values.yaml

# Default values for medcat-service.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.

# -- This will set the replicaset count more information can be found here: https://kubernetes.io/docs/concepts/workloads/controllers/replicaset/
replicaCount: 1

# -- This sets the container image more information can be found here: https://kubernetes.io/docs/concepts/containers/images/
image:
  # -- Image repository for the MedCAT service container
  repository: cogstacksystems/medcat-service
  # repository: cogstacksystems/medcat-service-gpu
  # -- This sets the pull policy for images.
  pullPolicy: IfNotPresent
  # Overrides the image tag whose default is the chart appVersion.
  # tag: "latest"

env:
  APP_ENABLE_DEMO_UI: true

  # -- 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.
  APP_MEDCAT_MODEL_PACK: "/cat/models/examples/example-medcat-v2-model-pack.zip"

  # Alternatively download a model on startup from a URL
  # ENABLE_MODEL_DOWNLOAD: "true"
  # MODEL_NAME: "medmen"
  # MODEL_VOCAB_URL: "https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/vocab.dat"
  # MODEL_CDB_URL: "https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/cdb-medmen-v1.dat"
  # MODEL_META_URL: "https://cogstack-medcat-example-models.s3.eu-west-2.amazonaws.com/medcat-example-models/mc_status.zip"
  # APP_MODEL_CDB_PATH: "/cat/models/medmen/cdb.dat"

  # Enable DeID mode with the following
  # APP_MEDCAT_MODEL_PACK: "/cat/models/examples/example-deid-model-pack.zip"
  # DEID_MODE: true
  # DEID_REDACT: true

  # -- Set SERVER_GUNICORN_MAX_REQUESTS to a high number instead of the default 1000. Trust k8s instead to restart pod when needed.
  # Example (tuning): see the commented `SERVER_GUNICORN_EXTRA_ARGS` setting below.
  SERVER_GUNICORN_MAX_REQUESTS: "100000"

  # Recommended env vars to set to try to limit to 1 CPU for scaling
  # OMP_NUM_THREADS: "1"
  # OPENBLAS_NUM_THREADS: "1"
  # MKL_NUM_THREADS: "1"
  # VECLIB_MAXIMUM_THREADS: "1"
  # NUMEXPR_NUM_THREADS: "1"
  # TOKENIZERS_PARALLELISM: "false"
  # PYTORCH_ENABLE_MPS_FALLBACK: "1"
  # SERVER_GUNICORN_EXTRA_ARGS: "--worker-connections 1 --backlog 1"

  # Recommended env vars for GPU support
  # APP_CUDA_DEVICE_COUNT: "1"
  # APP_TORCH_THREADS: "-1"

  # -- Observability Env Vars
  APP_ENABLE_METRICS: true
  APP_ENABLE_TRACING: false
  OTEL_EXPORTER_OTLP_ENDPOINT: "http://<unused>:4317"
  OTEL_SERVICE_NAME: "medcat-service"
  OTEL_TRACES_EXPORTER: "otlp"
  OTEL_EXPORTER_OTLP_PROTOCOL: "grpc"
  OTEL_EXPERIMENTAL_RESOURCE_DETECTORS: "containerid,os"
  OTEL_RESOURCE_ATTRIBUTES: "k8s.pod.uid=$(K8S_POD_UID),k8s.pod.name=$(K8S_POD_NAME),k8s.namespace.name=$(K8S_POD_NAMESPACE),k8s.node.name=$(K8S_NODE_NAME)"
  OTEL_METRICS_EXPORTER: "none"
  OTEL_LOGS_EXPORTER: "none"
  OTEL_PYTHON_FASTAPI_EXCLUDED_URLS: "/api/health,/metrics"

# -- Enable downloading of public models using wget on startup. Model will be downloaded to /models/<name> and used for APP_MEDCAT_MODEL_PACK
# Example: uncomment `model.downloadUrl` and `model.name` below to fetch a model pack at startup.
model: {}
  # Public URL to download a model pack from
  # downloadUrl: "http://localhost:9000/models/my-model.zip"
  # Name of the model pack to save to. Will be stored at /models/<name>
  # name: my-model.zip

# -- Allow setting env values from field/configmap/secret references. Defaults to include k8s details for observability.
envValueFrom:
  K8S_NODE_NAME:
    fieldRef:
      fieldPath: spec.nodeName
  K8S_POD_NAME:
    fieldRef:
      fieldPath: metadata.name
  K8S_POD_UID:
    fieldRef:
      fieldPath: metadata.uid
  K8S_POD_NAMESPACE:
    fieldRef:
      fieldPath: metadata.namespace

# -- This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
imagePullSecrets: []
# -- This is to override the chart name.
nameOverride: ""
fullnameOverride: ""

updateStrategy:
  # -- Used for Kubernetes deployment .spec.strategy.type. Allowed values are "Recreate" or "RollingUpdate".
  type: RollingUpdate
  # RollingUpdate default options example
  # rollingUpdate:
  #   maxSurge: 25%
  #   maxUnavailable: 25%

# This section builds out the service account more information can be found here: https://kubernetes.io/docs/concepts/security/service-accounts/
serviceAccount:
  # -- Specifies whether a service account should be created
  create: true
  # -- Automatically mount a ServiceAccount's API credentials?
  automount: true
  # -- Annotations to add to the service account
  annotations: {}
  # -- The name of the service account to use.
  # If not set and create is true, a name is generated using the fullname template
  name: ""

# -- This is for setting Kubernetes Annotations to a Pod.
# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
podAnnotations: {}
# -- This is for setting Kubernetes Labels to a Pod.
# For more information checkout: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
podLabels: {}

podSecurityContext: {}
  # fsGroup: 2000

securityContext: {}
  # capabilities:
  #   drop:
  #   - ALL
  # readOnlyRootFilesystem: true
  # runAsNonRoot: true
  # runAsUser: 1000

# This is for setting up a service more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/
service:
  # -- This sets the service type more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types
  type: ClusterIP
  # -- This sets the ports more information can be found here: https://kubernetes.io/docs/concepts/services-networking/service/#field-spec-ports
  port: 5000

# This block is for setting up the ingress for more information can be found here: https://kubernetes.io/docs/concepts/services-networking/ingress/
ingress:
  enabled: false
  className: ""
  annotations: {}
    # kubernetes.io/ingress.class: nginx
    # kubernetes.io/tls-acme: "true"
  hosts:
    - host: chart-example.local
      paths:
        - path: /
          pathType: ImplementationSpecific
  # - Optional alternative to hosts: allows for global ingress without hostname. Overrides hosts if both are set.
  # http:
  #   - paths:
  #       - path: /medcat-service
  #         pathType: ImplementationSpecific
  tls: []
  #  - secretName: chart-example-tls
  #    hosts:
  #      - chart-example.local

# -- Configure resources for the pod. More information can be found here: https://kubernetes.io/docs/concepts/containers/
# Recommendation for a default production model is { requests: { cpu: 1, memory: 4Gi }, limits: { cpu: null <unset>, memory: 4Gi } }
resources: {}
  # We usually recommend not to specify default resources and to leave this as a conscious
  # choice for the user. This also increases chances charts run on environments with little
  # resources, such as Minikube. If you do want to specify resources, uncomment the following
  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
  # limits:
  #   cpu: 2 # Note one general k8s recommendation is to leave CPU limit unset
  #   memory: 4Gi
  # requests:
  #   cpu: 1
  #   memory: 2Gi

# This is to setup the liveness and readiness probes more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-startup-probes/
livenessProbe:
  httpGet:
    path: /api/health/live
    port: http
readinessProbe:
  httpGet:
    path: /api/health/ready
    port: http
startupProbe:
  httpGet:
    path: /api/health/ready
    port: http
  failureThreshold: 30
  periodSeconds: 10
  initialDelaySeconds: 2

# This section is for setting up autoscaling more information can be found here: https://kubernetes.io/docs/concepts/workloads/autoscaling/
autoscaling:
  enabled: false
  minReplicas: 1
  maxReplicas: 100
  targetCPUUtilizationPercentage: 80
  # targetMemoryUtilizationPercentage: 80

# -- Additional volumes on the output Deployment definition.
volumes: []
# - name: foo
#   secret:
#     secretName: mysecret
#     optional: false

# -- Additional volumeMounts on the output Deployment definition.
volumeMounts: []
# - name: foo
#   mountPath: "/etc/foo"
#   readOnly: true

# -- Runtime class name for the pod (e.g., "nvidia" for GPU workloads)
# More information: https://kubernetes.io/docs/concepts/containers/runtime-class/
runtimeClassName: ""

nodeSelector: {}

tolerations: []

affinity: {}

# -- Host aliases for the pod
hostAliases: []
  # - ip: "127.0.0.1"
  #   hostnames:
  #   - "foo.local"

networkPolicy:
  # -- Choose to create a default network policy blocking all ingress other than to the service port.
  enabled: true
  egress:
    # -- Choose to block egress by enabling it in the network policy
    enabled: false
    # -- Append any custom egress rules following the standard format
    egressRules: []
      # # Example format
      # - to:
      #     - podSelector:
      #         matchLabels:
      #           app.kubernetes.io/name: model-downloader
      #   ports:
      #     - port: 5000

# -- Additional init containers to run before the main container. Can be templated
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: {}