ocp4-workload-rhte-analytics_data_ocp_infra fails on OCP 4.3

[pdmack]

Describe the bug
Current Seldon CRD cannot deploy into OCP 4.3 due to upgrade of k8s to 1.16

To Reproduce
ansible-playbook --connection local -i localhost, configs/ocp-workloads/ocp-workload.yml -e 'ocp_username='${OCP_ADMIN_USERNAME} -e 'ocp_workload=ocp4-workload-rhte-analytics_data_ocp_infra' -e 'silent=False' -e 'ACTION=create'

failed: [localhost] (item=---
# Source: seldon-core-crd/templates/seldon-deployment-crd.json
{
  "apiVersion": "apiextensions.k8s.io/v1beta1",
  "kind": "CustomResourceDefinition",
  "metadata": {
    "name": "seldondeployments.machinelearning.seldon.io"
  },

Expected behavior
ocp4-workload-rhte-analytics_data_ocp_infra : workload tasks complete ----- 0.03s

Versions (please complete the following information):

• Red Hat Enterprise Linux Server release 7.5 (Maipo)
• AAD version

2341b122dcf67db7780b91b925804aa09d38a2b0 Fix Knative CRD check (#1497)
35186e765459c7199f5a874c78e52924b49ff5be Add default for rgw_endpoint_url (#1496)

• Ansible

ansible 2.8.8
  config file = /root/agnosticd/ansible/ansible.cfg
  configured module search path = [u'/root/.ansible/plugins/modules', u'/usr/share/ansible/plugins/modules']
  ansible python module location = /usr/lib/python2.7/site-packages/ansible
  executable location = /bin/ansible
  python version = 2.7.5 (default, May 31 2018, 09:41:32) [GCC 4.8.5 20150623 (Red Hat 4.8.5-28)]

• AWS

Additional context
Related to this ODH issue.

[pdmack]

/assign @LaVLaS

[LaVLaS]

Instead of constant updating this role that was built specifically for RHTE 2019. I'll submit a PR to add a new infra role for a generic ODH deployment that is versioned for different ODH releases and OCP versions