Even though I had opted out of performance measurement cookies, I noticed a lot of web requests that look like performance measurement in the AWS console. In this article I investigate what’s being sent and what we can do about it.
In this article, we’ll be using GenAI to generate alternative texts for images in Markdown documents, which will help people relying on screen readers to access your content.
Large language models (LLMs) can generate complex text and solve numerous tasks such as question-answering, information extraction, and text summarization. However, they may suffer from issues such as information gaps or hallucinations. In this blog article, we will explore how to mitigate these issues using Retrieval Augmented Generation (RAG) and build a low-cost solution in the process.
Imagine you’re managing an e-commerce platform with millions of products. Your search functionality is tightly coupled with your application code, making it challenging to update search logic without redeploying the entire application. This scenario illustrates the critical need for decoupling search logic in modern application development. This blog post explores how OpenSearch templates and aliases can address this challenge, offering practical strategies to enhance search performance and simplify maintenance.
In cloud computing, security is a critical concern. While AWS provides backup solutions for many resources, custom configurations often require additional protection. Two key services, AWS Key Management Service (KMS) and AWS Secrets Manager, don’t offer direct backup options. However, they implement a deletion grace period— by default 30 days and this is the maximum — allowing for potential restoration.
Amazon OpenSearch Service is a powerful tool for search, log analytics, and RAG (Retrieval-Augmented Generation) systems. To ensure optimal performance and reliability, effective monitoring is crucial.
10th of Juli: The ten new features, which were announced in AWS NY Summmit, show a trend in Amazon Bedrock: to implement Prompt Engineering Patterns as services. One of the best practices to avoid prompt injection attacks is GuardRails. Here, I do a deep dive into the new GuardRails features “contextual grounding filter” and “independent API to call your guardrails.” Note: Guardrails work ONLY with English currently.
Amazon SageMaker offers a highly customizable platform for machine learning at scale. Job execution within Amazon SageMaker can take some time to set up, which can be inconvenient or even time consuming during development and debugging phases. Running training and processing jobs locally can greatly increase the speed of development and debugging before running them at scale on AWS.
