agent-platform/docker-compose.yml

services:
  postgres:
    image: postgres:16-alpine
    environment:
      POSTGRES_DB: agent_platform
      POSTGRES_USER: agent
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-CHANGE_ME}
    ports:
      - "15432:5432"
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U agent -d agent_platform"]
      interval: 5s
      timeout: 5s
      retries: 20

  redis:
    image: redis:7-alpine
    command: redis-server --appendonly yes --maxmemory 512mb --maxmemory-policy allkeys-lru
    ports:
      - "16379:6379"
    volumes:
      - redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 5s
      retries: 20

  etcd:
    image: quay.io/coreos/etcd:v3.5.5
    command: >-
      etcd -advertise-client-urls=http://127.0.0.1:2379
      -listen-client-urls=http://0.0.0.0:2379
      --data-dir /etcd
    ports:
      - "2379:2379"
    volumes:
      - etcd_data:/etcd
    healthcheck:
      test: ["CMD-SHELL", "etcdctl endpoint health --endpoints=http://127.0.0.1:2379"]
      interval: 10s
      timeout: 5s
      retries: 20

  minio:
    image: minio/minio:RELEASE.2024-01-13T07-53-03Z
    command: server /data --console-address :9001
    environment:
      MINIO_ROOT_USER: minioadmin
      MINIO_ROOT_PASSWORD: minioadmin
    ports:
      - "9000:9000"
      - "9001:9001"
    volumes:
      - minio_data:/data
    healthcheck:
      test:
        [
          "CMD-SHELL",
          "mc ready local >/dev/null 2>&1 || curl -fsS http://localhost:9000/minio/health/live >/dev/null",
        ]
      interval: 10s
      timeout: 5s
      retries: 20

  milvus:
    image: milvusdb/milvus:v2.4.15
    command: ["milvus", "run", "standalone"]
    environment:
      ETCD_ENDPOINTS: etcd:2379
      MINIO_ADDRESS: minio:9000
      MILVUS_LOG_LEVEL: info
    depends_on:
      etcd:
        condition: service_healthy
      minio:
        condition: service_healthy
    ports:
      - "19531:19530"
      - "19091:9091"
    volumes:
      - milvus_data:/var/lib/milvus
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:9091/healthz"]
      interval: 10s
      timeout: 5s
      retries: 30

  otel-collector:
    image: otel/opentelemetry-collector-contrib:0.110.0
    command: ["--config=/etc/otel/config.yaml"]
    volumes:
      - ./docker/otel-collector-config.yml:/etc/otel/config.yaml:ro
    ports:
      - "4317:4317"
      - "4318:4318"
      - "13133:13133"
      - "8889:8889"
    healthcheck:
      test: ["CMD", "/otelcol-contrib", "--version"]
      interval: 2s
      timeout: 5s
      retries: 2
      start_period: 1s

  prometheus:
    image: prom/prometheus:v2.54.0
    command: ["--config.file=/etc/prometheus/prometheus.yml"]
    volumes:
      - ./docker/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus_data:/prometheus
    ports:
      - "19090:9090"
    healthcheck:
      test: ["CMD-SHELL", "wget -q -O - http://localhost:9090/-/ready >/dev/null"]
      interval: 10s
      timeout: 5s
      retries: 20

  grafana:
    image: grafana/grafana:11.2.0
    environment:
      GF_AUTH_ANONYMOUS_ENABLED: "true"
      GF_AUTH_ANONYMOUS_ORG_ROLE: Admin
    volumes:
      - ./core/observability/dashboards/:/var/lib/grafana/dashboards/
      - grafana_data:/var/lib/grafana
    ports:
      - "13000:3000"
    healthcheck:
      test: ["CMD-SHELL", "wget -q -O - http://localhost:3000/api/health >/dev/null"]
      interval: 10s
      timeout: 5s
      retries: 20

  api:
    build:
      context: .
      dockerfile: docker/Dockerfile.api
      target: builder
    command: uv run --frozen uvicorn api.main:app --host 0.0.0.0 --port 8000 --reload
    env_file:
      - .env
    environment:
      DATABASE_URL: "postgresql+asyncpg://agent:${POSTGRES_PASSWORD:-CHANGE_ME}@postgres:5432/agent_platform"
      REDIS_URL: "redis://redis:6379/0"
      MILVUS_HOST: milvus
      MILVUS_PORT: 19530
      OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4317
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
      milvus:
        condition: service_healthy
    volumes:
      - .:/app
      - /app/.venv
    ports:
      - "18000:8000"
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:8000/health"]
      interval: 10s
      timeout: 5s
      retries: 20

volumes:
  postgres_data:
  redis_data:
  etcd_data:
  minio_data:
  milvus_data:
  prometheus_data:
  grafana_data: