Create a multimodal assistant with advanced RAG and Amazon Bedrock

Retrieval Augmented Generation (RAG) models have emerged as a promising approach to enhance the capabilities of language models by incorporating external knowledge from large text corpora. However, despite their impressive performance in various natural language processing tasks, RAG models still face several limitations that need to be addressed. Naive RAG models face limitations such as…

How 20 Minutes empowers journalists and boosts audience engagement with generative AI on Amazon Bedrock

This post is co-written with Aurélien Capdecomme and Bertrand d’Aure from 20 Minutes. With 19 million monthly readers, 20 Minutes is a major player in the French media landscape. The media organization delivers useful, relevant, and accessible information to an audience that consists primarily of young and active urban readers. Every month, nearly 8.3 million 25–49-year-olds choose…

Efficient and cost-effective multi-tenant LoRA serving with Amazon SageMaker

In the rapidly evolving landscape of artificial intelligence (AI), the rise of generative AI models has ushered in a new era of personalized and intelligent experiences. Organizations are increasingly using the power of these language models to drive innovation and enhance their services, from natural language processing to content generation and beyond. Using generative AI…

Robot-phobia could exasperate hotel, restaurant labor shortage

Using more robots to close labor gaps in the hospitality industry may backfire and cause more human workers to quit, according to a new study. The study, involving more than 620 lodging and food service employees, found that ‘robot-phobia’ — specifically the fear that robots and technology will take human jobs — increased workers’ job…

Building a better sarcasm detector

Sarcasm is notoriously tricky to convey through text, and the subtle changes in tone that convey sarcasm often confuse computer algorithms as well, limiting virtual assistants and content analysis tools. So researchers have now developed a multimodal algorithm for improved sarcasm detection that examines multiple aspects of audio recordings for increased accuracy. They used two…

Building Generative AI prompt chaining workflows with human in the loop

Generative AI is a type of artificial intelligence (AI) that can be used to create new content, including conversations, stories, images, videos, and music. Like all AI, generative AI works by using machine learning models—very large models that are pretrained on vast amounts of data called foundation models (FMs). FMs are trained on a broad…

Mixtral 8x22B is now available in Amazon SageMaker JumpStart

Today, we are excited to announce the Mixtral-8x22B large language model (LLM), developed by Mistral AI, is available for customers through Amazon SageMaker JumpStart to deploy with one click for running inference. You can try out this model with SageMaker JumpStart, a machine learning (ML) hub that provides access to algorithms and models so you…

Large language models can’t effectively recognize users’ motivation, but can support behavior change for those ready to act

Large language model-based chatbots can’t effectively recognize users’ motivation when they are hesitant about making healthy behavior changes, but they can support those who are committed to take action, say researchers.

How LotteON built a personalized recommendation system using Amazon SageMaker and MLOps

This post is co-written with HyeKyung Yang, Jieun Lim, and SeungBum Shim from LotteON. LotteON aims to be a platform that not only sells products, but also provides a personalized recommendation experience tailored to your preferred lifestyle. LotteON operates various specialty stores, including fashion, beauty, luxury, and kids, and strives to provide a personalized shopping…