Fix/sanity (rh-aiservices-bu#208)

* removing references to sanity.
* adding confidence pipeline image to puller. speeds up pipelines.
* also copied the image into a repo with a new name in quay.io

Author: erwangranger

bootstrap/ic-rhoai-configuration/images-puller.yaml

@@ -154,4 +154,14 @@ spec:
             requests:
               cpu: 10m
               memory: 10Mi
+        - name: ds-pipeline-runtime-image-confidence
+          image: quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-confidence-pipeline:1.1
+          command: ["tail"]
+          args: ["-f", "/dev/null"]
+          resources:
+            limits:
+              memory: 20Mi
+            requests:
+              cpu: 10m
+              memory: 10Mi
 

lab-materials/03/03-04-comparing-model-servers.ipynb

@@ -236,7 +236,7 @@
     "\n",
     "The art of working with LLM is to find the right balance between the performance and accuracy you require, and the resources it takes along with the involved costs.\n",
     "\n",
-    "Therefore it's important to have sanity checks in place to make sure that as you data changes, or your model evolves, you always get the behaviour you expected."
+    "Therefore it's important to have confidence checks in place to make sure that as you data changes, or your model evolves, you always get the behaviour you expected."
    ]
   }
  ],

lab-materials/03/06/README.md

@@ -1,3 +1,3 @@
 # 04
 
-Instructions for how to run the sanity pipeline...
+Instructions for how to run the confidence pipeline...

lab-materials/03/06/confidence-check.pipeline

@@ -281,7 +281,7 @@
             "mounted_volumes": [],
             "kubernetes_secrets": [],
             "env_vars": [],
-            "runtime_image": "quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-sanity-pipeline:1.1"
+            "runtime_image": "quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-confidence-pipeline:1.1"
           }
         }
       },

lab-materials/03/06/confidence-check.yaml

@@ -1,7 +1,7 @@
 apiVersion: tekton.dev/v1beta1
 kind: PipelineRun
 metadata:
-  name: sanity-check
+  name: confidence-check
   annotations:
     tekton.dev/output_artifacts: '{"run-a-file": [{"key": "artifacts/$PIPELINERUN/run-a-file/mlpipeline-metrics.tgz",
       "name": "mlpipeline-metrics", "path": "/tmp/mlpipeline-metrics.json"}, {"key":
@@ -71,7 +71,7 @@ spec:
             valueFrom:
               fieldRef:
                 fieldPath: metadata.annotations['pipelines.kubeflow.org/run_name']
-          image: quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-sanity-pipeline:1.1
+          image: quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-confidence-pipeline:1.1
         stepTemplate:
           volumeMounts:
           - name: mlpipeline-metrics
@@ -127,7 +127,7 @@ spec:
             valueFrom:
               fieldRef:
                 fieldPath: metadata.annotations['pipelines.kubeflow.org/run_name']
-          image: quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-sanity-pipeline:1.1
+          image: quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-confidence-pipeline:1.1
         stepTemplate:
           volumeMounts:
           - name: mlpipeline-metrics
@@ -183,7 +183,7 @@ spec:
             valueFrom:
               fieldRef:
                 fieldPath: metadata.annotations['pipelines.kubeflow.org/run_name']
-          image: quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-sanity-pipeline:1.1
+          image: quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-confidence-pipeline:1.1
         stepTemplate:
           volumeMounts:
           - name: mlpipeline-metrics
@@ -239,7 +239,7 @@ spec:
             valueFrom:
               fieldRef:
                 fieldPath: metadata.annotations['pipelines.kubeflow.org/run_name']
-          image: quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-sanity-pipeline:1.1
+          image: quay.io/rh-aiservices-bu/rhoai-lab-insurance-claim-confidence-pipeline:1.1
         stepTemplate:
           volumeMounts:
           - name: mlpipeline-metrics