Author: Jackie Chen

How to assume root user of an AWS account?


Due to that some tasks require root user credentials, from time to time we need to login into an AWS account as root, e.g removing a misconfigured S3 bucket policy which denies all principals. Conventionally, we login into the account from the AWS login console with root user email, password and MFA. Now, there is … Continue reading How to assume root user of an AWS account? →

Unleashing the Power of Generative AI: Building a Smart Image Library


In our ever-evolving digital landscape, managing and organising vast collections of images can be a daunting task. However, with the advent of Generative AI (GenAI), we now have the ability to revolutionise the way we interact with and search for images. In this blog, we'll explore how to harness the power of GenAI to build … Continue reading Unleashing the Power of Generative AI: Building a Smart Image Library →

Image-Reader: A project to explore Claude 3 Vision Capabilities


A week ago, AWS announced that Anthropic's Claude 3 Sonnet model now available on Amazon Bedrock. I am so eager to give it a try, especially its vision capabilities, as it is the first multimodal foundation model in Amazon Bedrock excluding embedding models. According to Anthropic's introduction, the Claude 3 family is smarter, faster and … Continue reading Image-Reader: A project to explore Claude 3 Vision Capabilities →

Increase max input length for HuggingFace model in SageMaker deployment


I deployed HuggingFace zephyr-7b-beta model to SageMaker by using the default deploy.py script. When trying to invoke the model endpoint, I received the error "ValueError: Error raised by inference endpoint: An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (422) from primary with message "{"error":"Input validation error: inputs must have less than … Continue reading Increase max input length for HuggingFace model in SageMaker deployment →