AWS Lambda ML Model Deployment

Deploying an ML model in AWS Lambda.

This code is used in this blog post.

Requirements

This project requires the serverless framework, which itself requires the node.js framework.

In order to create the lambda deployment package, the serverless-python-requirements extension for serverless must be installed.

In order to compile the packages in the lambda deployment package docker needs to be installed.

Installation

The makefile included with this project contains targets that help to automate several tasks.

To download the source code execute this command:

git clone https://github.com/schmidtbri/lambda-ml-model-deployment

Then create a virtual environment and activate it:

# go into the project directory
cd lambda-ml-model-deployment

make venv

source venv/bin/activate

Install the dependencies:

make dependencies

Running the unit tests

To run the unit test suite execute these commands:

# first install the test dependencies
make test-dependencies

# run the test suite
make test