Add Helm chart, Docs, and Config conversion script

deploy/helm/datacenter-docs/values-production.yaml

@@ -0,0 +1,304 @@
+# Production values for datacenter-docs
+# This is an example configuration for production deployment
+# Copy this file and customize it for your environment
+
+global:
+  imagePullPolicy: Always
+  storageClass: "standard"  # Use your storage class
+
+# MongoDB configuration for production
+mongodb:
+  enabled: true
+  auth:
+    rootUsername: admin
+    rootPassword: "CHANGE-THIS-IN-PRODUCTION"  # Use strong password
+    database: datacenter_docs
+  persistence:
+    enabled: true
+    size: 50Gi  # Adjust based on expected data volume
+    storageClass: "fast-ssd"  # Use SSD storage class for better performance
+  resources:
+    requests:
+      memory: "2Gi"
+      cpu: "1000m"
+    limits:
+      memory: "4Gi"
+      cpu: "2000m"
+
+# Redis configuration for production
+redis:
+  enabled: true
+  resources:
+    requests:
+      memory: "256Mi"
+      cpu: "200m"
+    limits:
+      memory: "1Gi"
+      cpu: "1000m"
+
+# API service - production scale
+api:
+  enabled: true
+  replicaCount: 5
+  image:
+    repository: your-registry.io/datacenter-docs-api
+    tag: "v1.0.0"  # Use specific version, not latest
+    pullPolicy: Always
+  service:
+    type: ClusterIP
+    port: 8000
+  resources:
+    requests:
+      memory: "1Gi"
+      cpu: "500m"
+    limits:
+      memory: "4Gi"
+      cpu: "2000m"
+  autoscaling:
+    enabled: true
+    minReplicas: 5
+    maxReplicas: 20
+    targetCPUUtilizationPercentage: 70
+    targetMemoryUtilizationPercentage: 80
+
+# Chat service - enable in production
+chat:
+  enabled: true
+  replicaCount: 3
+  image:
+    repository: your-registry.io/datacenter-docs-chat
+    tag: "v1.0.0"
+    pullPolicy: Always
+  resources:
+    requests:
+      memory: "512Mi"
+      cpu: "250m"
+    limits:
+      memory: "2Gi"
+      cpu: "1000m"
+
+# Worker service - enable in production
+worker:
+  enabled: true
+  replicaCount: 5
+  image:
+    repository: your-registry.io/datacenter-docs-worker
+    tag: "v1.0.0"
+    pullPolicy: Always
+  resources:
+    requests:
+      memory: "1Gi"
+      cpu: "500m"
+    limits:
+      memory: "4Gi"
+      cpu: "2000m"
+  autoscaling:
+    enabled: true
+    minReplicas: 3
+    maxReplicas: 20
+    targetCPUUtilizationPercentage: 75
+
+# Frontend - production scale
+frontend:
+  enabled: true
+  replicaCount: 3
+  image:
+    repository: your-registry.io/datacenter-docs-frontend
+    tag: "v1.0.0"
+    pullPolicy: Always
+  resources:
+    requests:
+      memory: "128Mi"
+      cpu: "100m"
+    limits:
+      memory: "512Mi"
+      cpu: "500m"
+
+# Ingress - production configuration
+ingress:
+  enabled: true
+  className: "nginx"
+  annotations:
+    cert-manager.io/cluster-issuer: "letsencrypt-prod"
+    nginx.ingress.kubernetes.io/ssl-redirect: "true"
+    nginx.ingress.kubernetes.io/force-ssl-redirect: "true"
+    nginx.ingress.kubernetes.io/proxy-body-size: "50m"
+    nginx.ingress.kubernetes.io/rate-limit: "100"
+    nginx.ingress.kubernetes.io/limit-rps: "50"
+  hosts:
+    - host: datacenter-docs.yourdomain.com
+      paths:
+        - path: /
+          pathType: Prefix
+          service: frontend
+        - path: /api
+          pathType: Prefix
+          service: api
+        - path: /ws
+          pathType: Prefix
+          service: chat
+  tls:
+    - secretName: datacenter-docs-tls
+      hosts:
+        - datacenter-docs.yourdomain.com
+
+# Application configuration for production
+config:
+  # MongoDB connection (if using external MongoDB, change this)
+  mongodbUrl: "mongodb://admin:CHANGE-THIS-IN-PRODUCTION@{{ include \"datacenter-docs.mongodb.fullname\" . }}:27017/datacenter_docs?authSource=admin"
+
+  # Redis connection
+  redisUrl: "redis://{{ include \"datacenter-docs.redis.fullname\" . }}:6379/0"
+
+  # LLM Provider configuration
+  llm:
+    # For OpenAI
+    baseUrl: "https://api.openai.com/v1"
+    model: "gpt-4-turbo-preview"
+
+    # For Anthropic Claude (alternative)
+    # baseUrl: "https://api.anthropic.com/v1"
+    # model: "claude-3-opus-20240229"
+
+    # For Azure OpenAI (alternative)
+    # baseUrl: "https://your-resource.openai.azure.com"
+    # model: "gpt-4"
+
+    maxTokens: 4096
+    temperature: 0.7
+
+  # MCP configuration
+  mcp:
+    baseUrl: "http://mcp-server:8080"
+    timeout: 30
+
+  # Auto-remediation configuration
+  autoRemediation:
+    enabled: true
+    minReliabilityScore: 90.0  # Higher threshold for production
+    requireApprovalThreshold: 95.0
+    maxActionsPerHour: 50  # Conservative limit
+    dryRun: false  # Set to true for initial deployment
+
+  # Security
+  apiKeyEnabled: true
+  corsOrigins:
+    - "https://datacenter-docs.yourdomain.com"
+    - "https://admin.yourdomain.com"
+
+  # Logging
+  logLevel: "INFO"  # Use "DEBUG" for troubleshooting
+  logFormat: "json"
+
+# Secrets - MUST BE CHANGED IN PRODUCTION
+secrets:
+  # LLM API Key
+  llmApiKey: "CHANGE-THIS-TO-YOUR-ACTUAL-API-KEY"
+
+  # API authentication secret key
+  apiSecretKey: "CHANGE-THIS-TO-A-STRONG-RANDOM-KEY"
+
+  # MongoDB credentials
+  mongodbUsername: "admin"
+  mongodbPassword: "CHANGE-THIS-IN-PRODUCTION"
+
+# ServiceAccount
+serviceAccount:
+  create: true
+  annotations:
+    # Add cloud provider annotations if needed
+    # eks.amazonaws.com/role-arn: arn:aws:iam::ACCOUNT-ID:role/IAM-ROLE-NAME
+  name: ""
+
+# Pod security context
+podSecurityContext:
+  fsGroup: 1000
+  runAsNonRoot: true
+  runAsUser: 1000
+  seccompProfile:
+    type: RuntimeDefault
+
+# Container security context
+securityContext:
+  allowPrivilegeEscalation: false
+  capabilities:
+    drop:
+      - ALL
+  readOnlyRootFilesystem: false
+  runAsNonRoot: true
+  runAsUser: 1000
+
+# Node selector - place workloads on specific nodes
+nodeSelector:
+  workload-type: "application"
+  # kubernetes.io/arch: amd64
+
+# Tolerations - allow scheduling on tainted nodes
+tolerations:
+  - key: "workload-type"
+    operator: "Equal"
+    value: "application"
+    effect: "NoSchedule"
+
+# Affinity rules - spread pods across zones and nodes
+affinity:
+  podAntiAffinity:
+    preferredDuringSchedulingIgnoredDuringExecution:
+      - weight: 100
+        podAffinityTerm:
+          labelSelector:
+            matchExpressions:
+              - key: app.kubernetes.io/name
+                operator: In
+                values:
+                  - datacenter-docs
+          topologyKey: kubernetes.io/hostname
+      - weight: 100
+        podAffinityTerm:
+          labelSelector:
+            matchExpressions:
+              - key: app.kubernetes.io/component
+                operator: In
+                values:
+                  - api
+          topologyKey: topology.kubernetes.io/zone
+
+# Priority class - ensure critical pods are scheduled first
+priorityClassName: "high-priority"
+
+# Additional production recommendations:
+#
+# 1. Use external secret management:
+#    - HashiCorp Vault
+#    - AWS Secrets Manager
+#    - Azure Key Vault
+#    - Google Secret Manager
+#
+# 2. Enable monitoring:
+#    - Prometheus metrics
+#    - Grafana dashboards
+#    - AlertManager alerts
+#
+# 3. Enable logging:
+#    - ELK Stack
+#    - Loki
+#    - CloudWatch
+#
+# 4. Enable tracing:
+#    - Jaeger
+#    - OpenTelemetry
+#
+# 5. Backup strategy:
+#    - MongoDB backups (Velero, native tools)
+#    - Disaster recovery plan
+#
+# 6. Network policies:
+#    - Restrict pod-to-pod communication
+#    - Isolate database access
+#
+# 7. Pod disruption budgets:
+#    - Ensure high availability during updates
+#
+# 8. Regular security scans:
+#    - Container image scanning
+#    - Dependency vulnerability scanning