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

# MySQL configurations for helm dependency
# you can find more details about this here https://artifacthub.io/packages/helm/bitnami/mysql
global:
  security:
    allowInsecureImages: true

cronJobLabels: {}

mysql:
  enabled: true
  fullnameOverride: "mysql"
  architecture: standalone
  image:
    registry: docker.io
    repository: bitnamilegacy/mysql
    tag: 8.0.37-debian-12-r2
    pullPolicy: "Always"
  auth:
    rootPassword: password    # to be provided by CI/CD
  primary:
    extraFlags: "--sort_buffer_size=10M"
    persistence:
      size: 50Gi
    service:
      nodePort: 3306
  initdbScripts:
    init_openmetadata_db_scripts.sql: |
      CREATE DATABASE openmetadata_db;
      CREATE USER 'openmetadata_user'@'%' IDENTIFIED BY 'openmetadata_password';
      GRANT ALL PRIVILEGES ON openmetadata_db.* TO 'openmetadata_user'@'%' WITH GRANT OPTION;
      commit;
    init_airflow_db_scripts.sql: |
      CREATE DATABASE airflow_db CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci;
      CREATE USER 'airflow_user'@'%' IDENTIFIED BY 'airflow_pass';
      GRANT ALL PRIVILEGES ON airflow_db.* TO 'airflow_user'@'%' WITH GRANT OPTION;
      commit;

# OpenSearch Helm Dependency
# you can find more details about this here https://artifacthub.io/packages/helm/opensearch-project-helm-charts/opensearch/2.12.2
opensearch:
  enabled: true
  clusterName: opensearch
  fullnameOverride: opensearch
  nodeGroup: ""
  imagePullPolicy: Always
  opensearchJavaOpts: "-Xmx1g -Xms1g"
  persistence:
    size: 30Gi
  protocol: http
  config:
    opensearch.yml: |
      plugins.security.disabled: true
      indices.query.bool.max_clause_count: 4096
  singleNode: true
  resources:
    requests:
      cpu: "100m"
      memory: "256M"
    limits:
      cpu: "2000m"
      memory: "2048M"

# Airflow configurations for helm dependency
# you can find more details about this here https://airflow.apache.org/docs/helm-chart/
airflow:
  enabled: true
  # Static secret key for Airflow webserver (strongly recommended for Airflow 3)
  # Without this, JWT token authentication may fail between Airflow components
  # Generate a new key with: openssl rand -hex 32
  # Set to empty string (~) to auto-generate (not recommended for production)

  # Fernet key settings
  # Note: fernetKey can only be set during install, not upgrade
  fernetKey: ~

  # Flask secret key for Airflow 3+ Api: `[api] secret_key` in airflow.cfg
  apiSecretKey: "a5f8c3e2d1b9a7f6e4c3b2a1f9e8d7c6b5a4f3e2d1c9b8a7f6e5d4c3b2a1f0e9"

  # Secret key used to encode and decode JWTs: `[api_auth] jwt_secret` in airflow.cfg
  jwtSecret: ~

  # Use OpenMetadata Airflow image with Airflow 3
  images:
    airflow:
      repository: docker.getcollate.io/openmetadata/ingestion
      tag: 1.13.5
      pullPolicy: "IfNotPresent"
  # Use KubernetesExecutor for production deployments (recommended)
  # For local development (Docker Desktop/Minikube), use LocalExecutor instead
  # Note: KubernetesExecutor requires shared DAGs storage (RWX PVC) which isn't available in Docker Desktop
  executor: "KubernetesExecutor"
  # Environment variables for Airflow configuration
  env:
    # This is required for OpenMetadata UI to fetch status of DAGs
    - name: AIRFLOW__API__AUTH_BACKENDS
      value: "airflow.api.auth.backend.session,airflow.api.auth.backend.basic_auth"
    # OpenMetadata Airflow Apis Plugin DAGs Configuration
    - name: AIRFLOW__OPENMETADATA_AIRFLOW_APIS__DAG_GENERATED_CONFIGS
      value: "/opt/airflow/dags"
    # OpenMetadata Airflow Secrets Manager Configuration
    - name: AIRFLOW__OPENMETADATA_SECRETS_MANAGER__AWS_REGION
      value: ""
    - name: AIRFLOW__OPENMETADATA_SECRETS_MANAGER__AWS_ACCESS_KEY_ID
      value: ""
    - name: AIRFLOW__OPENMETADATA_SECRETS_MANAGER__AWS_ACCESS_KEY
      value: ""
  # Create admin user
  createUserJob:
    # Whether the create user job should be created
    enabled: true
    # The default user to create
    defaultUser:
      role: Admin
      username: admin
      email: spiderman@superhero.org
      firstName: Peter
      lastName: Parker
      password: admin

  # Airflow database migration job settings
  migrateDatabaseJob:
    enabled: true

  # Worker configuration for KubernetesExecutor (from 1.19.0 let's use workers.kubernetes)
  # Set replicas to 0 for LocalExecutor (local development)
  workers:
    kubernetes:
      # Resource configuration for pods created with pod-template-file
      resources: {}
      #  limits:
      #   cpu: 100m
      #   memory: 128Mi
      #  requests:
      #   cpu: 100m
      #   memory: 128Mi


  # Airflow scheduler settings
  scheduler:
    enabled: true

    # Amount of scheduler replicas (recommended to be set larger than 2 with MYSQL 8+ and Postgres 12+)
    replicas: 1

  # API server needs access to DAGs volume for OpenMetadata dynamic DAG generation
  apiServer:
    enabled: true

    # Number of Airflow API servers in the deployment.
    # Omitted from the Deployment, when HPA is enabled.
    replicas: 1

    extraVolumes:
      - name: dags
        persistentVolumeClaim:
          claimName: '{{ include "airflow.fullname" . }}-dags'
    extraVolumeMounts:
      - name: dags
        mountPath: /opt/airflow/dags

  # Airflow Triggerer Config
  triggerer:
    enabled: true
    # Number of airflow triggerers in the deployment
    replicas: 1

  # Airflow Dag Processor Config
  dagProcessor:
    enabled: false
    # Number of airflow dag processors in the deployment
    replicas: 1

  # Disable Flower when use KubernetesExecutor
  flower:
    enabled: false

  # StatsD settings
  statsd:
    enabled: true

  # Disable internal PostgreSQL, use external MySQL
  postgresql:
    enabled: false

  # Disable internal Redis when use KubernetesExecutor
  redis:
    enabled: false
  # Configure external MySQL database
  data:
    metadataConnection:
      user: airflow_user
      pass: airflow_pass
      protocol: mysql
      host: mysql
      port: 3306
      db: airflow_db
      sslmode: disable
  # Service account configuration (required for KubernetesExecutor)
  # DAGs persistence configuration
  dags:
    persistence:
      enabled: true
      storageClassName: ""
      size: 1Gi
  # Logs persistence configuration
  logs:
    persistence:
      enabled: true
      storageClassName: ""
      size: 1Gi
# Apache Jena Fuseki SPARQL server for the OpenMetadata RDF / Knowledge Graph feature.
# Disabled by default. When enabled it deploys an in-cluster Fuseki (Deployment +
# Service "fuseki" on port 3030 + optional PVC). Point OpenMetadata at it by setting
# openmetadata.config.rdf in the openmetadata chart values, e.g.:
#   rdf:
#     enabled: true
#     remoteEndpoint: "http://fuseki:3030/openmetadata"
#     username: "admin"
#     dataset: "openmetadata"
#     password:
#       secretRef: fuseki-admin-credentials
#       secretKey: admin-password
# Both the server (ADMIN_PASSWORD) and the app (RDF_REMOTE_PASSWORD) read the same
# admin password secret. Create it before installing:
#   kubectl create secret generic fuseki-admin-credentials \
#     --from-literal=admin-password=<STRONG_PASSWORD> -n <namespace>
fuseki:
  enabled: false
  replicaCount: 1
  image:
    repository: daschswiss/apache-jena-fuseki
    tag: "6.0.0"
    pullPolicy: IfNotPresent
  # Production BYOC resource recommendation. Override for smaller deployments.
  resources:
    requests:
      cpu: "1500m"
      memory: "10Gi"
    limits:
      cpu: "2500m"
      memory: "12Gi"
  adminPassword:
    secretName: "fuseki-admin-credentials"
    secretKey: "admin-password"
  jvmArgs: "-Xmx8g -Xms8g"
  service:
    type: ClusterIP
    port: 3030
  persistence:
    enabled: true
    size: 100Gi
    # Empty string uses the cluster default StorageClass. Set e.g. "gp3" on AWS.
    storageClass: ""
  extraEnvs: []
  serviceMonitor:
    enabled: false
    interval: 30s
  nodeSelector: {}
  tolerations: []
  affinity: {}