification, Underestimation Bias, and Shallow Knowledge…Navigating the Dunning–Kruger Effect in the Age of Generative AIOct 27Oct 27
Building Smarter Content Recommendations with PCA, K-Means, and Generative AIHow Embeddings, Clustering, and Generative AI-Driven Labeling Reveal Semantic Relationships Between Streaming TitlesOct 19Oct 19
Published inITNEXTBuild a Web Research Agent with Strands Agents, Ollama, Qwen3, and the Tavily MCP ServerThis post guides you through building a web-based research agent using Strands Agents, Ollama running Qwen3, and the Tavily MCP Server…Sep 15Sep 15
Published inAWS in Plain EnglishMulti-Vector Semantic Search: Advanced Video Search with TwelveLabs and Amazon OpenSearchHow TwelveLabs AI Models and Amazon OpenSearch Serverless enable multi-vector semantic and hybrid search for video content.Jun 18A response icon1Jun 18A response icon1
Published inAWS in Plain EnglishAWS Strands Agents: Building and Connecting Your First Model Context Protocol (MCP) ServerDeploy an MCP server that searches for stock photography based on your current location and weather conditions using third-party APIs, and…Jun 2A response icon2Jun 2A response icon2
Introducing AWS Strands Agents: A New Paradigm in AI Agent DevelopmentCreate a Perplexity-like web search agent using Strands Agents and Amazon Bedrock SoTA foundation models, including Anthropic Claude Sonnet…May 27A response icon3May 27A response icon3
Finding Your LLM’s Breaking Point: Load Testing SageMaker Real-time Inference Endpoints with LocustLearn how variables such as model size, instance choice, deployment configuration, and inference parameters impact peak requests-per-second…May 25May 25
Supervised Fine-tuning of Small Language Models using Agentic DUKE-based Model Distillation and…Fine-tune Meta’s lightweight Llama small language models using Agent-based Document Understanding and Knowledge Extraction (DUKE) with…May 15May 15
Automatic Speech Recognition (ASR) and Speech Translation Models for Batch Video Transcription and…Master the use of compact, open-weight transformer models tailored for specific tasks to efficiently transcribe and translate speech from…Apr 16Apr 16