Skip to content

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

License

Notifications You must be signed in to change notification settings

SeldonIO/seldon-core

Folders and files

NameName
Last commit message
Last commit date

Latest commit

cf0cb67 · Jun 27, 2018
Jan 9, 2018
Jun 27, 2018
Jun 27, 2018
Jun 6, 2018
Jun 23, 2018
Jun 27, 2018
Jun 24, 2018
Jun 27, 2018
Aug 28, 2017
Mar 15, 2017
Dec 2, 2017
Jun 16, 2018
Oct 9, 2017
Jan 24, 2018
Oct 13, 2017
Jun 27, 2018
May 27, 2018
Mar 1, 2018
Jun 24, 2018
Aug 14, 2017
May 23, 2018
Dec 18, 2017
Jan 23, 2018
Jun 4, 2018
Jan 9, 2018
Jan 9, 2018
Dec 4, 2017
Jan 25, 2018
Dec 9, 2017
Dec 4, 2017
Dec 5, 2017
Feb 5, 2018
Jun 25, 2018
Jun 6, 2018
Jun 6, 2018

Repository files navigation

Seldon Core

Branch Status
master Build Status
release-0.1 Build Status

Seldon Core is an open source platform for deploying machine learning models on Kubernetes.

Goals

Machine learning deployment has many challenges. Seldon Core intends to help with these challenges. Its high level goals are:

  • Allow data scientists to create models using any machine learning toolkit or programming language. We plan to initially cover the tools/languages below:
    • Python based models including
      • Tensorflow models
      • Sklearn models
    • Spark models
    • H2O models
    • R models
  • Expose machine learning models via REST and gRPC automatically when deployed for easy integration into business apps that need predictions.
  • Allow complex runtime inference graphs to be deployed as microservices. These graphs can be composed of:
    • Models - runtime inference executable for machine learning models
    • Routers - route API requests to sub-graphs. Examples: AB Tests, Multi-Armed Bandits.
    • Combiners - combine the responses from sub-graphs. Examples: ensembles of models
    • Transformers - transform request or responses. Example: transform feature requests.
  • Handle full lifecycle management of the deployed model:
    • Updating the runtime graph with no downtime
    • Scaling
    • Monitoring
    • Security

Prerequisites

A Kubernetes Cluster.
Kubernetes can be deployed into many environments, both in cloud and on-premise.

Quick Start

Advanced Tutorials

  • Advanced graphs showing the various types of runtime prediction graphs that can be built.

Example Components

Seldon-core allows various types of components to be built and plugged into the runtime prediction graph. These include models, routers, transformers and combiners. Some example components that are available as part of the project are:

Integrations

Install

Follow the install guide for details on ways to install seldon onto your Kubernetes cluster.

Deployment Guide

API

Three steps:

  1. Wrap your runtime prediction model.
    • We provide easy to use wrappers for python, R and Java
  2. Define your runtime inference graph in a seldon deployment custom resource.
  3. Deploy the graph.

Reference

Articles/Blogs/Videos

Testing

Community

Developer