RnDAO/tc-operation

version: '3.9'

x-logging:
  &logging
  logging:
    driver: loki
    options:
      loki-url: http://172.22.22.15:3100/loki/api/v1/push
      loki-retries: 5
      loki-batch-size: 400

x-sm-resources-common:
  &sm-resources-common
  deploy:
    resources:
      limits:
        cpus: '0.5'
        memory: 1G
  <<: [*logging]

x-md-resources-common:
  &md-resources-common
  deploy:
    resources:
      limits:
        cpus: '1'
        memory: 2G
  <<: [*logging]

x-lg-resources-common:
  &lg-resources-common
  deploy:
    resources:
      limits:
        cpus: '1'
        memory: 4G
  <<: [*logging]

x-xl-resources-common:
  &xl-resources-common
  deploy:
    resources:
      limits:
        cpus: '2'
        memory: 8G
  <<: [*logging]

x-redis-healthcheck:
  &redis-healthcheck
  healthcheck:
      test: [ "CMD", "redis-cli", "--raw", "incr", "ping" ]
      interval: 60s
      timeout: 10s
      retries: 2
      start_period: 40s

x-rabbitmq-healthcheck:
  &rabbitmq-healthcheck
  healthcheck:
      test: rabbitmq-diagnostics -q ping
      interval: 30s
      timeout: 30s
      retries: 2
      start_period: 40s

x-mongodb-healthcheck:
  &mongodb-healthcheck
  healthcheck:
      test: test $(echo $(mongosh -u $$MONGO_INITDB_ROOT_USERNAME -p $$MONGO_INITDB_ROOT_PASSWORD --quiet /etc/mongo/healthcheck.js)) -eq 1
      interval: 60s
      timeout: 10s
      retries: 2
      start_period: 40s

x-neo4j-healthcheck:
  &neo4j-healthcheck
  healthcheck:
    test: ["CMD" ,"wget", "http://localhost:7474"]
    interval: 1m30s
    timeout: 10s
    retries: 2
    start_period: 40s

x-redis:
  &redis
  image: redis:7.2.4
  restart: unless-stopped
  command: ["redis-server", "/usr/local/etc/redis/redis.conf"]
  networks:
    - production
    - monitoring
  <<: [*redis-healthcheck, *lg-resources-common]

x-airflow-common:
  &airflow-common
  image: ghcr.io/togethercrew/airflow-dags:main
  restart: unless-stopped
  env_file:
    &airflow-common-env
    - ./.env.airflow
  volumes:
    - airflow_logs:/opt/airflow/logs
    - airflow_config:/opt/airflow/config
    - airflow_plugins:/opt/airflow/plugins
  user: "50000:0"
  depends_on:
    &airflow-common-depends-on
    redis-airflow:
      condition: service_healthy
    pgvector:
      condition: service_healthy
    neo4j:
      condition: service_healthy
    mongodb:
      condition: service_healthy
    qdrant-healthcheck:
      condition: service_healthy
  networks:
    - production
    - monitoring
  <<: [*sm-resources-common]

x-hivemind-common:
  &hivemind-common
  image: ghcr.io/togethercrew/hivemind-bot:main
  restart: unless-stopped
  env_file:
    - ./.env.hivemind
  depends_on:
    &hivemind-common-depends-on
    neo4j:
      condition: service_healthy
    mongodb:
      condition: service_healthy
    pgvector:
      condition: service_healthy
  networks:
    - production
    - monitoring
  <<: [*sm-resources-common]

x-telegram-common:
  &telegram-common
  image: ghcr.io/togethercrew/telegram:main
  restart: unless-stopped
  env_file:
    - ./.env.telegram
  depends_on:
    rabbitmq:
      condition: service_healthy
    neo4j:
      condition: service_healthy
    mongodb:
      condition: service_healthy
  networks:
    - production
    - monitoring
  <<: [*md-resources-common]

services:

  ### DATABASES ###

  mongodb:
    container_name: mongodb
    image: mongo:7.0.5
    restart: unless-stopped
    command: ['--replSet', 'rs0', '--keyFile', '/etc/mongo/replica.key']
    ports:
      - 37017:27017
    env_file:
      - ./.env.mongodb
    volumes:
      - ../init-mongo.sh:/docker-entrypoint-initdb.d/init-mongo.sh:ro
      - ./mongo:/etc/mongo:ro
      - mongodb_data_container:/data/db
    networks:
      - production
      - monitoring
    <<: [*mongodb-healthcheck, *md-resources-common]

  rabbitmq:
    container_name: rabbitmq
    image: rabbitmq:3.12.12-management
    restart: unless-stopped
    ports:
      - 6672:5672
      - 25672:15672
    volumes:
      - rmq_data_container:/var/lib/rabbitmq/
      - ./rabbitmq/enabled_plugins:/etc/rabbitmq/enabled_plugins:ro
    env_file:
      - ./.env.rabbitmq
    networks:
      - production
      - monitoring
    <<: [*rabbitmq-healthcheck, *md-resources-common]

  neo4j:
    container_name: neo4j
    image: neo4j:5.9.0
    restart: unless-stopped
    ports:
      - 27474:7474
      - 27687:7687
    env_file:
      - ./.env.neo4j
    volumes:
      # - neo4j_conf:/var/lib/neo4j/conf
      - neo4j_data:/data
      - neo4j_import:/import
      - neo4j_plugins:/plugins
    environment:
      # Raise memory limits
      - NEO4J_server.memory.heap.initial_size=2G
      - NEO4J_server.memory.heap.max_size=4G
      - NEO4J_PLUGINS=["apoc", "graph-data-science"]
      - NEO4J_dbms_security_procedures_unrestricted=apoc.*,gds.*
    networks:
      - production
      - monitoring
    <<: [*neo4j-healthcheck, *xl-resources-common]

  pgvector:
    container_name: pgvector
    image: ankane/pgvector:v0.5.1
    ports:
      - 45432:5432
    env_file:
      ./.env.pgvector
    volumes:
      - pgvector_data:/var/lib/postgresql/data
    healthcheck:
      test: pg_isready -U $$POSTGRES_USER -d $$POSTGRES_DB
      interval: 10s
      retries: 5
      start_period: 5s
    restart: always
    networks:
      - production
      - monitoring
    <<: [*md-resources-common]

  qdrant:
    container_name: qdrant
    image: qdrant/qdrant:v1.9.2
    restart: always
    ports:
      - 6333:6333
    volumes:
      - qdrant_data:/qdrant/storage
      - qdrant_snapshots:/qdrant/snapshots
    networks:
      - production
      - monitoring
    <<: [*lg-resources-common]

  qdrant-healthcheck:
    container_name: qdrant-healthcheck
    restart: always
    image: curlimages/curl:latest
    entrypoint: ["/bin/sh", "-c", "--", "while true; do sleep 30; done;"]
    depends_on:
      - qdrant
    healthcheck:
      test: ["CMD", "curl", "-f", "http://qdrant:6333/readyz"]
      interval: 10s
      timeout: 2s
      retries: 5
    networks:
      - production
      - monitoring
    <<: [*sm-resources-common]

  redis-discord:
    container_name: redis-discord
    volumes:
      - ./redis/discord.conf:/usr/local/etc/redis/redis.conf:ro
    <<: [*redis]

  redis-analyzer:
    container_name: redis-analyzer
    volumes:
      - ./redis/analyzer.conf:/usr/local/etc/redis/redis.conf:ro
    <<: [*redis]

  redis-api:
    container_name: redis-api
    volumes:
      - ./redis/api.conf:/usr/local/etc/redis/redis.conf:ro
    <<: [*redis]

  redis-discourse:
    container_name: redis-discourse
    volumes:
      - ./redis/discourse.conf:/usr/local/etc/redis/redis.conf:ro
    <<: [*redis]

  redis-airflow:
    container_name: redis-airflow
    volumes:
      - ./redis/airflow.conf:/usr/local/etc/redis/redis.conf:ro
    <<: [*redis]

  redis-cadvisor:
    container_name: redis-cadvisor
    volumes:
      - ./redis/cadvisor.conf:/usr/local/etc/redis/redis.conf:ro
    <<: [*redis]


  ### SERVICES ###

  api:
    container_name: api
    image: ghcr.io/togethercrew/api:main
    restart: unless-stopped
    environment:
      PORT: $PORT
    ports:
      - $HOST:$PORT:$PORT
    env_file:
      - ./.env.api
    depends_on:
      mongodb:
        condition: service_healthy
      neo4j:
        condition: service_healthy
      rabbitmq:
        condition: service_healthy
      redis-api:
        condition: service_healthy
    volumes:
      - ./githubapp.private-key.pem:/project/githubapp.private-key.pem:ro
    networks:
      - production
      - monitoring
    <<: [*sm-resources-common]

  discord:
    container_name: discord
    image: ghcr.io/togethercrew/discord-bot:development
    restart: unless-stopped
    env_file:
      - ./.env.discord
    ports:
      - 3300:3000
    depends_on:
      mongodb:
        condition: service_healthy
      redis-discord:
        condition: service_healthy
      rabbitmq:
        condition: service_healthy
    networks:
      - production
      - monitoring
    <<: [*lg-resources-common]

  analyzer-server:
    container_name: analyzer-server
    image: ghcr.io/togethercrew/discord-analyzer:pr-70
    command: python3 server.py
    restart: unless-stopped
    env_file:
      - ./.env.analyzer
    depends_on:
      redis-analyzer:
        condition: service_healthy
      rabbitmq:
        condition: service_healthy
    networks:
      - production
      - monitoring
    <<: [*sm-resources-common]

  analyzer-worker:
    container_name: analyzer-worker
    image: ghcr.io/togethercrew/discord-analyzer:pr-70
    command: python3 worker.py
    restart: unless-stopped
    env_file:
      - ./.env.analyzer
    depends_on:
      mongodb:
        condition: service_healthy
      redis-analyzer:
        condition: service_healthy
      neo4j:
        condition: service_healthy
      rabbitmq:
        condition: service_healthy
    networks:
      - production
      - monitoring
    <<: [*md-resources-common]

  discourse:
    container_name: discourse
    image: ghcr.io/togethercrew/discourse:main
    command: yarn run start:prod
    restart: always
    ports:
      - 43001:3000
    env_file:
      - .env.discourse
    depends_on:
      redis-discourse:
        condition: service_healthy
      rabbitmq:
        condition: service_healthy
      neo4j:
        condition: service_healthy
    networks:
      - discourse
      - production
      - monitoring
    <<: [*md-resources-common]

  ### AIRFLOW ###

  airflow-webserver:
    container_name: airflow-webserver
    <<: *airflow-common
    command: webserver
    ports:
      - 48080:8080
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8080/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-scheduler:
    container_name: airflow-scheduler
    <<: *airflow-common
    command: scheduler
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8974/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-worker:
    container_name: airflow-worker
    <<: [*airflow-common, *lg-resources-common]
    command: celery worker
    healthcheck:
      # yamllint disable rule:line-length
      test:
        - "CMD-SHELL"
        - 'celery --app airflow.providers.celery.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}" || celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"'
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    environment:
      # Required to handle warm shutdown of the celery workers properly
      # See https://airflow.apache.org/docs/docker-stack/entrypoint.html#signal-propagation
      DUMB_INIT_SETSID: "0"
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-triggerer:
    container_name: airflow-triggerer
    <<: *airflow-common
    command: triggerer
    healthcheck:
      test: ["CMD-SHELL", 'airflow jobs check --job-type TriggererJob --hostname "$${HOSTNAME}"']
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-init:
    container_name: airflow-init
    restart: "no"
    <<: *airflow-common
    entrypoint: /bin/bash
    command: -c "./init.sh"
    env_file:
      - ./.env.airflow
      - ./.env.airflow.init
    user: "0:0"
    volumes:
      - airflow_sources:/sources

  airflow-cli:
    container_name: airflow-cli
    restart: "no"
    <<: *airflow-common
    profiles:
      - debug
    environment:
      CONNECTION_CHECK_MAX_COUNT: "0"
    # Workaround for entrypoint issue. See: https://github.com/apache/airflow/issues/16252
    command: bash -c airflow

  # You can enable flower by adding "--profile flower" option e.g. docker-compose --profile flower up
  # or by explicitly targeted on the command line e.g. docker-compose up flower.
  # See: https://docs.docker.com/compose/profiles/
  flower:
    container_name: flower
    <<: *airflow-common
    command: celery flower
    profiles:
      - flower
    ports:
      - "5555:5555"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:5555/"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: unless-stopped
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  hivemind-server:
    container_name: hivemind-server
    <<: [*hivemind-common, *sm-resources-common]
    depends_on:
      <<: *hivemind-common-depends-on

  hivemind-worker:
    container_name: hivemind-worker
    <<: [*hivemind-common, *md-resources-common]
    command: python3 worker.py

  ### TELEGRAM

  telegram-bot:
    <<: [*telegram-common]
    container_name: telegram-bot
    command: ["node", "dist/apps/bot/main"]

  telegram-events:
    <<: [*telegram-common]
    container_name: telegram-events
    command: ["node", "dist/apps/event-store/main"]

  telegram-graph:
    <<: [*telegram-common]
    container_name: telegram-graph
    command: ["node", "dist/apps/graph-store/main"]

  ### ADMIN

  admin-panel:
    container_name: admin-panel
    image: ghcr.io/togethercrew/admin-panel:main
    restart: always
    ports:
      - 8501:8501
    env_file:
      - .env.admin-panel
    depends_on:
      mongodb:
        condition: service_healthy
      neo4j:
        condition: service_healthy
    networks:
      - production
      - monitoring
    <<: [*md-resources-common]

  ### MONITORING

  grafana:
    container_name: grafana
    image: grafana/grafana:10.3.3
    restart: unless-stopped
    volumes:
      - ./grafana/provisioning/:/etc/grafana/provisioning
      - grafana_volume:/var/lib/grafana
    depends_on:
      - prometheus
      - loki
    ports:
      - 3000:3000
    networks:
      - monitoring
    <<: [*sm-resources-common]

  prometheus:
    container_name: prometheus
    image: prom/prometheus:v2.49.1
    command:
      - --config.file=/etc/prometheus/prometheus.yml
    restart: unless-stopped
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus_volume:/prometheus
    depends_on:
      - cadvisor
      - node-exporter
    networks:
      - monitoring
    <<: [*sm-resources-common]

  cadvisor:
    container_name: cadvisor
    image: gcr.io/cadvisor/cadvisor:v0.47.2
    restart: unless-stopped
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
    depends_on:
      - redis-cadvisor
    networks:
      - monitoring
    <<: [*sm-resources-common]

  loki:
    container_name: loki
    image: grafana/loki:2.8.0
    restart: unless-stopped
    ports:
      - 3100
    volumes:
      - ./loki/loki-config.yaml:/etc/loki/loki-config.yaml
      - loki_volume:/data/loki
    command: -config.file=/etc/loki/loki-config.yaml
    networks:
      monitoring:
        ipv4_address: 172.22.22.15
    <<: [*sm-resources-common]

  node-exporter:
    container_name: node-exporter
    image: prom/node-exporter:v1.7.0
    restart: unless-stopped
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.rootfs=/rootfs'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    networks:
      - monitoring
    <<: [*sm-resources-common]

  otel-collector:
    container_name: otel-collector
    image: otel/opentelemetry-collector:0.92.0
    command: [ "--config=/etc/otel-collector.yaml" ]
    restart: unless-stopped
    volumes:
      - ./otel-collector/otel-collector.yaml:/etc/otel-collector.yaml
    networks:
      - monitoring
      - production
    <<: [*sm-resources-common]

  tempo:
    container_name: tempo
    image: grafana/tempo:2.3.1
    command: [ "-config.file=/etc/tempo.yaml" ]
    restart: unless-stopped
    volumes:
      - ./tempo/tempo.yaml:/etc/tempo.yaml
      - tempo_data:/tmp/tempo
    networks:
      - monitoring
      - production
    <<: [*sm-resources-common]

  pyroscope:
    container_name: pyroscope
    image: grafana/pyroscope:1.4.0
    restart: unless-stopped
    networks:
      - monitoring
      - production
    <<: [*sm-resources-common]

  ### SERVICE MANAGEMENT ###

  watchtower:
    container_name: watchtower
    image: containrrr/watchtower:1.7.1
    command: --interval 10 --http-api-metrics --http-api-token demotoken -d
    restart: unless-stopped
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
    networks:
      - monitoring
    <<: [*sm-resources-common]

volumes:
  mongodb_data_container:
  rmq_data_container:
  grafana_volume:
  graphite_volume:
  prometheus_volume:
  loki_volume:
  neo4j_data:
  neo4j_import:
  neo4j_plugins:
  hivemind_vector_store:
  pgvector_data:
  airflow_config:
  airflow_logs:
  airflow_plugins:
  airflow_sources:
  tempo_data:
  qdrant_data:
  qdrant_snapshots:

networks:
  production:
    driver: bridge
  hivemind:
    driver: bridge
  discourse:
    driver: bridge
  monitoring:
    driver: bridge
    ipam:
      config:
        - subnet: 172.22.22.0/16