AWS Machine Learning Blog

Empowering everyone with GenAI to rapidly build, customize, and deploy apps securely: Highlights from the AWS New York Summit

See how AWS is democratizing generative AI with innovations like Amazon Q Apps to make AI apps from prompts, Amazon Bedrock upgrades to leverage more data sources, new techniques to curtail hallucinations, and AI skills training.

Unleash your Salesforce data using the Amazon Q Salesforce Online connector

In this post, we walk you through configuring and setting up the Amazon Q Salesforce Online connector. Thousands of companies worldwide use Salesforce to manage their sales, marketing, customer service, and other business operations. The Salesforce cloud-based platform centralizes customer information and interactions across the organization, providing sales reps, marketers, and support agents with a unified 360-degree view of each customer. With Salesforce at the heart of their business, companies accumulate vast amounts of customer data within the platform over time. This data is incredibly valuable for gaining insights into customers, improving operations, and guiding strategic decisions. However, accessing and analyzing the blend of structured data and unstructured data can be challenging. With the Amazon Q Salesforce Online connector, companies can unleash the value of their Salesforce data.

Flow diagram of custom hallucination detection and mitigation : The user's question is fed to a search engine (with optional LLM-based step to pre-process it to a good search query). The documents or snippets returned by the search engine, together with the user's question, are inserted into a prompt template - and an LLM generates a final answer based on the retrieved documents. The final answer can be evaluated against the reference answer from the dataset to get a custom hallucination score. Based on a pre-defined empirical threshold, a customer service agent is requested to join the conversation using SNS notification

Reducing hallucinations in large language models with custom intervention using Amazon Bedrock Agents

This post demonstrates how to use Amazon Bedrock Agents, Amazon Knowledge Bases, and the RAGAS evaluation metrics to build a custom hallucination detector and remediate it by using human-in-the-loop. The agentic workflow can be extended to custom use cases through different hallucination remediation techniques and offers the flexibility to detect and mitigate hallucinations using custom actions.

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

In this post, we walk through the steps to deploy the Meta Llama 3.1-8B model on Inferentia 2 instances using Amazon EKS. This solution combines the exceptional performance and cost-effectiveness of Inferentia 2 chips with the robust and flexible landscape of Amazon EKS. Inferentia 2 chips deliver high throughput and low latency inference, ideal for LLMs.

Serving LLMs using vLLM and Amazon EC2 instances with AWS AI chips

The use of large language models (LLMs) and generative AI has exploded over the last year. With the release of powerful publicly available foundation models, tools for training, fine tuning and hosting your own LLM have also become democratized. Using vLLM on AWS Trainium and Inferentia makes it possible to host LLMs for high performance […]

Using LLMs to fortify cyber defenses: Sophos’s insight on strategies for using LLMs with Amazon Bedrock and Amazon SageMaker

In this post, SophosAI shares insights in using and evaluating an out-of-the-box LLM for the enhancement of a security operations center’s (SOC) productivity using Amazon Bedrock and Amazon SageMaker. We use Anthropic’s Claude 3 Sonnet on Amazon Bedrock to illustrate the use cases.

Enhanced observability for AWS Trainium and AWS Inferentia with Datadog

This post walks you through Datadog’s new integration with AWS Neuron, which helps you monitor your AWS Trainium and AWS Inferentia instances by providing deep observability into resource utilization, model execution performance, latency, and real-time infrastructure health, enabling you to optimize machine learning (ML) workloads and achieve high-performance at scale.

Create a virtual stock technical analyst using Amazon Bedrock Agents

n this post, we create a virtual analyst that can answer natural language queries of stocks matching certain technical indicator criteria using Amazon Bedrock Agents.

Apply Amazon SageMaker Studio lifecycle configurations using AWS CDK

This post serves as a step-by-step guide on how to set up lifecycle configurations for your Amazon SageMaker Studio domains. With lifecycle configurations, system administrators can apply automated controls to their SageMaker Studio domains and their users. We cover core concepts of SageMaker Studio and provide code examples of how to apply lifecycle configuration to […]

Build a read-through semantic cache with Amazon OpenSearch Serverless and Amazon Bedrock

This post presents a strategy for optimizing LLM-based applications. Given the increasing need for efficient and cost-effective AI solutions, we present a serverless read-through caching blueprint that uses repeated data patterns. With this cache, developers can effectively save and access similar prompts, thereby enhancing their systems’ efficiency and response times.

Rad AI reduces real-time inference latency by 50% using Amazon SageMaker

This post is co-written with Ken Kao and Hasan Ali Demirci from Rad AI. Rad AI has reshaped radiology reporting, developing solutions that streamline the most tedious and repetitive tasks, and saving radiologists’ time. Since 2018, using state-of-the-art proprietary and open source large language models (LLMs), our flagship product—Rad AI Impressions— has significantly reduced the […]