End-to-end examples

A series of notebooks demonstrating end-to-end integrations from various model serving platforms

The following guide will leverage our public integration repository and demonstrate end-to-end integration examples. To use the code snippet, clone the repository to your local machine and use the relevant notebook.

To download the repository please run the following steps:

git clone https://github.com/superwise-ai/quickstart.git
cd getting_started

All code examples use public datasets. There's no need to download them, the code includes the retrieval of each dataset.

The notebooks below contain two main parts. First, download the example data, train an ML model, and deploy it. Then the second part will connect the actual integration code to integrate the new deployed model into Superwise.

Integrate with AWS Sagemaker

This notebook demonstrates how to connect an ML model that you've developed with AWS Sagemaker into Superwise.

The dataset used in this notebook is a public dataset called "Diamonds" and is usually used for classification tasks. To read more about the diamonds dataset, see here.

Integrate with Google Vertex

This notebook demonstrates how to connect an ML model that you developed with Google Vertex into Superwise.

The dataset used in this notebook is a public dataset called "Titanic" and is usually being used for classification tasks. To read more about the Titanic dataset, visit here.

Run everywhere

This is a generic notebook that demonstrates how to connect an ML model that you developed into Superwise. This example is generic because it's assumes nothing regarding the platform that the model is being deployed on.

The dataset used in this notebook is a public dataset called "Diamonds" and is usually being used for classification tasks. To read more about the diamonds dataset, visit here.