Reduce ML training costs with Amazon SageMaker HyperPod

Training a frontier model is highly compute-intensive, requiring a distributed system of hundreds, or thousands, of accelerated instances running for several weeks or months to complete a single job. For example, pre-training the Llama 3 70B model with 15 trillion training tokens took 6.5 million H100 GPU hours. On 256 Amazon EC2 P5 instances (p5.48xlarge, […]

Model customization, RAG, or both: A case study with Amazon Nova

As businesses and developers increasingly seek to optimize their language models for specific tasks, the decision between model customization and Retrieval Augmented Generation (RAG) becomes critical. In this post, we seek to address this growing need by offering clear, actionable guidelines and best practices on when to use each approach, helping you make informed decisions […]

Generate user-personalized communication with Amazon Personalize and Amazon Bedrock

Today, businesses are using AI and generative models to improve productivity in their teams and provide better experiences to their customers. Personalized outbound communication can be a powerful tool to increase user engagement and conversion. For instance, as a marketing manager for a video-on-demand company, you might want to send personalized email messages tailored to […]

Automating regulatory compliance: A multi-agent solution using Amazon Bedrock and CrewAI

Financial institutions today face an increasingly complex regulatory world that demands robust, efficient compliance mechanisms. Although organizations traditionally invest countless hours reviewing regulations such as the Anti-Money Laundering (AML) rules and the Bank Secrecy Act (BSA), modern AI solutions offer a transformative approach to this challenge. By using Amazon Bedrock Knowledge Bases alongside CrewAI—an open […]

Pixtral Large is now available in Amazon Bedrock

Today, we are excited to announce that Mistral AI’s Pixtral Large foundation model (FM) is generally available in Amazon Bedrock. With this launch, you can now access Mistral’s frontier-class multimodal model to build, experiment, and responsibly scale your generative AI ideas on AWS. AWS is the first major cloud provider to deliver Pixtral Large as […]

Implement human-in-the-loop confirmation with Amazon Bedrock Agents

Agents are revolutionizing how businesses automate complex workflows and decision-making processes. Amazon Bedrock Agents helps you accelerate generative AI application development by orchestrating multi-step tasks. Agents use the reasoning capability of foundation models (FMs) to break down user-requested tasks into multiple steps. In addition, they use the developer-provided instruction to create an orchestration plan and […]

Boost team productivity with Amazon Q Business Insights

Employee productivity is a critical factor in maintaining a competitive advantage. Amazon Q Business offers a unique opportunity to enhance workforce efficiency by providing AI-powered assistance that can significantly reduce the time spent searching for information, generating content, and completing routine tasks. Amazon Q Business is a fully managed, generative AI-powered assistant that lets you […]

Multi-LLM routing strategies for generative AI applications on AWS

Organizations are increasingly using multiple large language models (LLMs) when building generative AI applications. Although an individual LLM can be highly capable, it might not optimally address a wide range of use cases or meet diverse performance requirements. The multi-LLM approach enables organizations to effectively choose the right model for each task, adapt to different […]