Category: Advanced (300)

Ray is an open source framework that makes it straightforward to create, deploy, and optimize distributed Python jobs. In this post, we demonstrate the steps involved in running Ray jobs on SageMaker HyperPod.

In this post, we explore practical strategies for using Constitutional AI to produce compliant content efficiently and effectively using HAQM Bedrock and LangGraph to build ConstitutionalChain for rapid content creation in highly regulated industries like finance and healthcare

To improve factual accuracy of large language model (LLM) responses, AWS announced HAQM Bedrock Automated Reasoning checks (in gated preview) at AWS re:Invent 2024. In this post, we discuss how to help prevent generative AI hallucinations using HAQM Bedrock Automated Reasoning checks.

In this post, we explore how you can use these multi-modal generative AI models to streamline the management of technical documents. By extracting and structuring the key information from the source materials, the models can create a searchable knowledge base that allows you to quickly locate the data, formulas, and visualizations you need to support your work.

This post focuses on RAG evaluation with HAQM Bedrock Knowledge Bases, provides a guide to set up the feature, discusses nuances to consider as you evaluate your prompts and responses, and finally discusses best practices. By the end of this post, you will understand how the latest HAQM Bedrock evaluation features can streamline your approach to AI quality assurance, enabling more efficient and confident development of RAG applications.

In this post, we walk through how to build the FoodSavr solution (fictitious name used for the purposes of this post) using HAQM Rekognition Custom Labels to detect the ingredients and generate personalized recipes using Anthropic’s Claude 3.0 on HAQM Bedrock. We demonstrate an end-to-end architecture where a user can upload an image of their fridge, and using the ingredients found there (detected by HAQM Rekognition), the solution will give them a list of recipes (generated by HAQM Bedrock). The architecture also recognizes missing ingredients and provides the user with a list of nearby grocery stores.

In this post, we explain how BMW uses generative AI to speed up the root cause analysis of incidents in complex and distributed systems in the cloud such as BMW’s Connected Vehicle backend serving 23 million vehicles. Read on to learn how the solution, collaboratively pioneered by AWS and BMW, uses HAQM Bedrock Agents and HAQM CloudWatch logs and metrics to find root causes quicker. This post is intended for cloud solution architects and developers interested in speeding up their incident workflows.

In this two-part series, we discuss how you can reduce the DeepSeek model customization complexity by using the pre-built fine-tuning workflows (also called “recipes”) for both DeepSeek-R1 model and its distilled variations, released as part of HAQM SageMaker HyperPod recipes. In this first post, we will build a solution architecture for fine-tuning DeepSeek-R1 distilled models and demonstrate the approach by providing a step-by-step example on customizing the DeepSeek-R1 Distill Qwen 7b model using recipes, achieving an average of 25% on all the Rouge scores, with a maximum of 49% on Rouge 2 score with both SageMaker HyperPod and SageMaker training jobs. The second part of the series will focus on fine-tuning the DeepSeek-R1 671b model itself.

In this guide, we walk you through step-by-step instructions for configuring cross-account access for HAQM Bedrock Custom Model Import, covering both non-encrypted and AWS Key Management Service (AWS KMS) based encrypted scenarios.

In this post, we share how we modernized Rocket Companies’ data science solution on AWS to increase the speed to delivery from eight weeks to under one hour, improve operational stability and support by reducing incident tickets by over 99% in 18 months, power 10 million automated data science and AI decisions made daily, and provide a seamless data science development experience.