name: tools-litellm
services:
  postgres:
    image: postgres:17-alpine@sha256:b0f9560a2de083e2cc7382e75f808c7381a32852a7ec49117deedb300e552b24
    container_name: tools-litellm-postgres
    restart: unless-stopped
    environment:
      POSTGRES_DB: litellm
      POSTGRES_USER: litellm
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?required}
      TZ: Asia/Shanghai
    volumes:
      - database:/var/lib/postgresql/data
    healthcheck:
      test: [CMD-SHELL, 'pg_isready -U litellm -d litellm']
      interval: 10s
      timeout: 5s
      retries: 10
    logging:
      driver: json-file
      options: {max-size: 10m, max-file: "3"}

  litellm:
    image: ghcr.io/berriai/litellm:main-stable@sha256:3d88bd757134a00e8c00237b85a021ab1f6d54abb9c1df750f411dbe7256a500
    container_name: tools-litellm
    restart: unless-stopped
    depends_on:
      postgres:
        condition: service_healthy
    ports:
      - '${LISTEN_ADDRESS:-192.168.50.49}:${LITELLM_PORT:-4000}:4000'
    environment:
      TZ: Asia/Shanghai
      DATABASE_URL: postgresql://litellm:${POSTGRES_PASSWORD:?required}@postgres:5432/litellm
      LITELLM_MASTER_KEY: ${LITELLM_MASTER_KEY:?required}
      LITELLM_SALT_KEY: ${LITELLM_SALT_KEY:?required}
      ZENMUX_SUBSCRIPTION_API_KEY: ${ZENMUX_SUBSCRIPTION_API_KEY:-}
      ZENMUX_PAYG_API_KEY: ${ZENMUX_PAYG_API_KEY:-}
      OPENROUTER_API_KEY: ${OPENROUTER_API_KEY:-}
      OPENAI_API_KEY: ${OPENAI_API_KEY:-}
      BAILIAN_CN_API_KEY: ${BAILIAN_CN_API_KEY:-}
      BAILIAN_CN_API_BASE: ${BAILIAN_CN_API_BASE:-https://ws-v68kvjnmhkiejaxo.cn-beijing.maas.aliyuncs.com/api/v1}
      GOOGLE_AI_STUDIO_API_KEY: ${GOOGLE_AI_STUDIO_API_KEY:-}
      VERTEXAI_ENABLED: ${VERTEXAI_ENABLED:-false}
      VERTEXAI_PROJECT: ${VERTEXAI_PROJECT:-}
      VERTEXAI_LOCATION: ${VERTEXAI_LOCATION:-global}
      GOOGLE_APPLICATION_CREDENTIALS: /tokens/google/adc.json
      CHATGPT_TOKEN_DIR: /tokens/chatgpt
      XAI_OAUTH_TOKEN_DIR: /tokens/xai
      LITELLM_LOG: WARNING
    volumes:
      - ./models.yaml:/etc/litellm/models.yaml:ro
      - ./render_config.py:/etc/litellm/render_config.py:ro
      - ./personal_transcription.py:/etc/litellm/personal_transcription.py:ro
      - ./bailian_transcription.py:/etc/litellm/bailian_transcription.py:ro
      - /opt/litellm/personal-vocabulary.json:/etc/litellm/personal-vocabulary.json:ro
      - oauth:/tokens
    entrypoint: [/bin/sh, -c]
    command:
      - 'python /etc/litellm/render_config.py && exec python /etc/litellm/personal_transcription.py --config /tmp/litellm.yaml --host 0.0.0.0 --port 4000 --num_workers 1'
    healthcheck:
      test: [CMD, python, -c, 'import urllib.request; urllib.request.urlopen("http://127.0.0.1:4000/health/liveliness", timeout=5)']
      interval: 30s
      timeout: 10s
      retries: 6
      start_period: 120s
    logging:
      driver: json-file
      options: {max-size: 10m, max-file: "3"}

volumes:
  database:
    name: tools-litellm-database
  oauth:
    name: tools-litellm-oauth