docker-compose.yml

# Local production-like stack for Phase 1. Usage: docker compose up -d --build
# Host ports chosen to avoid clashes with existing Postgres (5432) / Neo4j (7474, 7687) on the machine.
#
# This is the prod-oriented compose variant: backend runs from the built image, frontend is a static Vite build
# behind nginx on :8787. For hot-reload development use `docker-compose.dev.yml` or `make dev-up`.
#
# `web` (nginx) publishes :8787 and proxies /v1, /health, etc. to `api`. Rebuild UI only: docker compose build web
# Rebuild backend only: docker compose build api
#
# API uses Docker network hostnames (postgres, neo4j, qdrant). Host .env with localhost:* is for
# CLI/benchmarks on the machine; override via compose `environment` below when running the API container.
services:
  neo4j:
    image: neo4j:5-community
    env_file:
      - .env
    ports:
      - "17474:7474"
      - "17687:7687"
    environment:
      NEO4J_AUTH: ${SCIENCE_GRAPHRAG_NEO4J_USER:-neo4j}/${SCIENCE_GRAPHRAG_NEO4J_PASSWORD:-change-me}
    volumes:
      - neo4j_data:/data
    healthcheck:
      test: ["CMD", "wget", "-q", "-O", "-", "http://127.0.0.1:7474"]
      interval: 20s
      timeout: 10s
      retries: 6
      start_period: 30s

  postgres:
    image: postgres:16-alpine
    env_file:
      - .env
    ports:
      - "15432:5432"
    environment:
      POSTGRES_USER: ${POSTGRES_USER:-science}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-change-me}
      POSTGRES_DB: ${POSTGRES_DB:-science_graphrag}
    volumes:
      - pg_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-science} -d ${POSTGRES_DB:-science_graphrag}"]
      interval: 20s
      timeout: 8s
      retries: 8
      start_period: 15s

  qdrant:
    image: qdrant/qdrant:v1.12.4
    ports:
      - "16333:6333"
    volumes:
      - qdrant_data:/qdrant/storage
    healthcheck:
      test: ["CMD", "/qdrant/qdrant", "--version"]
      interval: 20s
      timeout: 8s
      retries: 8
      start_period: 10s

  redis:
    image: redis:7-alpine
    command: ["redis-server", "--appendonly", "yes", "--maxmemory", "512mb", "--maxmemory-policy", "allkeys-lru"]
    ports:
      - "16379:6379"
    volumes:
      - redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 20s
      timeout: 5s
      retries: 5

  minio:
    image: minio/minio:latest
    command: ["server", "/data", "--console-address", ":9001"]
    ports:
      - "19000:9000"
      - "19001:9001"
    environment:
      MINIO_ROOT_USER: ${MINIO_ROOT_USER:-minioadmin}
      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-minioadmin}
    volumes:
      - minio_data:/data
    healthcheck:
      test: ["CMD", "curl", "-f", "http://127.0.0.1:9000/minio/health/live"]
      interval: 15s
      timeout: 5s
      retries: 5
      start_period: 15s

  phoenix:
    # Override in `.env` for deterministic builds, e.g.:
    # SCIENCE_GRAPHRAG_PHOENIX_IMAGE=arizephoenix/phoenix@sha256:<digest>
    image: ${SCIENCE_GRAPHRAG_PHOENIX_IMAGE:-arizephoenix/phoenix:latest}
    ports:
      - "16006:6006"
      - "14317:4317"
    volumes:
      - phoenix_data:/mnt/data
    healthcheck:
      test:
        [
          "CMD",
          "python3",
          "-c",
          "import urllib.request; urllib.request.urlopen('http://127.0.0.1:6006', timeout=5)",
        ]
      interval: 30s
      timeout: 10s
      retries: 6
      start_period: 20s

  api:
    build:
      context: .
      dockerfile: Dockerfile
    expose:
      - "8787"
    ports:
      # Optional: hit FastAPI directly (bypasses nginx /ui). Main entry remains `web` :8787.
      - "18787:8787"
    env_file:
      - .env
    environment:
      # Keep DB credentials in sync with the postgres service defaults/.env values.
      SCIENCE_GRAPHRAG_DATABASE_URL: ${SCIENCE_GRAPHRAG_DATABASE_URL_DOCKER:-postgresql+psycopg://${POSTGRES_USER:-science}:${POSTGRES_PASSWORD:-change-me}@postgres:5432/${POSTGRES_DB:-science_graphrag}}
      SCIENCE_GRAPHRAG_NEO4J_URI: bolt://neo4j:7687
      SCIENCE_GRAPHRAG_NEO4J_USER: ${SCIENCE_GRAPHRAG_NEO4J_USER:-neo4j}
      SCIENCE_GRAPHRAG_NEO4J_PASSWORD: ${SCIENCE_GRAPHRAG_NEO4J_PASSWORD:-change-me}
      SCIENCE_GRAPHRAG_QDRANT_URL: http://qdrant:6333
      SCIENCE_GRAPHRAG_REDIS_URL: redis://redis:6379/0
      SCIENCE_GRAPHRAG_AGENT_SESSION_MEMORY_BACKEND: redis
      SCIENCE_GRAPHRAG_BLOB_ROOT: /data/blobs
      SCIENCE_GRAPHRAG_ARTIFACT_ROOT: /data/artifacts
      PHOENIX_COLLECTOR_ENDPOINT: http://phoenix:6006/v1/traces
      # One LangGraph turn wall clock (sync JSON or SSE collection). Override from host shell, e.g.
      # ``SCIENCE_GRAPHRAG_AGENT_STEP_TIMEOUT_SECONDS=300 docker compose up -d api``.
      SCIENCE_GRAPHRAG_AGENT_STEP_TIMEOUT_SECONDS: ${SCIENCE_GRAPHRAG_AGENT_STEP_TIMEOUT_SECONDS:-240}
      # Phase 1: MinIO on compose network (override via .env MINIO_ROOT_* if needed).
      SCIENCE_GRAPHRAG_S3_ENDPOINT_URL: http://minio:9000
      SCIENCE_GRAPHRAG_S3_ACCESS_KEY_ID: ${MINIO_ROOT_USER:-minioadmin}
      SCIENCE_GRAPHRAG_S3_SECRET_ACCESS_KEY: ${MINIO_ROOT_PASSWORD:-minioadmin}
      SCIENCE_GRAPHRAG_S3_BUCKET: science-raw
      SCIENCE_GRAPHRAG_S3_USE_SSL: "false"
    volumes:
      - ./data/blobs:/data/blobs
      - ./data/artifacts:/data/artifacts
    depends_on:
      postgres:
        condition: service_healthy
      neo4j:
        condition: service_healthy
      qdrant:
        condition: service_healthy
      redis:
        condition: service_healthy
      minio:
        condition: service_healthy
    healthcheck:
      test:
        [
          "CMD",
          "python",
          "-c",
          "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8787/health', timeout=5)",
        ]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 25s

  web:
    build:
      context: .
      dockerfile: Dockerfile.web
    ports:
      - "8787:80"
    depends_on:
      api:
        condition: service_healthy
    healthcheck:
      test:
        [
          "CMD",
          "wget",
          "-q",
          "-O",
          "-",
          "http://127.0.0.1/health",
        ]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 10s

  worker:
    build:
      context: .
      dockerfile: Dockerfile
    command: ["python", "-m", "science_graphrag.worker"]
    env_file:
      - .env
    environment:
      SCIENCE_GRAPHRAG_DATABASE_URL: ${SCIENCE_GRAPHRAG_DATABASE_URL_DOCKER:-postgresql+psycopg://${POSTGRES_USER:-science}:${POSTGRES_PASSWORD:-change-me}@postgres:5432/${POSTGRES_DB:-science_graphrag}}
      SCIENCE_GRAPHRAG_NEO4J_URI: bolt://neo4j:7687
      SCIENCE_GRAPHRAG_NEO4J_USER: ${SCIENCE_GRAPHRAG_NEO4J_USER:-neo4j}
      SCIENCE_GRAPHRAG_NEO4J_PASSWORD: ${SCIENCE_GRAPHRAG_NEO4J_PASSWORD:-change-me}
      SCIENCE_GRAPHRAG_QDRANT_URL: http://qdrant:6333
      SCIENCE_GRAPHRAG_REDIS_URL: redis://redis:6379/0
      SCIENCE_GRAPHRAG_BLOB_ROOT: /data/blobs
      SCIENCE_GRAPHRAG_ARTIFACT_ROOT: /data/artifacts
      PHOENIX_COLLECTOR_ENDPOINT: http://phoenix:6006/v1/traces
      SCIENCE_GRAPHRAG_S3_ENDPOINT_URL: http://minio:9000
      SCIENCE_GRAPHRAG_S3_ACCESS_KEY_ID: ${MINIO_ROOT_USER:-minioadmin}
      SCIENCE_GRAPHRAG_S3_SECRET_ACCESS_KEY: ${MINIO_ROOT_PASSWORD:-minioadmin}
      SCIENCE_GRAPHRAG_S3_BUCKET: science-raw
      SCIENCE_GRAPHRAG_S3_USE_SSL: "false"
    volumes:
      - ./data/blobs:/data/blobs
      - ./data/artifacts:/data/artifacts
    depends_on:
      postgres:
        condition: service_healthy
      neo4j:
        condition: service_healthy
      qdrant:
        condition: service_healthy
      redis:
        condition: service_healthy
      minio:
        condition: service_healthy

volumes:
  neo4j_data:
  pg_data:
  qdrant_data:
  phoenix_data:
  redis_data:
  minio_data: