ops: CU-869adnv5w Create Helm chart for MedCAT Trainer

.github/workflows/kubernetes-charts-build.yaml

@@ -70,11 +70,14 @@ jobs:
       uses: actions/checkout@v5
 
     - name: Package Helm Charts
-      run: helm package ./charts/medcat-service-helm --version $CHART_VERSION
+      run: |
+        helm package ./charts/medcat-service-helm --version $CHART_VERSION
+        helm package ./charts/medcat-trainer-helm --version $CHART_VERSION --dependency-update 
 
     - name: Helm OCI login to Docker Hub
       run: helm registry login registry-1.docker.io -u ${{ secrets.DOCKERHUB_USERNAME }} -p ${{ secrets.DOCKERHUB_TOKEN }}
 
     - name: Push Helm Chart to Docker Hub OCI
       run: |
         helm push ./medcat-service-helm-${CHART_VERSION}.tgz oci://registry-1.docker.io/cogstacksystems
+        helm push ./medcat-trainer-helm-${CHART_VERSION}.tgz oci://registry-1.docker.io/cogstacksystems

deployment/kubernetes/charts/medcat-trainer-helm/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

deployment/kubernetes/charts/medcat-trainer-helm/Chart.lock

@@ -0,0 +1,9 @@
+dependencies:
+- name: solr
+  repository: oci://registry-1.docker.io/bitnamicharts
+  version: 9.6.10
+- name: postgresql
+  repository: oci://registry-1.docker.io/bitnamicharts
+  version: 16.7.27
+digest: sha256:a02db326b15b24d92e4c0787792803d7b224babd4f288e28a73d66a7d4506a70
+generated: "2025-09-10T11:29:31.705470067Z"

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

@@ -0,0 +1,34 @@
+apiVersion: v2
+name: medcat-trainer-helm
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.0.1
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "latest"
+
+# Chart.yaml
+dependencies:
+- name: solr
+  version: "9.6.10"
+  repository: "oci://registry-1.docker.io/bitnamicharts"
+- name: postgresql
+  version: 16.7.27
+  repository: "oci://registry-1.docker.io/bitnamicharts"
+  condition: postgresql.enabled

deployment/kubernetes/charts/medcat-trainer-helm/README.md

@@ -0,0 +1,49 @@
+# MedCAT Trainer Helm Chart
+
+This Helm chart deploys MedCAT Trainer and infrastructure to a Kubernetes cluster.
+
+By default the chart will:
+
+- Run MedCAT Trainer Django server
+- Run NGINX for static site hosting and routing
+- Run a SOLR and Zookeeper cluster for the Concept DB
+- Run a Postgres database for persistence
+
+
+## Installation
+
+```sh
+helm install my-medcat-trainer oci://registry-1.docker.io/cogstacksystems/medcat-trainer-helm
+```
+
+## Configuration
+
+See these values for common configurations to change:
+
+| Setting  |description    |
+| -------- | -------- |
+| `env`          | Environment variables as defined in the [MedCAT Trainer docs](https://docs.cogstack.org/projects/medcat-trainer/en/latest/installation.html).    |
+|`medcatConfig`|MedCAT config file as described [here](https://github.com/CogStack/cogstack-nlp/blob/main/medcat-v2/medcat/config/config.py)|
+| `env.CSRF_TRUSTED_ORIGINS` | The Host and Port to access the application on |
+
+
+### Use Sqlite instead of Postgres
+
+Sqlite can be used for smaller single instance deployments
+
+Set these values:
+
+```yaml
+DB_ENGINE: "sqlite3"
+
+postgresql:
+  enabled: false
+```
+
+## Missing features
+These features are not yet existing but to be added in future:
+- Use a pre existing postgres db
+- Use a pre existing SOLR instance
+- Migrate from supervisord to standalone deployment for background tasks for better scaling
+- Support SOLR authentication from medcat trainer
+- Support passing DB OPTIONS to medcat trainer for use in cloud environments

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

@@ -0,0 +1,22 @@
+1. Get the application URL by running these commands:
+{{- if .Values.ingress.enabled }}
+{{- range $host := .Values.ingress.hosts }}
+  {{- range .paths }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
+  {{- end }}
+{{- end }}
+{{- else if contains "NodePort" .Values.service.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "medcat-trainer-helm.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch its status by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "medcat-trainer-helm.fullname" . }}'
+  export SERVICE_IP=$(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=nginx" -o jsonpath="{.items[0].metadata.name}")
+  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].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
+{{- end }}

deployment/kubernetes/charts/medcat-trainer-helm/templates/_helpers.tpl

@@ -0,0 +1,95 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "medcat-trainer-helm.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "medcat-trainer-helm.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "medcat-trainer-helm.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "medcat-trainer-helm.labels" -}}
+helm.sh/chart: {{ include "medcat-trainer-helm.chart" . }}
+{{ include "medcat-trainer-helm.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+app.kubernetes.io/part-of: cogstack
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "medcat-trainer-helm.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "medcat-trainer-helm.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "medcat-trainer-helm.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "medcat-trainer-helm.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}
+
+
+{{- /*
+Return Solr host: either user-supplied or constructed from release name
+
+TODO: Make Solr use the chart fullname instead of release name
+*/ -}}
+{{- define "medcat-trainer-helm.solrHost" -}}
+{{- if .Values.solrHost }}
+{{ .Values.solrHost }}
+{{- else }}
+{{- .Release.Name }}-solr
+{{- end }}
+{{- end }}
+
+{{- /*
+Return Solr port: either user-supplied or default from values
+*/ -}}
+{{- define "medcat-trainer-helm.solrPort" -}}
+{{- if .Values.solrPort }}
+{{ .Values.solrPort }}
+{{- else }}
+{{- .Values.solr.service.ports.http }}
+{{- end }}
+{{- end }}
+
+{{- /*
+Return full Solr URL: combines host and port
+*/ -}}
+{{- define "medcat-trainer-helm.solrURL" -}}
+http://{{ include "medcat-trainer-helm.solrHost" . }}:{{ include "medcat-trainer-helm.solrPort" . }}
+{{- end }}

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

@@ -0,0 +1,32 @@
+{{- if .Values.autoscaling.enabled }}
+apiVersion: autoscaling/v2
+kind: HorizontalPodAutoscaler
+metadata:
+  name: {{ include "medcat-trainer-helm.fullname" . }}
+  labels:
+    {{- include "medcat-trainer-helm.labels" . | nindent 4 }}
+spec:
+  scaleTargetRef:
+    apiVersion: apps/v1
+    kind: Deployment
+    name: {{ include "medcat-trainer-helm.fullname" . }}
+  minReplicas: {{ .Values.autoscaling.minReplicas }}
+  maxReplicas: {{ .Values.autoscaling.maxReplicas }}
+  metrics:
+    {{- if .Values.autoscaling.targetCPUUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: cpu
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetCPUUtilizationPercentage }}
+    {{- end }}
+    {{- if .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    - type: Resource
+      resource:
+        name: memory
+        target:
+          type: Utilization
+          averageUtilization: {{ .Values.autoscaling.targetMemoryUtilizationPercentage }}
+    {{- end }}
+{{- end }}

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

@@ -0,0 +1,43 @@
+{{- if .Values.ingress.enabled -}}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: {{ include "medcat-trainer-helm.fullname" . }}
+  labels:
+    {{- include "medcat-trainer-helm.labels" . | nindent 4 }}
+  {{- with .Values.ingress.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+spec:
+  {{- with .Values.ingress.className }}
+  ingressClassName: {{ . }}
+  {{- end }}
+  {{- if .Values.ingress.tls }}
+  tls:
+    {{- range .Values.ingress.tls }}
+    - hosts:
+        {{- range .hosts }}
+        - {{ . | quote }}
+        {{- end }}
+      secretName: {{ .secretName }}
+    {{- end }}
+  {{- end }}
+  rules:
+    {{- range .Values.ingress.hosts }}
+    - host: {{ .host | quote }}
+      http:
+        paths:
+          {{- range .paths }}
+          - path: {{ .path }}
+            {{- with .pathType }}
+            pathType: {{ . }}
+            {{- end }}
+            backend:
+              service:
+                name: {{ include "medcat-trainer-helm.fullname" $ }}
+                port:
+                  number: {{ $.Values.service.port }}
+          {{- end }}
+    {{- end }}
+{{- end }}

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

@@ -0,0 +1,41 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "medcat-trainer-helm.fullname" . }}-medcat-trainer-config
+  labels:
+    {{- include "medcat-trainer-helm.labels" . | nindent 4 }}
+    app.kubernetes.io/component: medcat-trainer
+data:
+  # This is mounted in the path for MEDCAT_CONFIG_FILE in the backend. Default to /home/configs/base.txt
+  medcat-base.txt: |
+{{ .Values.medcatConfig | indent 4 }}
+  supervisord.conf: |
+    [supervisord]
+    nodaemon=true
+    user=root
+    logfile=/var/log/supervisord.log
+    pidfile=/var/run/supervisord.pid
+
+    [program:medcattrainer]
+    command=sh -c "exec /home/scripts/run.sh 2>&1 | sed 's/^/[medcattrainer] /'"
+    stdout_logfile=/dev/stdout
+    stdout_logfile_maxbytes=0
+    stderr_logfile=/dev/stderr
+    stderr_logfile_maxbytes=0
+    autorestart=true
+
+    [program:bg-process]
+    command=sh -c "exec /home/scripts/run-bg-process.sh 2>&1 | sed 's/^/[bg-process] /'"
+    stdout_logfile=/dev/stdout
+    stdout_logfile_maxbytes=0
+    stderr_logfile=/dev/stderr
+    stderr_logfile_maxbytes=0
+    autorestart=true
+
+    [program:db-backup]
+    command=sh -c "exec cron -f -l 2 2>&1 | sed 's/^/[db-backup] /'"
+    stdout_logfile=/dev/stdout
+    stdout_logfile_maxbytes=0
+    stderr_logfile=/dev/stderr
+    stderr_logfile_maxbytes=0
+    autorestart=true