engblogs

Deploy Meta Llama 3.1-8B on AWS Inferentia using Amazon EKS and vLLM

Intervening to reduce hallucinations in large language models using Amazon Bedrock Agents

Leverage the Amazon Q Salesforce Online connector to unleash the value of Salesforce data with generative AI assistance

Explore building an autonomous AI assistant with Mosaic AI Agent Framework and large language models for advanced natural language processing tasks.

Leveraging Large Language Models (LLMs) with Amazon Bedrock and Amazon SageMaker for bolstering cybersecurity defenses, with a focus on tasks such as query generation, incident severity prediction, and incident summarization from incoming incidents.

Incident analysis and prevention strategies after Cloudflare's log loss incident on November 14, 2024

Explore how Crexi implemented ML models deployment at scale on AWS to enhance efficiency

Extract information from graphs, diagrams, tables, and scanned pages using multimodal prompts in Amazon Bedrock

Rad AI showcases how to reduce real-time inference latency by 50% using Amazon SageMaker in healthcare ML models deployment

Optimize LLM-based AI applications with a serverless read-through semantic cache using Amazon OpenSearch Serverless and Amazon Bedrock

Guide on setting up lifecycle configurations for Amazon SageMaker Studio using AWS CDK

Build a virtual stock technical analyst with Amazon Bedrock Agents