Tutorial: GitHub Issue Summarization

Prerequisites:
  • An Internet connection is required to download the dependencies needed for this tutorial. This tutorial is not available for Air Gapped environments.
  • Before starting this tutorial, ensure that you have a Jupyter Notebook with ML toolkits enabled. The KubeDirector notebook should have PVC, as the trained model is stored in this notebook, and Seldon core reads this model from the notebook's PVC.

To complete this tutorial:

  1. Log into the KubeDirector notebook as an LDAP user.
  2. In the KubeDirector notebook, open the folder examples/kubeflow/text-processing. The working directory contains all the necessary files to work with the example.
  3. Open the Training.ipynb notebook file and run all cells: Run -> Run All Cells.
  4. Get the full path of the current home directory in the notebook. Edit the seldon-issue-sum-deployment.yaml file and replace <home_dir> with the full path of the current home directory.
  5. Open the web terminal in the HPE Ezmeral Runtime Enterprise UI, or from the terminal within the KubeDirector notebook.
    NOTE
    By default, you cannot execute kubectl commands in a newly created KubeDirector notebook. To enable kubectl in a notebook, select one of the following methods:
    • Through the HPE Ezmeral Runtime Enterprise UI:
      1. In the HPE Ezmeral Runtime Enterprise UI, navigate to the Tenant section and initialize a web terminal with the corresponding button.
      2. Start a new Terminal session inside the KubeDirector notebook. Check that the files inside your KubeDirector notebook have the appropriate file permissions that allow you to work with them.
      3. Move all files you want to work with to the following path:
        /bd-fs-mnt/TenantShare
      4. You can now access the files inside the web terminal with kubectl.
    • From inside the KubeDirector notebook:
      1. To authorize your user inside the KubeDirector notebook, execute the following Jupyter code cell:
        from ezmllib.kubeconfig.ezkubeconfig import set_kubeconfig
        set_kubeconfig()
      2. A prompt appears below the code cell you executed. Enter your user password in the prompt.
      3. kubectl is now enabled for your KubeDirector notebook. Start a Terminal session in the KubeDirector notebook to work with kubectl.
  6. Apply seldon-issue-sum-deployment.yaml with the following command:
    kubectl apply -f seldon-issue-sum-deployment.yaml
  7. Execute the following command to make a prediction:
    python seldon-request.py http://issue-summarization-example.<tenant-name>.svc.cluster.local:8000