Machine Learning Model Release Definition Templates

hashicorp-aws offers a Screwdriver template that deploys immutable instances of Machine Learning models as REST API to AWS. It uses the screwdriver-template-main npm package to assist with template validation, publishing, and tagging.

This release definition contains the following templates:

• Deploying ML models via MLflow Docker container

All templates tag the latest versions with the latest tag.

How to Use the Templates

Using the Template

Create a Screwdriver pipeline that uses this template with the following contents:

---
jobs:
  main:
    requires: [~pr, ~commit]
    template: QubitPi/machine-learning-model-release-definition-template-mlflow-docker@latest
    steps:
      - build-ml-models: ...
    secrets:
      - AWS_ACCESS_KEY_ID
      - AWS_SECRET_ACCESS_KEY
      - AWS_ML_PKRVARS_HCL
      - AWS_ML_TFVARS

The following Screwdriver CD - steps must be implemented:

• build-ml-models - Commands that package up MLflow Python models

The following Screwdriver Secrets needs to be defined before running this template:

• AWS_ACCESS_KEY_ID

• AWS_SECRET_ACCESS_KEY

• AWS_ML_PKRVARS_HCL - A HashiCorp Packer variable values file with the following variable values:

  aws_image_region = "us-east-2"
  ami_name         = "my-ml-ami"
  instance_type    = "t2.small"
  ml_models_path   = "/home/my-nlp-models"
  • aws_image_region is the image region of AWS AMI
  • ami_name is the name of the resulting AMI that will appear when managing AMIs in the AWS console or via APIs. This can be the same across builds, because hashicorp-aws will deregister the old AMI with the same name and replace it with the current built one
  • instance_type is the recommended AWS EC2 instance type running this image
  • ml_models_path is the absolute path to the model directory generated by the build-ml-models step above

• AWS_ML_TFVARS - A HashiCorp Terraform variable values file with the following variable values:

  aws_ec2_region   = "us-east-2"
  ami_name            = "my-ml-ami"
  instance_type       = "t2.small"
  ec2_instance_name   = "My Machine Learning REST Service"
  ec2_security_groups = ["ML REST Service Security Group"]
  • aws_ec2_region is the EC2 runtime region
  • ami_name is the name of the published AMI; it must be the same as the ami_name in AWS_ML_PKRVARS_HCL
  • instance_type is the AWS EC2 instance type used for deployed infrastructure
  • ec2_instance_name is the deployed EC2 name as appeared in the instance list of AWS console; it can be arbitrary
  • ec2_security_groups is the AWS Security Group name (yes, not ID, but name...)