Category: Learning Levels

This post introduces a solution to reduce hallucinations in Large Language Models (LLMs) by implementing a verified semantic cache using Amazon Bedrock Knowledge Bases, which checks if user questions match curated and verified responses before generating new answers. The solution combines the flexibility of LLMs with reliable, verified answers to improve response accuracy, reduce latency, and lower costs while preventing potential misinformation in critical domains such as healthcare, finance, and legal services.

In this post, we present the continuous self-instruct fine-tuning framework as a compound AI system implemented by the DSPy framework. The framework first generates a synthetic dataset from the domain knowledge base and documents for self-instruction, then drives model fine-tuning through SFT, and introduces the human-in-the-loop workflow to collect human and AI feedback to the model response, which is used to further improve the model performance by aligning human preference through reinforcement learning (RLHF/RLAIF).

In this post, we show you how to connect Amazon Q, a generative AI-powered assistant, to Amazon FSx for Windows File Server to securely analyze, query, and extract insights from your file system data.

In this post, we explore how you can use LLMs with advanced Retrieval Augmented Generation (RAG) to generate high-quality synthetic data for a finance domain use case. You can use the same technique for synthetic data for other business domain use cases as well. For this post, we demonstrate how to generate counterparty risk (CR) data, which would be beneficial for over-the-counter (OTC) derivatives that are traded directly between two parties, without going through a formal exchange.

In this post, we provide best practices to maximize the value of SageMaker HyperPod task governance and make the administration and data science experiences seamless. We also discuss common governance scenarios when administering and running generative AI development tasks.

To better protect themselves, many cyclists are starting to ride with cameras mounted to the front or back of their bicycle. In this blog post, I will demonstrate a machine learning solution that cyclists can use to better identify close calls. The architecture of the solution uses Amazon Rekognition to detect vehicles in recorded bike ride videos. It then analyzes the video to determine if any vehicles are passing too close to the cyclist, within the 3-foot safe distance required by law. The solution automatically generates video clips of these dangerous passing events, which can then be shared with authorities to help improve cyclist safety.

In this post, we explore how to use Amazon Bedrock to generate synthetic training data to fine-tune an LLM. Additionally, we provide concrete evaluation results that showcase the power of synthetic data in fine-tuning when data is scarce.

Researchers developed Medusa, a framework to speed up LLM inference by adding extra heads to predict multiple tokens simultaneously. This post demonstrates how to use Medusa-1, the first version of the framework, to speed up an LLM by fine-tuning it on Amazon SageMaker AI and confirms the speed up with deployment and a simple load test. Medusa-1 achieves an inference speedup of around two times without sacrificing model quality, with the exact improvement varying based on model size and data used. In this post, we demonstrate its effectiveness with a 1.8 times speedup observed on a sample dataset.

This blog post explores LLM-as-a-judge on Amazon Bedrock Model Evaluation, providing comprehensive guidance on feature setup, evaluating job initiation through both the console and Python SDK and APIs, and demonstrating how this innovative evaluation feature can enhance generative AI applications across multiple metric categories including quality, user experience, instruction following, and safety.

In this post, we present a streamlined approach to deploying an AI-powered agent by combining Amazon Bedrock Agents and a foundation model (FM). We guide you through the process of configuring the agent and implementing the specific logic required for the virtual meteorologist to provide accurate weather-related responses.