Tools

Accelerated PyTorch inference with torch.compile on AWS...

Originally PyTorch used an eager mode where each PyTorch operation that forms th...

Create an end-to-end serverless digital assistant for s...

With the rise of generative artificial intelligence (AI), an increasing number o...

Accenture creates a custom memory-persistent conversati...

Traditionally, finding relevant information from documents has been a time-consu...

Indian language RAG with Cohere multilingual embeddings...

Media and entertainment companies serve multilingual audiences with a wide range...

Identify idle endpoints in Amazon SageMaker

Amazon SageMaker is a machine learning (ML) platform designed to simplify the pr...

Build a self-service digital assistant using Amazon Lex...

Organizations strive to implement efficient, scalable, cost-effective, and autom...

The future of productivity agents with NinjaTech AI and...

NinjaTech AI’s mission is to make everyone more productive by taking care of tim...

Build generative AI applications on Amazon Bedrock — th...

Generative AI has revolutionized industries by creating content, from text and i...

Build a conversational chatbot using different LLMs wit...

With the advent of generative artificial intelligence (AI), foundation models (F...

AI-powered assistants for investment research with mult...

This post is a follow-up to Generative AI and multi-modal agents in AWS: The key...

Automate derivative confirms processing using AWS AI se...

In this post, we show how you can automate and intelligently process derivative ...

AI21 Labs Jamba-Instruct model is now available in Amaz...

We are excited to announce the availability of the Jamba-Instruct large language...

Scale and simplify ML workload monitoring on Amazon EKS...

Amazon Web Services is excited to announce the launch of the AWS Neuron Monitor ...

Improve visibility into Amazon Bedrock usage and perfor...

In this blog post, we will share some of capabilities to help you get quick and ...

Build safe and responsible generative AI applications w...

Large language models (LLMs) enable remarkably human-like conversations, allowin...

Build an automated insight extraction framework for cus...

In this post, we explore how to integrate LLMs into enterprise applications to h...

浮动元件示例