Packaging a Python model for Seldon Core using Docker

In this guide, we illustrate the steps needed to wrap your own python model in a docker image ready for deployment with Seldon Core using Docker.

Step 1 - Create your source code

You will need:

  • A python file with a class that runs your model
  • A requirements.txt with a seldon-core entry

We will go into detail for each of these steps:

Python file

Your source code should contain a python file which defines a class of the same name as the file. For example, looking at our skeleton python model file at wrappers/s2i/python/test/model-template-app/

class MyModel(object):
    Model template. You can load your model parameters in __init__ from a location accessible at runtime

    def __init__(self):
        Add any initialization parameters. These will be passed at runtime from the graph definition parameters defined in your seldondeployment kubernetes resource manifest.

    def predict(self,X,features_names):
        Return a prediction.

        X : array-like
        feature_names : array of feature names (optional)
        print("Predict called - will run identity function")
        return X
  • The file is called and it defines a class MyModel
  • The class contains a predict method that takes an array (numpy) X and feature_names and returns an array of predictions.
  • You can add any required initialization inside the class init method.
  • Your return array should be at least 2-dimensional.


Populate a requirements.txt with any software dependencies your code requires. At a minimum the file should contain:


Step 2 - Define the Dockerfile

Define a Dockerfile in the same directory as your source code and requirements.txt. It will define the core parameters needed by our python builder image to wrap your model as env vars. An example is:

FROM python:3.7-slim
COPY . /app
RUN pip install -r requirements.txt

# Define environment variable

CMD exec seldon-core-microservice $MODEL_NAME $API_TYPE --service-type $SERVICE_TYPE --persistence $PERSISTENCE

Step 3 - Build your image

Use docker build . -t $ORG/$MODEL_NAME:$TAG to create your Docker image from source code. A simple name can be used but convention is to use the ORG/IMAGE:TAG format.

Using with Keras/Tensorflow Models

To ensure Keras models with the Tensorflow backend work correctly you may need to call _make_predict_function() on your model after it is loaded. This is because Flask may call the prediction request in a separate thread from the one that initialised your model. See the keras issue for further discussion.

Environment Variables

The required environment variables understood by the builder image are explained below. You can provide them in the Dockerfile or as -e parameters to docker run.


The name of the class containing the model. Also the name of the python file which will be imported.


API type to create. Can be REST or GRPC


The service type being created. Available options are:



Set either to 0 or 1. Default is 0. If set to 1 then your model will be saved periodically to redis and loaded from redis (if exists) or created fresh if not.

Advanced Usage

Model Class Arguments

You can add arguments to your component which will be populated from the parameters defined in the SeldonDeloyment when you deploy your image on Kubernetes. For example, our Python TFServing proxy has the class init method signature defined as below:

class TfServingProxy(object):

    def __init__(self,rest_endpoint=None,grpc_endpoint=None,model_name=None,signature_name=None,model_input=None,model_output=None):

These arguments can be set when deploying in a Seldon Deployment. An example can be found in the MNIST TFServing example where the arguments are defined in the SeldonDeployment which is partly show below:

 "graph": {
            "name": "tfserving-proxy",
            "endpoint": { "type" : "REST" },
            "type": "MODEL",
            "children": [],

The allowable type values for the parameters are defined in the proto buffer definition.

Custom Metrics

from version 0.3

To add custom metrics to your response you can define an optional method metrics in your class that returns a list of metric dicts. An example is shown below:

class MyModel(object):

    def predict(self,X,features_names):
        return X

    def metrics(self):
        return [{"type":"COUNTER","key":"mycounter","value":1}]

For more details on custom metrics and the format of the metric dict see here.

There is an example notebook illustrating a model with custom metrics in python.

Custom Meta Data

from version 0.3

To add custom meta data you can add an optional method tags which can return a dict of custom meta tags as shown in the example below:

class MyModel(object):

    def predict(self,X,features_names):
        return X

    def tags(self):
        return {"mytag":1}