docker-compose.yml

version: "3.9"

services:
  litellm:
    image: ghcr.io/berriai/litellm:main-latest
    restart: unless-stopped
    volumes:
      - ./litellm_config.yaml:/app/config.yaml
    env_file: .env
    # Port 4000 is internal only — not exposed to LAN
    expose:
      - "4000"
    command: ["--config", "/app/config.yaml", "--port", "4000", "--detailed_debug"]
    deploy:
      resources:
        limits:
          memory: 512M
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:4000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s

  app:
    build: ./app
    restart: unless-stopped
    env_file: .env
    ports:
      - "${APP_PORT:-7860}:7860"
    depends_on:
      - litellm
    volumes:
      - ./app:/app       # live editing without rebuild during dev
      - ./litellm_config.yaml:/litellm_config.yaml:ro  # models_config.py reads this
    environment:
      - LITELLM_BASE_URL=http://litellm:4000