Batch Prediction Requests


MinIO should already be installed with Seldon Enterprise Platform. The MinIO browser should be exposed on /minio/ (note the trailing forward slash).

For trials, the credentials will by default be the same as the Enterprise Platform login, with MinIO using the email as its Access Key and the password as its Secret Key.


Other cloud storage services, such as S3 and GCS, can be specified alternatively with the corresponding secret files configured.

On a production cluster, the namespace needs to have been set up with a service account. This can be found under the argo install documentation.


We will:

  • Deploy a pipeline with a pretrained SKlearn iris model

  • Run a batch job to get predictions

  • Check the output

Create a Pipeline

  1. Click on Create new deployment button.

  2. Enter the deployment details as follows:

    • Name: batch-demo

    • Namespace: seldon

    • Type: Seldon ML Pipeline

    Expand to see deploy pipeline

    Deployment Details

  3. Configure the default predictor as follows:

    • Runtime: Scikit Learn

    • Model URI: gs://seldon-models/v1.18.1/sklearn/iris

    • Model Project: default

    • Storage Secret: (leave blank/none)

    • Additional Model Requirements: (leave blank/none)

  4. Skip Next for the remaining steps, then click Launch.

  5. If your deployment is launched successfully, it will have Available status, on the overview page.

Setup Input Data

  1. Download the input data file. Note that this input file is different from the input data from seldon-core-v1 batch prediction requests. The first few lines of the input file ‘input-data-v2.txt’ should show the following format:

  2. Go to the MinIO browser and use the button in the bottom-right to create a bucket. Call it data.

    Expand to see MinIO bucket creation


  3. Again from the bottom-right choose to upload the input-data-v2.txt file to the data bucket.

    Expand to see MinIO file upload


Run a Batch Job

  1. Click on the tile for your new pipeline called batch-demo in the Overview page of the Enterprise Platform UI.

  2. Go to the Batch Jobs section for this deployment by clicking on the Batch Jobs button in the sidebar on the left.

  3. Click on the Create your first job button, enter the following details, and click Submit:

    • Input Data Location: minio://data/input-data-v2.txt

    • Output Data Location: minio://data/output-data-v2-{{}}.txt

    • Number of Workers: 5

    • Number of Retries: 3

    • Batch Size: 10

    • Minimum Batch Wait Interval (sec): 0

    • Method: Predict

    • Transport Protocol: REST

    • Input Data Type: V2 Raw

    • Object Store Secret Name: minio-bucket-envvars

    Expand to see batch job setup

    create your first job button


    Here minio-bucket-envvars is a pre-created secret in the same namespace as the model, containing environment variables.


    In the Resources (Optional) section, you can specify how much memory and CPU are allocated to the containers in this specific batch job workflow. If no values are set on this form, the default values specified in Helm values will be used. Refer to the Kubernetes documentation on requests and limits for details.

  4. Give the job a couple of minutes to complete, then refresh the page to see the status.

    Expand to see batch job status


  5. Inspect the output file in MinIO:

    Expand to see MinIO output file


    If you open that file you should see contents such as:


    If not, see the argo section for troubleshooting.

Micro batching

You can specify a batch-size parameter which will group multiple predictions into a single request. This allows you to take advantage of the higher performance batching provides for some models, and reduce networking overhead. The response will be split back into multiple, single-prediction responses so that the output file looks identical to running the processor with a batch size of 1.