feat(helm): Add prometheus servicemonitor to medcat-service-helm (#67)

Author: alhendrickson

helm-charts/medcat-service-helm/README.md

@@ -132,7 +132,7 @@ You should see the NVIDIA GPU device listing if the GPU is properly accessible.
 | autoscaling.minReplicas | int | `1` |  |
 | autoscaling.targetCPUUtilizationPercentage | int | `80` |  |
 | env.APP_ENABLE_DEMO_UI | bool | `true` |  |
-| env.APP_ENABLE_METRICS | bool | `false` | Observability Env Vars |
+| env.APP_ENABLE_METRICS | bool | `true` | Observability Env Vars |
 | env.APP_ENABLE_TRACING | bool | `false` |  |
 | env.APP_MEDCAT_MODEL_PACK | string | `"/cat/models/examples/example-medcat-v2-model-pack.zip"` | This defines the Model Pack used by the medcat service Example (download on startup): uncomment `ENABLE_MODEL_DOWNLOAD` and the `MODEL_*` URLs below. Example (DeID mode): uncomment `DEID_MODE`/`DEID_REDACT` and use the DeID model pack referenced below. |
 | env.OTEL_EXPERIMENTAL_RESOURCE_DETECTORS | string | `"containerid,os"` |  |
@@ -184,6 +184,12 @@ You should see the NVIDIA GPU device listing if the GPU is properly accessible.
 | serviceAccount.automount | bool | `true` | Automatically mount a ServiceAccount's API credentials? |
 | serviceAccount.create | bool | `true` | Specifies whether a service account should be created |
 | serviceAccount.name | string | `""` | The name of the service account to use. If not set and create is true, a name is generated using the fullname template |
+| serviceMonitor | object | `{"enabled":false,"interval":"10s","labels":{},"path":"/metrics","scheme":"http","tlsConfig":{}}` | Create a Prometheus ServiceMonitor for the medcat service. Requires the Prometheus Operator to be installed Ensure APP_ENABLE_METRICS is set to true to expose the /metrics endpoint. |
+| serviceMonitor.enabled | bool | `false` | Set to true to enable creation of a ServiceMonitor resource |
+| serviceMonitor.interval | string | `"10s"` | Frequency at which Prometheus will scrape metrics. |
+| serviceMonitor.labels | object | `{}` | Additional labels to be added to the ServiceMonitor |
+| serviceMonitor.path | string | `"/metrics"` | HTTP path where metrics are exposed. |
+| serviceMonitor.scheme | string | `"http"` | Scheme to use for scraping. |
 | startupProbe.failureThreshold | int | `30` |  |
 | startupProbe.httpGet.path | string | `"/api/health/ready"` |  |
 | startupProbe.httpGet.port | string | `"http"` |  |

helm-charts/medcat-service-helm/templates/serviceMonitor.yaml

@@ -0,0 +1,25 @@
+{{- if .Values.serviceMonitor.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: {{ include "medcat-service.fullname" . }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "medcat-service.labels" . | nindent 4 }}
+    {{- with .Values.serviceMonitor.labels }}
+      {{- toYaml . | nindent 4 }}
+    {{- end }}
+spec:
+  selector:
+    matchLabels:
+      {{- include "medcat-service.selectorLabels" . | nindent 6 }}
+  endpoints:
+  - port: http
+    interval: {{ .Values.serviceMonitor.interval }}
+    path: {{ .Values.serviceMonitor.path }}
+    scheme: {{ .Values.serviceMonitor.scheme }}
+    {{- with .Values.serviceMonitor.tlsConfig }}
+    tlsConfig:
+      {{- toYaml . | nindent 8 }}
+    {{- end }}
+{{- end }}

helm-charts/medcat-service-helm/values.yaml

@@ -55,7 +55,7 @@ env:
   # APP_TORCH_THREADS: "-1"
 
   # -- Observability Env Vars
-  APP_ENABLE_METRICS: false
+  APP_ENABLE_METRICS: true
   APP_ENABLE_TRACING: false
   OTEL_EXPORTER_OTLP_ENDPOINT: "http://<unused>:4317"
   OTEL_SERVICE_NAME: "medcat-service"
@@ -252,3 +252,18 @@ extraInitContainers: []
 
 # -- Additional manifests to deploy to kubernetes. Can be templated
 extraManifests: []
+
+# -- Create a Prometheus ServiceMonitor for the medcat service. Requires the Prometheus Operator to be installed
+# Ensure APP_ENABLE_METRICS is set to true to expose the /metrics endpoint.
+serviceMonitor:
+  # -- Set to true to enable creation of a ServiceMonitor resource
+  enabled: false
+  # -- HTTP path where metrics are exposed.
+  path: /metrics
+  # -- Scheme to use for scraping.
+  scheme: http
+  # -- Frequency at which Prometheus will scrape metrics.
+  interval: 10s
+  # -- Additional labels to be added to the ServiceMonitor
+  labels: {}
+  tlsConfig: {}