[RHOAIENG-191] Add sample models to use as reference for verifying ML…

davidesalerno commented 9 months ago

…Ops Pipeline functionality

The RHOAI Edge features need to consume the model servers and runtimes that are supported by RHOAI Model Serving stack, for this reason we need some more sample models that can be easily served using OVMS or Seldon ML Server

Description

In order to provide sample models that can be consumed by the model servers and runtimes we added 4 models that could be served using OVMS or Seldon ML Server:

Iris
Mushrooms
MNIST
Face Detection

How Has This Been Tested?

Each model is tested following the relative Test section in its README file in order to be able to verify that:

we are able to serve it using the target model server
the inference is working (a sample call is provided)

Merge criteria:

[x] The commits are squashed in a cohesive manner and have meaningful messages.
[x] Testing instructions have been added in the PR body (for PRs involving changes that are not immediately obvious).
[x] The developer has manually tested the changes and verified that the changes work

grdryn commented 8 months ago

/test test-ai-edge

grdryn commented 8 months ago

(none of these questions in this comment suggest changes to this PR)

@davidesalerno @LaVLaS For the two existing models, we've got Tekton PipelineRun examples, and things like ACM registration resources and repo files. Do we expect to have equivalents for these new model examples? If so, are there follow-up tasks for that?

OTOH, these new models come with README files with relevant information. We're missing such a thing for the existing bike-rentals-auto-ml model at least...should we have one?

davidesalerno commented 8 months ago

I'm leaving a few additional comments. Also, maybe remove the.idea folder?

After you fix, IMO this would be in shape for merging.

@israel-hdez I did it

LaVLaS commented 8 months ago

@davidesalerno @LaVLaS For the two existing models, we've got Tekton PipelineRun examples, and things like ACM registration resources and repo files. Do we expect to have equivalents for these new model examples? If so, are there follow-up tasks for that?

Yes, the idea is to provide these as inputs for PipelineRuns for CI testing. I don't think there is a follow-up task [yet] since this and the CI test framework are in development OR in the backlog.

openshift-ci[bot] commented 8 months ago

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: davidesalerno, grdryn

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files: - ~~[OWNERS](https://github.com/opendatahub-io/ai-edge/blob/main/OWNERS)~~ [grdryn] Approvers can indicate their approval by writing `/approve` in a comment Approvers can cancel approval by writing `/approve cancel` in a comment

opendatahub-io / ai-edge