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
Tag: AWS
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
Build EKS with EKS Blueprints
I have created the eks-blueprints-demo repository to demonstrate how to quickly bootstrap a new EKS cluster by using EKS Blueprints.
Masking PII Image with Slack Bot
A few months back, I introduced this project which masks texts in an image by utilizing a couple of AWS ML services (Rekognition, Textract and Comprehend). There are many use cases for such tooling, so last week I presented to my team with a live demo - Masking sensitive information in Slack with mask-it bot. … Continue reading Masking PII Image with Slack Bot
Learning AWS Landing Zone Accelerator (LZA) as a Developer
From a developer's perspective, LZA is an abstraction layer which hides the complexity of setting up a landing zone on AWS. This is especially useful for the customers who are new to AWS, as they don't necessarily need to have expertise in CloudFormation, CDK and AWS SDK to setup a landing zone with LZA. All they need to maintain are just a few configuration files.