Skip to content Skip to sidebar Skip to footer

Intermediate (200)

Create confidential and safe corporate generative AI applications using Amazon Q Business and AWS IAM Identity Center.

Launched on April 30, 2024, Amazon Q Business is a conversational assistant using generative artificial intelligence (AI) to improve workforce productivity by answering queries and completing tasks based on information from your enterprise systems. Employees can access enterprise content securely and privately via web applications developed with Amazon Q Business. The functionality of the system…

Read More

Developing scalable, safe and dependable RAG applications using Knowledge Bases for Amazon Bedrock

Generative artificial intelligence (AI) is advancing rapidly, and organizations are exploring its potential applications. To ensure long-term success of AI-powered systems, it is essential to align them with well-established architectural principles. In this sense, the Amazon Web Services (AWS) Well-Architected Framework offers valuable guidelines for designing and operating reliable, secure, efficient, and cost-effective systems in…

Read More

Slack provides an original and secure AI system, powered by Amazon’s SageMaker JumpStart.

Slack, now part of Salesforce, has joined forces with Amazon SageMaker JumpStart to introduce AI services that will improve data searching, summarization, and security for users. The collaboration involves leveraging SageMaker JumpStart's large language models (LLMs) in a way that data stays within Slack's infrastructure and does not get shared with external model providers. The…

Read More

Create personalized, compliant Infrastructure as Code (IaC) scripts for AWS Landing Zone utilizing Amazon Bedrock.

Cloud adoption is a major goal for many organizations today, but it can be a complex and daunting journey. Adopting Infrastructure as Code (IaC) tools like Terraform and AWS CloudFormation can simplify the process by allowing businesses to define and manage their cloud environments. However, such tools often require time and resources to learn, which…

Read More

Efficient scalability and distributed training using the Model Parallel and Data Parallel Libraries of Amazon SageMaker.

Distributed deep learning for extensive language models (LLMs) continues to make considerable advancements, primarily since the unveiling of ChatGPT in 2022. These models continue to grow with billions or trillions of parameters, which often cannot fit within a single acceleration device or node due to memory constraints. Hence, customers must distribute their workloads across hundreds…

Read More