Prompt Engineering Patterns for Successful RAG Implementations
You know it as well as I do: people are relying more and more on generative AI and large language models (LLM) for quick and easy information acquisition.
ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning
Humanoid robots have significant gaps in their sensing and perception, making it hard to perform motion planning in dense environments. To address this, we introduce ARMOR, a novel egocentric perception system that integrates both hardware and software, specifically incorporating wearable-like depth sensors for humanoid robots. Our distributed perception approach enhances the robot’s spatial awareness, and …
Read more “ARMOR: Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning”
Build a dynamic, role-based AI agent using Amazon Bedrock inline agents
AI agents continue to gain momentum, as businesses use the power of generative AI to reinvent customer experiences and automate complex workflows. We are seeing Amazon Bedrock Agents applied in investment research, insurance claims processing, root cause analysis, advertising campaigns, and much more. Agents use the reasoning capability of foundation models (FMs) to break down …
Read more “Build a dynamic, role-based AI agent using Amazon Bedrock inline agents”
Operationalizing generative AI apps with Apigee
Generative AI is now well beyond the hype and into the realm of practical application. But while organizations are eager to build enterprise-ready gen AI solutions on top of large language models (LLMs), they face challenges in managing, securing, and scaling these deployments, especially when it comes to APIs. As part of the platform team, …
AI’s biggest obstacle? Data reliability. Astronomer’s new platform tackles the challenge
Astronomer launches Astro Observe, an AI-powered data observability platform that combines orchestration and monitoring.Read More
Implementing Multi-Modal RAG Systems
Large language models (LLMs) have evolved and permeated our lives so much and so quickly that many we have become dependent on them in all sorts of scenarios.
Findings of the IWSLT 2024 Evaluation Campaign
Ibrahim Said Ahmad†, Antonios Anastasopoulos††††, Ondřej Bojar¶, Claudia Borg††, Marine Carpuat‡, Roldano Cattoni§, Mauro Cettolo§, William Chen‡‡, Qianqian Dong¶¶, Marcello Federico§§, Barry Haddow‡‡‡, Dávid Javorsky¶, Mateusz Krubiński¶, Tsz Kin Lam‡‡‡, Xutai Ma‡‡§, Prashant Mathur§§, Evgeny Matusov¶¶¶, Chandresh Kumar Maurya¶¶†, John P. McCrae†††, Kenton Murray†††, Satoshi Nakamura§§§, Matteo Negri§, Jan Niehues††¶, Xing Niu§§, Atul Kr. Ojha†††, …
Fine-tune LLMs with synthetic data for context-based Q&A using Amazon Bedrock
There’s a growing demand from customers to incorporate generative AI into their businesses. Many use cases involve using pre-trained large language models (LLMs) through approaches like Retrieval Augmented Generation (RAG). However, for advanced, domain-specific tasks or those requiring specific formats, model customization techniques such as fine-tuning are sometimes necessary. Amazon Bedrock provides you with the …
Read more “Fine-tune LLMs with synthetic data for context-based Q&A using Amazon Bedrock”
What Are Foundation Models?
Editor’s note: This article, originally published on March 13, 2023, has been updated. The mics were live and tape was rolling in the studio where the Miles Davis Quintet was recording dozens of tunes in 1956 for Prestige Records. When an engineer asked for the next song’s title, Davis shot back, “I’ll play it, and …
Too many models, too much confusion: OpenAI pledges to simplify its product line
Altman is the rare CEO to admit that the number of models the company released has made their core products more complicated to use.Read More