feat(helm): Add Medcat-trainer startup provisioning

deployment/kubernetes/charts/medcat-trainer-helm/templates/NOTES.txt

@@ -15,7 +15,7 @@
   export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "medcat-trainer-helm.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
   echo http://$SERVICE_IP:{{ .Values.service.port }}
 {{- else if contains "ClusterIP" .Values.service.type }}
-  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "medcat-trainer-helm.name" . }},app.kubernetes.io/instance={{ .Release.Name }},app.kubernetes.io/component=medcat-trainer" -o jsonpath="{.items[0].metadata.name}")
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "medcat-trainer-helm.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
   export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[?(@.name==\"nginx\")].ports[0].containerPort}")
   echo "Visit http://127.0.0.1:8080 to use your application"
   kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT

deployment/kubernetes/charts/medcat-trainer-helm/templates/medcat-trainer-configmap.yaml

@@ -38,4 +38,8 @@ data:
     stdout_logfile_maxbytes=0
     stderr_logfile=/dev/stderr
     stderr_logfile_maxbytes=0
-    autorestart=true
+    autorestart=true
+{{- if and .Values.provisioning .Values.provisioning.enabled }}
+  provisioning.yaml: |
+{{ toYaml .Values.provisioning.config | indent 4 }}
+{{- end }}

deployment/kubernetes/charts/medcat-trainer-helm/templates/medcat-trainer-deployment.yaml

@@ -85,6 +85,11 @@ spec:
               name: api-media
             - mountPath: /home/api/static
               name: api-static
+            {{- if and .Values.provisioning .Values.provisioning.enabled }}
+            - mountPath: /home/configs/provisioning.yaml
+              name: medcat-trainer-config
+              subPath: provisioning.yaml
+            {{- end }}
             {{- if eq .Values.DB_ENGINE "sqlite3" }}  
             - mountPath: /home/api/db
               name: api-db

deployment/kubernetes/charts/medcat-trainer-helm/templates/medcat-trainer-env-configmap.yaml

@@ -14,6 +14,10 @@ data:
   DB_PATH: "/home/api/db/db.sqlite3"
   MCT_VERSION: {{ .Values.image.tag | default .Chart.AppVersion }}
   API_URL: http://localhost:{{ .Values.service.apiPort }}/api/
+  {{- if and .Values.provisioning .Values.provisioning.enabled }}
+  LOAD_EXAMPLES: "1"
+  PROVISIONING_CONFIG_PATH: "/home/configs/provisioning.yaml"
+  {{- end }}
 {{- range $key, $value := .Values.env }}
   {{ $key }}: {{ $value | quote }}
 {{- end }}

deployment/kubernetes/charts/medcat-trainer-helm/values.yaml

@@ -26,7 +26,6 @@ env:
   EMAIL_PORT: "465"
   EMAIL_USER: "example@cogstack.org"
   ENV: "non-prod"
-  LOAD_EXAMPLES: "0"
   LOAD_NUM_DOC_PAGES: "10"
   MAX_DATASET_SIZE: "10000"
   MAX_MEDCAT_MODELS: "2"
@@ -40,6 +39,24 @@ env:
   DB_ENGINE: "postgresql"
   DB_PORT: "5432"
 
+provisioning:
+  # -- Set to true to enable provisioning of projects and models on startup..
+  enabled: false
+  # -- Put yaml file contents here.See https://docs.cogstack.org/projects/medcat-trainer/en/latest/provisioning/
+  config:
+    projects:
+      - dataset:
+          name: "Example Dataset - psych.csv"
+          url: "https://raw.githubusercontent.com/CogStack/cogstack-nlp/be9825f151da2d3b6faac80d49e5be91a1629c68/medcat-trainer/notebook_docs/example_data/psych.csv"
+          description: "Dataset from https://raw.githubusercontent.com/CogStack/cogstack-nlp/be9825f151da2d3b6faac80d49e5be91a1629c68/medcat-trainer/notebook_docs/example_data/psych.csv"
+        modelPack:
+          name: "Example Model Pack"
+          url: "https://github.com/CogStack/cogstack-nlp/raw/be9825f151da2d3b6faac80d49e5be91a1629c68/medcat-service/models/examples/example-medcat-v2-model-pack.zip"
+        project:
+          name: "Example Project"
+          description: "Example project for medcat trainer"
+          annotationGuidelineLink: "https://docs.google.com/document/d/1xxelBOYbyVzJ7vLlztP2q1Kw9F5Vr1pRwblgrXPS7QM/edit?usp=sharing"
+
 postgresql:
   enabled: true
   # TODO: Support custom DB overrides

deployment/kubernetes/local_dev_startup.sh

@@ -20,7 +20,7 @@ helm test medcat-service --logs
 # Test medcat trainer
 # kubectl port-forward svc/nginx 8000:8000
 
-# helm upgrade x ./medcat-trainer-helm --install  --wait --timeout 5m0s # Install if it doesnt already exist, else upgrade
+# helm upgrade medcat-trainer-helm ./medcat-trainer-helm --install  --wait --timeout 5m0s # Install if it doesnt already exist, else upgrade
 # kubectl port-forward svc/medcat-trainer-solr 8983:8983
 
 ## helm install trainer-registry oci://registry-1.docker.io/cogstacksystems/medcat-trainer-helm --wait --timeout 5m0s