v1.3.2

Added Grafana Dashboards for real-time analytics.

For more information please read our 1.3.2 release blog post.

v1.3.1

Bug fix release. Fixes for kubernetes deployment

v1.3

Release 1.3 provides Seldon running as docker containers orchestrated within a Kubernetes cluster. By leveraging Kubernetes Seldon can easily be run on cloud (AWS, Google, Azure) or on-premise. This release also provides easier control of Seldon via the seldon-cli. Full docs can be found at http://docs.seldon.io

Highlights:

• Seldon on Kubernetes.
  • Single command install with seldon-up.sh
  • Example configurations for HostPath or GlusterFS included for persistent data, but any Kubernetes persistent volume can be used.
• Seldon-cli
• Modelling jobs using luigi
• Simple examples for basic recommendation and prediction using reuters, iris and Movielens 100k data sets. We will be adding more examples soon.

For more information please read our 1.3 release blog post.

v1.3-alpha.1

1.3 alpha 1 release for Kubernetes and Seldon CLI updates.

v1.2.3

bug fix release

V1.1

• includes beta shell interface to control Seldon

v0.99

• Updates python pipelines to be scikit-learn compatible and allow use with pandas data frames.
  online docs

v0.98

This release contains an update to Python feature transformation library to use pandas internally.

v0.97

This release provides the ability to create predictive pipelines for multi-class classification models.

• Create feature extraction and manipulation pipelines in python to create appropriate features for training machine learning models. Automatically load and run the same transformations at runtime when receiving features to provide predictions on. Feature transformations include:
• TFIDF feaures with chi-squared feature selection
• Automatic detection of categorical, date and numeric features with normalisation of numeric features
• Simple pipeline and transformation classes that can be extended to create custom feature transformations
• Create classification models using Vowpal Wabbit and XGBoost
• Example microservices for runtime scoring that load and run feature pipelines and predict against Vowpal Wabbit and XGBoost models

For further technical docs please see: http://docs.seldon.io/prediction-overview.html
We provide a demo for creating a multi-class classification predictive endpoint for the classic Iris classification task: http://docs.seldon.io/iris-demo.html

v0.96.2

Bug fix release