This repository houses the reference implementations for the Deployment of AI Models Bootcamp.
The Deployment of AI Models Bootcamp aims to introduce and explain the details of the different elements and concepts of a production AI model inferencing pipeline.
This repository contains reference implementations with terraform and python scripts to make online (real-time) and offline (batch) pipelines in cloud providers, as well as detailed instructions on how to upload models, configure and run the code, and testing the pipelines.
- reference_implementations/: Reference Implementations are organized by cloud provider. Each reference implementation has its own directory containing scripts, terraform plans, and a README for guidance.
- data/: Includes sample datasets or links to datasets used in the bootcamp, along with usage instructions. It also contains the implementation of dataset modules, and anything related to that.
Each cloud provider covered in the bootcamp has a dedicated directory in the
reference_implementations/ directory. In each directory, there is a README file
that provides an overview of the code, prerequisites, and detailed instructions.
Here is the list of the covered cloud providers:
To get started with this bootcamp:
- Clone this repository to your machine.
- Navigate to the directory of the cloud provider you are going to use
- Follow the instructions in the README file.
This project is licensed under the terms of the LICENSE.md file located in the root directory of this repository.
To get started with contributing to our project, please read our CONTRIBUTING.md guide.
For more information or help with navigating this repository, please contact Marcelo Lotif at marcelo.lotif@vectorinstitute.ai.