# documentation: https://docs.argilla.io/latest/
# slogan: Argilla is a collaboration tool for AI engineers and domain experts who need to build high-quality datasets for their projects.
# tags: workflow, orchestration, data-pipeline, python, argilla, ai, elasticsearch, datasets, data, machine-learning, data-science, nlp
# logo: svgs/argilla.png
# port: 6900

version: "3"

services:
  argilla:
    image: "argilla/argilla-server:v2.2.0"
    restart: always
    environment:
      - SERVICE_FQDN_ARGILLA_6900
      - ARGILLA_HOME_PATH=/var/lib/argilla
      - ARGILLA_ELASTICSEARCH=http://elasticsearch:9200
      - ARGILLA_DATABASE_URL=postgresql+asyncpg://${SERVICE_USER_POSTGRES}:${SERVICE_PASSWORD_POSTGRES}@postgres:5432/${POSTGRES_DB}
      - ARGILLA_REDIS_URL=redis://redis:6379/0
      - ARGILLA_AUTH_SECRET_KEY="${SERVICE_PASSWORD_AUTHSECRET}"
      - ARGILLA_ENABLE_TELEMETRY=0
      - HF_HUB_DISABLE_TELEMETRY=1
      - REINDEX_DATASETS=1
      - DEFAULT_USER_ENABLED=true
      - USERNAME=${ARGILLA_USERNAME:-argilla}
      - PASSWORD="${SERVICE_PASSWORD_ARGILLA}"
      - API_KEY="${SERVICE_PASSWORD_APIKEY}"
      - DEFAULT_USER_PASSWORD="${SERVICE_PASSWORD_ARGILLA}"
      - DEFAULT_USER_API_KEY="${SERVICE_PASSWORD_APIKEY}"
    depends_on:
      elasticsearch:
        condition: service_healthy
      redis:
        condition: service_healthy
      postgres:
        condition: service_healthy
    volumes:
      - "argilla_data:/var/lib/argilla"
    healthcheck:
      test:
        - CMD-SHELL
        - 'python -c "import requests as r;r.get(\"http://localhost:6900/api/_status\").raise_for_status()"'
      interval: 10s
      timeout: 10s
      retries: 5
  worker:
    image: "argilla/argilla-server:v2.2.0"
    restart: always
    environment:
      - ARGILLA_HOME_PATH=/var/lib/argilla
      - ARGILLA_ELASTICSEARCH=http://elasticsearch:9200
      - ARGILLA_DATABASE_URL=postgresql+asyncpg://${SERVICE_USER_POSTGRES}:${SERVICE_PASSWORD_POSTGRES}@postgres:5432/${POSTGRES_DB}
      - ARGILLA_REDIS_URL=redis://redis:6379/0
      - ARGILLA_AUTH_SECRET_KEY="${SERVICE_PASSWORD_AUTHSECRET}"
      - ARGILLA_ENABLE_TELEMETRY=0
      - HF_HUB_DISABLE_TELEMETRY=1
      - REINDEX_DATASETS=1
      - DEFAULT_USER_ENABLED=true
      - USERNAME=${ARGILLA_USERNAME:-argilla}
      - PASSWORD="${SERVICE_PASSWORD_ARGILLA}"
      - API_KEY="${SERVICE_PASSWORD_APIKEY}"
      - DEFAULT_USER_PASSWORD="${SERVICE_PASSWORD_ARGILLA}"
      - DEFAULT_USER_API_KEY="${SERVICE_PASSWORD_APIKEY}"
      - BACKGROUND_NUM_WORKERS=${BACKGROUND_NUM_WORKERS:-1}
    depends_on:
      elasticsearch:
        condition: service_healthy
      redis:
        condition: service_healthy
      postgres:
        condition: service_healthy
    volumes:
      - "argilla_data:/var/lib/argilla"
    command: "sh -c 'python -m argilla_server worker --num-workers $${BACKGROUND_NUM_WORKERS}'"
    healthcheck:
      test:
        - CMD-SHELL
        - pwd
      interval: 10s
      timeout: 10s
      retries: 5
  postgres:
    image: "postgres:14"
    restart: always
    environment:
      - POSTGRES_USER=${SERVICE_USER_POSTGRES}
      - POSTGRES_PASSWORD=${SERVICE_PASSWORD_POSTGRES}
      - POSTGRES_DB=${POSTGRES_DB:-argilla}
    volumes:
      - "pg_data:/var/lib/postgresql/data"
    healthcheck:
      test:
        - CMD-SHELL
        - "pg_isready -h localhost -U $${POSTGRES_USER} -d $${POSTGRES_DB}"
      interval: 5s
      timeout: 5s
      retries: 3
  redis:
    image: "redis:7"
    restart: always
    volumes:
      - "redis_data:/data"
    healthcheck:
      test:
        - CMD-SHELL
        - "redis-cli -h localhost -p 6379 ping"
      interval: 5s
      timeout: 5s
      retries: 3
  elasticsearch:
    image: "docker.elastic.co/elasticsearch/elasticsearch:8.12.2"
    restart: always
    environment:
      - node.name=elasticsearch
      - cluster.name=es-argilla-local
      - discovery.type=single-node
      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
      - cluster.routing.allocation.disk.threshold_enabled=false
      - xpack.security.enabled=false
    ulimits:
      memlock:
        soft: -1
        hard: -1
    volumes:
      - "elasticsearch_data:/usr/share/elasticsearch/data/"
    healthcheck:
      test:
        - CMD-SHELL
        - "curl --silent --fail http://elasticsearch:9200"
      interval: 10s
      timeout: 10s
      retries: 5
volumes:
  argilla_data: null
  elastic_data: null
  redis_data: null
  pg_data: null