• Machine learning deserves its own flavor of Continuous Delivery

    By Derek Haynes
    blog image

    Things feel slightly different - but eerily similar - when traveling through Canada as an American. The red vertical lines on McDonald's straws are a bit thicker, for example. It's a lot like my travels through the world of data science as a software engineer.

  • How to setup a local AWS SageMaker environment for PyTorch

    By Derek Haynes
    blog image

    As a hack data scientist but mostly-legit web developer, I’m frustrated with the process of creating an ML application (a simple UI to trigger predictions and a publicly accessible API). The flow for creating and iterating on a typical web application feels like driving down a low-traffic, gently curving country road on a spring day. The ML app dev flow? It’s like learning how to drive a car with a manual transmission.

  • How to integrate AWS Sagemaker with AWS Redshift

    By Adam Barnhard
    blog image

    Sending predictions from your AWS Sagemaker model to your AWS Redshift database can be a complex process requiring multiple steps. Booklet.ai makes it simple to integrate with your data warehouse quickly.

  • Turn a ML Model into a fully integrated web app with Booklet.ai

    By Adam Barnhard
    blog image

    From small-scale ML models in graduate school to massive-scale systems at Uber, I’ve trained a lot of Machine Learning models. No matter the model, it’s magical when months of work condense down to a single predict function call.

  • How to create a REST API for a AWS Sagemaker Endpoint (quickly)

    By Derek Haynes
    blog image

    Creating an HTTP API on AWS requires binding 4 or more AWS services together. Learn how to create a free HTTP API for a Sagemaker Endpoint using just Booklet.ai.

  • Create a web app for your AWS Sagemaker ML model (quickly)

    By Derek Haynes
    blog image

    You’ve painstakingly trained and evaluated your machine learning model in Jupyter notebooks. You’ve deployed the model to AWS Sagemaker. Now, your developer friends and higher-ups are anxious to see your model in action.