Where is Teddy?

Setup

This guide will help you to set up the Where is Teddy? Demo

Prepare the Infrastructure

1. Order an OpenShift Cluster using the TAP catalog item.

2. Tick the checkbox to enable RHOAI.

Prepare the OpenShift AI Notebook environment

1. From the command line, login to OpenShift as a cluster administrator.

   Use the data from the email you receive as part of the confirmation of the successful deployment of your environment.

2. Install the Authorino operator.

   oc apply -f ./setup/rhoai-config/subscription-authorino.yaml

3. Wait a few moments until the operator is fully installed.

4. Restart the data science operator pod.

   oc delete po -l name=rhods-operator -n redhat-ods-operator

5. Wait a few moments and check that the authorino pods are running correctly in the new redhat-ods-applications-auth-provider project.

   If this is not working you won't be able to expose your model serving route externally from the console and will need to edit the service manually.

6. Create the workspace image-generation.

   oc apply -f ./setup/image-gen/ds-project.yaml

7. Wait for project to be created.

8. Setup and configure Minio to enable the S3 storage.

   oc apply -n image-generation -f ./setup/image-gen/setup-s3.yaml

9. Wait for all the jobs to finish.

10. Create the serving runtime for the model serving.

    oc apply -n image-generation -f ./templates/serving-runtime.yaml

11. Create the storage for the workbench workbench-storage.

    oc apply -n image-generation -f ./setup/image-gen/pvc.yaml

    Currently there is an issue with the storage provider in the GPU worker nodes that prevent the workbench to start, creating the persistent volume claim with gp3-csi solves the issue.

Create a new OpenShift AI Workbench:

1. Go to OpenShift AI (from the OpenShift console view, click on the applications menu in the top right, then select Red Hat OpenShift AI).

   

2. Then Go to Data Science Projects. Select the "Image Generation" project.

   

3. In the overview tab, click on Create workbench.

   

4. From there, fill in the form with the following information:

   Name workbench

   Image selection PyTorch

   Version selection 2024.1

   Container size Medium

   Accelerator NVIDIA GPU

   Use existing persistent storage workbench-storage

   Use existing data connection My Storage

5. Click on Create workbench.

6. Wait a few minutes until the status in the page is Running.

   It is a big image to pull, it might take up to 10 minutes to get started.

7. Open the newly created workbench by clicking Open.

   

8. In the new Jupyter notebook click on the Git tab and then the Clone a Repository button. Type in the following URI https://github.com/cfchase/text-to-image-demo.git. Finally click Clone.

   

Run the notebook training

1. Run through the first 2 notebooks of the demo:

   • 1_experimentation.ipynb
   • 2_fine_tuning.ipynb

Deploy the newly trained model

1. Go back to the OpenShift AI console.

2. Register the serving runtime in Openshift AI by clicking on Settings then Serving Runtimes menu and finally the Add serving runtime button.

   

3. Select Single Model Serving Platform.

4. Select the API Protocol REST.

5. In the Add Serving Runtime click from scratch and past the contents /templates/serving-runtime.yaml file.

6. Click the Create button.

   

7. Select your working project. Click on the Models tab. Then click the Deploy Model button.

   

8. From there, fill in the form with the following information:

   Model name redhat-dog

   Serving runtime Diffusers Runtime

   Model framework pytorch - 1

   Model server size Custom (1CPU / 1 Gi)

   Accelerator NVIDIA GPU

   Model route Check Make deployment models available through an external route

   Token authentication Leave it unchecked

   Model location Existing data connection

   ​ Name My Storage

   ​ Path models/notebook-output/redhat-dog/

9. Click the Deploy button.

10. Wait a few minutes for the inference server to deploy. The status should turn green and the inference point should show in.

    

Deploy the consuming application

1. Go to Red Hat Developer Hub. In the Catalog view, click "Create", "Register Existing Component" and add template from the following url: https://github.com/redhat-developer-demos/where-is-teddy/blob/main/scaffolder-templates/wheres-teddy/template.yaml

2. Register the API entity from the following url: https://github.com/redhat-developer-demos/where-is-teddy/blob/main/genai-photo-generator-api/catalog-info.yaml

3. Create a new component using the software template from Developer Hub