Seldon Core Release 0.4.0

A summary of the main contributions to the Seldon Core release 0.4.0.

Prepackaged Model Servers

Seldon provides several prepacked servers you can use to deploy trained models:

For these servers you only need the location of the saved model in a local filestore, Google bucket or S3 bucket. An example manifest with an sklearn server is shown below:

kind: SeldonDeployment
  name: sklearn
  name: iris
  - graph:
      children: []
      implementation: SKLEARN_SERVER
      modelUri: gs://seldon-models/sklearn/iris
      name: classifier
    name: default
    replicas: 1

The modelUri specifies the bucket containing the saved model, in this case gs://seldon-models/sklearn/iris.

modeluri supports the following three object storage providers:

  • Google Cloud Storage (using gs://)
  • S3-comptaible (using s3://)
  • Azure Blob storage (using https://(.+?)

Gunicorn Alpha Feature

We have provided an early alpha release for the python language wrapper to run under gunicorn rather than Flask. For further details see our gunicorn documentation.

Kustomize Integration

We have a kustomize resource you can use and extend for your own particular setup for installing Seldon Core.

More Example Integrations

Our range of example has expanded to include: