search

opendatahub-io / ai-edge

ODH integration with AI at the Edge usecases
Apache License 2.0
8 stars 17 forks source link

RHOAIENG-2244: Add support for fetching models from S3 based on the modelRelativePath & Adds a universal OpenVino ContainerFile #254

Closed LaVLaS closed 1 month ago

LaVLaS commented 4 months ago

Description

This provides the ability for users to utilize the OpenShift AI Fraud Detection tutorial in the workflow to train and deploy a model using our pipelines

Jira: RHOAIENG-2244

How Has This Been Tested?

The test-model-rest-svc must be updated to match output based on the data: not prediction:

The Continerfile.openvino to build the inferencing container must be used with this model

Merge criteria:

Existing pipeline workflows for bike-rental and tensorflow-housing are not affected

openshift-ci[bot] commented 4 months ago

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: Once this PR has been reviewed and has the lgtm label, please ask for approval from lavlas. For more information see the Kubernetes Code Review Process.

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

Needs approval from an approver in each of these files: - **[OWNERS](https://github.com/opendatahub-io/ai-edge/blob/main/OWNERS)** Approvers can indicate their approval by writing `/approve` in a comment Approvers can cancel approval by writing `/approve cancel` in a comment
openshift-ci-robot commented 4 months ago

@LaVLaS: This pull request references RHOAIENG-2244 which is a valid jira issue.

Warning: The referenced jira issue has an invalid target version for the target branch this PR targets: expected the bug to target the "4.16.0" version, but no target version was set.

In response to [this](https://github.com/opendatahub-io/ai-edge/pull/254): > > >## Description >* Updates the `fetch-model-s3` task to provide basic support for fetching a model from a sub directory under the S3 bucket removing the hardcoded requirement that all model directories be stored at the root of the S3 bucket. >* Adds a universal OpenVino containerfile that can build an inference container image for any supported OpenVino Model format > >This provides the ability for users to utilize the [OpenShift AI Fraud Detection tutorial](https://access.redhat.com/documentation/en-us/red_hat_openshift_ai_self-managed/2.8/html/openshift_ai_tutorial_-_fraud_detection_example/index) in the workflow to train and deploy a model using our pipelines > >Jira: [RHOAIENG-2244](https://issues.redhat.com/browse/RHOAIENG-2244) > >## How Has This Been Tested? >* Followed the RHOAI Fraud Detection example to train a model and used that with minio and our Pipeline >OR >* Fetch the `fraud-detection` model from `s3://rhoai-edge/example-models/fraud-detection` > >The `test-model-rest-svc` must be updated to match output based on the `data:` not `prediction:` > >The `Continerfile.openvino` to build the inferencing container must be used with this model > >## Merge criteria: >Existing pipeline workflows for `bike-rental` and `tensorflow-housing` are not affected > > >- [ ] The commits are squashed in a cohesive manner and have meaningful messages. >- [ ] Testing instructions have been added in the PR body (for PRs involving changes that are not immediately obvious). >- [ ] The developer has manually tested the changes and verified that the changes work > Instructions for interacting with me using PR comments are available [here](https://prow.ci.openshift.org/command-help?repo=opendatahub-io%2Fai-edge). If you have questions or suggestions related to my behavior, please file an issue against the [openshift-eng/jira-lifecycle-plugin](https://github.com/openshift-eng/jira-lifecycle-plugin/issues/new) repository.
LaVLaS commented 1 month ago

Closing this as the changes are no longer relevant due to a planned refactor of this repository