docker-compose.yml

version: "3.9"

services:
  # ── RAG API ───────────────────────────────────────────────────
  api:
    build: .
    container_name: smartrag-api
    ports:
      - "8000:8000"
    volumes:
      - ./artifacts:/app/artifacts       # Persist models + vectorstore
      - huggingface_cache:/app/.cache/huggingface
    environment:
      - MLFLOW_TRACKING_URI=http://mlflow:5000
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    depends_on:
      - mlflow
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 90s

  # ── Streamlit UI ──────────────────────────────────────────────
  ui:
    build:
      context: .
      dockerfile: Dockerfile.ui
    container_name: smartrag-ui
    ports:
      - "8501:8501"
    environment:
      - API_BASE=http://api:8000
    depends_on:
      api:
        condition: service_healthy
    restart: unless-stopped

  # ── MLflow Tracking Server ────────────────────────────────────
  mlflow:
    image: ghcr.io/mlflow/mlflow:v2.12.0
    container_name: smartrag-mlflow
    ports:
      - "5000:5000"
    volumes:
      - mlflow_data:/mlflow
    command: >
      mlflow server
      --host 0.0.0.0
      --port 5000
      --backend-store-uri sqlite:///mlflow/mlflow.db
      --default-artifact-root /mlflow/artifacts
    restart: unless-stopped

volumes:
  huggingface_cache:
  mlflow_data: