Merge pull request #15 from Finoptimize/environment

Updating env vars samples

Author: dewitt4

.env.example

@@ -0,0 +1,193 @@
+# AgentaFlow SRO Community Edition - Environment Configuration
+# Copy this file to .env and update with your actual values
+
+# =============================================================================
+# GENERAL SETTINGS
+# =============================================================================
+
+# Application environment (development, staging, production)
+APP_ENV=development
+
+# Log level (debug, info, warn, error)
+LOG_LEVEL=info
+
+# Application port
+PORT=8080
+
+# =============================================================================
+# KUBERNETES CONFIGURATION
+# =============================================================================
+
+# Kubernetes cluster configuration
+KUBECONFIG_PATH=~/.kube/config
+K8S_NAMESPACE=agentaflow-monitoring
+K8S_SERVICE_ACCOUNT=agentaflow-scheduler
+
+# Kubernetes GPU scheduler settings
+K8S_GPU_SCHEDULER_ENABLED=true
+K8S_GPU_SCHEDULER_STRATEGY=least-utilized
+K8S_GPU_RESOURCE_NAME=nvidia.com/gpu
+
+# =============================================================================
+# GPU ORCHESTRATION
+# =============================================================================
+
+# GPU monitoring intervals (seconds)
+GPU_METRICS_INTERVAL=5
+GPU_HEALTH_CHECK_INTERVAL=30
+
+# GPU scheduling configuration
+GPU_SCHEDULER_STRATEGY=least-utilized
+GPU_MAX_UTILIZATION_THRESHOLD=90
+GPU_MIN_UTILIZATION_THRESHOLD=10
+
+# GPU resource limits
+GPU_MEMORY_LIMIT_MB=16384
+GPU_TEMPERATURE_THRESHOLD=85
+GPU_POWER_LIMIT_WATTS=300
+
+# =============================================================================
+# MODEL SERVING OPTIMIZATION
+# =============================================================================
+
+# Batch processing configuration
+BATCH_MAX_SIZE=32
+BATCH_MAX_WAIT_TIME_MS=100
+
+# Caching configuration
+CACHE_TTL_MINUTES=5
+CACHE_MAX_SIZE_MB=1024
+CACHE_ENABLED=true
+
+# Load balancing
+LOAD_BALANCER_STRATEGY=round-robin
+
+# =============================================================================
+# OBSERVABILITY & MONITORING
+# =============================================================================
+
+# Prometheus configuration
+PROMETHEUS_ENABLED=true
+PROMETHEUS_PORT=9090
+PROMETHEUS_METRICS_PATH=/metrics
+PROMETHEUS_SCRAPE_INTERVAL=15s
+
+# Grafana configuration
+GRAFANA_ENABLED=true
+GRAFANA_PORT=3000
+GRAFANA_ADMIN_USER=admin
+GRAFANA_ADMIN_PASSWORD=agentaflow123
+
+# Metrics collection
+METRICS_BUFFER_SIZE=10000
+METRICS_RETENTION_HOURS=24
+METRICS_EXPORT_INTERVAL_SECONDS=15
+
+# =============================================================================
+# COST TRACKING
+# =============================================================================
+
+# GPU cost configuration (USD per hour)
+COST_GPU_A100=3.06
+COST_GPU_V100=3.06
+COST_GPU_T4=0.526
+COST_GPU_RTX=1.00
+COST_GPU_GENERIC=1.50
+
+# Cost calculation settings
+COST_TRACKING_ENABLED=true
+COST_CURRENCY=USD
+COST_UTILIZATION_MIN_FACTOR=0.1
+COST_UTILIZATION_MAX_FACTOR=1.0
+
+# =============================================================================
+# CLOUD PROVIDER INTEGRATION
+# =============================================================================
+
+# AWS Configuration (for cost tracking and resource management)
+AWS_REGION=us-west-2
+AWS_ACCESS_KEY_ID=your_aws_access_key
+AWS_SECRET_ACCESS_KEY=your_aws_secret_key
+
+# Google Cloud Platform
+GCP_PROJECT_ID=your_gcp_project
+GCP_SERVICE_ACCOUNT_KEY_PATH=path/to/service-account.json
+
+# Azure
+AZURE_SUBSCRIPTION_ID=your_azure_subscription
+AZURE_CLIENT_ID=your_azure_client_id
+AZURE_CLIENT_SECRET=your_azure_client_secret
+AZURE_TENANT_ID=your_azure_tenant_id
+
+# =============================================================================
+# DATABASE (if using persistent storage)
+# =============================================================================
+
+# Database configuration (optional - for persistent metrics storage)
+DB_ENABLED=false
+DB_TYPE=postgres
+DB_HOST=localhost
+DB_PORT=5432
+DB_NAME=agentaflow
+DB_USER=agentaflow_user
+DB_PASSWORD=your_db_password
+DB_SSL_MODE=disable
+
+# =============================================================================
+# SECURITY
+# =============================================================================
+
+# API authentication
+API_KEY=your_secure_api_key
+JWT_SECRET=your_jwt_secret_key
+AUTH_ENABLED=false
+
+# TLS configuration
+TLS_ENABLED=false
+TLS_CERT_PATH=path/to/cert.pem
+TLS_KEY_PATH=path/to/key.pem
+
+# =============================================================================
+# ALERTS & NOTIFICATIONS
+# =============================================================================
+
+# Alert thresholds
+ALERT_GPU_HIGH_UTILIZATION=90
+ALERT_GPU_HIGH_TEMPERATURE=80
+ALERT_GPU_HIGH_MEMORY=85
+ALERT_WORKLOAD_QUEUE_SIZE=100
+
+# Notification endpoints (optional)
+SLACK_WEBHOOK_URL=https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK
+EMAIL_SMTP_HOST=smtp.gmail.com
+EMAIL_SMTP_PORT=587
+EMAIL_FROM=[email protected]
+EMAIL_PASSWORD=your_email_password
+
+# =============================================================================
+# DEBUGGING & DEVELOPMENT
+# =============================================================================
+
+# Debug settings
+DEBUG_ENABLED=false
+PROFILING_ENABLED=false
+TRACE_ENABLED=false
+
+# Performance monitoring
+PERFORMANCE_MONITORING=true
+SLOW_QUERY_THRESHOLD_MS=1000
+
+# =============================================================================
+# EXPERIMENTAL FEATURES
+# =============================================================================
+
+# Feature flags
+FEATURE_AUTO_SCALING=false
+FEATURE_PREDICTIVE_SCHEDULING=false
+FEATURE_MULTI_TENANT=false
+FEATURE_ADVANCED_ANALYTICS=true
+
+# Experimental GPU features
+EXPERIMENTAL_MULTI_GPU_WORKLOADS=false
+EXPERIMENTAL_GPU_SHARING=false
+EXPERIMENTAL_DYNAMIC_BATCHING=true