Katana ML Skipper

This is a simple and flexible ML workflow engine. It helps to orchestrate events across a set of microservices and create executable flow to handle requests. Engine is designed to be configurable with any microservises. Enjoy!

Author

Katana ML, Andrej Baranovskij

Instructions

Start/Stop

docker-compose up --build -d
docker-compose down

This will start RabbitMQ container. To run engine and services, navigate to related folders and follow instructions.

Web API FastAPI endpoint:

http://127.0.0.1:8000/docs

Components

api - Web API implementation
workflow - workflow logic
services - a set of microservices
rabbitmq - service for RabbitMQ broker
skipper-lib - reusable Python library to streamline event communication through RabbitMQ
logger - logger service

URLs

RabbitMQ: http://localhost:15672/ (skipper/welcome1)
PyPI: https://pypi.org/project/skipper-lib/

Usage

You can use Skipper engine to run Web API, workflow and communicate with a group of ML microservises implemented under services package.

deepwindlee/katana-skipper