Skip to content

CLI tool for deploying ML models in the cloud - built on top of BentoML 🚀

License

Notifications You must be signed in to change notification settings

atalaya-io/bentoctl

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

bentoctl

Best way to deploy BentoML to the cloud.

PyPI GitHub branch checks state Codecov


bentoctl is a command-line tool that uses easy and approachable YAML syntax to deploy Bento to the cloud. It supports multiple cloud providers, including AWS, Azure, Google Cloud, and more. It is completely extensible with operators that can add more cloud providers, uses-cases and workflows.

demo of bentoctl deploying to AWS-EC2

Quick Start

Installing

pip install bentoctl

To activate tab completion for you shell, source the script in bentoctl/completion. For More info please check click's documentation

Add AWS EC2 operator

bentoctl operators add aws-ec2

Deploy Bento to EC2

Use the interactive deployment helper. This will generate a deployment YAML file and will then deploy the Bento to the cloud.

$ bentoctl deploy

bentoctl deploy also accepts deployment configuration file.

Save the following configuration file to deployment_config.yaml

api_version: v1
metadata:
  name: my-bento-deployment
  operator: aws-ec2
spec:
  bento: iris_classifier:latest
  region: us-west-1
  instance_type: t2.micro
  ami_id: /aws/service/ami-amazon-linux-latest/amzn2-ami-hvm-x86_64-gp2
  enable_gpus: False

Call deploy command

$ bentoctl deploy deployment_config.yaml

Delete deployment

$ bentoctl delete deployment_config.yaml

Features:

  • Supports multiple cloud providers: AWS, Azure, Google Cloud, and more.
  • Manages the lifecycle of the BentoML deployment.
  • Minimal configuration
  • Optimized for CI/CD workflow
  • Built with optimization and best practices
  • Extensible with operators. Extends or modifies the cloud services and workflow via operators.

About

CLI tool for deploying ML models in the cloud - built on top of BentoML 🚀

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 90.0%
  • Shell 9.8%
  • Batchfile 0.2%