name: onyx

services:
  api_server:
    image: onyxdotapp/onyx-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
    command: >
      /bin/sh -c "
      alembic upgrade head &&
      echo \"Starting Onyx Api Server\" &&
      uvicorn onyx.main:app --host 0.0.0.0 --port 8080"
    depends_on:
      - relational_db
      - opensearch
      - cache
      - minio
      - inference_model_server
    restart: unless-stopped
    environment:
      - AUTH_TYPE=${AUTH_TYPE:-oidc}
      - POSTGRES_HOST=relational_db
      - OPENSEARCH_HOST=${OPENSEARCH_HOST:-opensearch}
      - OPENSEARCH_ADMIN_PASSWORD=${OPENSEARCH_ADMIN_PASSWORD:-StrongPassword123!}
      - REDIS_HOST=cache
      - MODEL_SERVER_HOST=${MODEL_SERVER_HOST:-inference_model_server}
      - CODE_INTERPRETER_BASE_URL=${CODE_INTERPRETER_BASE_URL:-http://code-interpreter:8000}
      - USE_IAM_AUTH=${USE_IAM_AUTH}
      - AWS_REGION_NAME=${AWS_REGION_NAME-}
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID-}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY-}
      # MinIO configuration
      - S3_ENDPOINT_URL=${S3_ENDPOINT_URL:-http://minio:9000}
      - S3_AWS_ACCESS_KEY_ID=${S3_AWS_ACCESS_KEY_ID:?set a strong value in .env, not minioadmin}
      - S3_AWS_SECRET_ACCESS_KEY=${S3_AWS_SECRET_ACCESS_KEY:?set a strong value in .env, not minioadmin}
    env_file:
      - path: .env
        required: false
    # Uncomment the line below to use if IAM_AUTH is true and you are using iam auth for postgres
    # volumes:
    #   - ./bundle.pem:/app/bundle.pem:ro
    extra_hosts:
      - "host.docker.internal:host-gateway"
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "6"
    volumes:
      - api_server_logs:/var/log/onyx
      # Shared volume for persistent document storage (Craft file-system mode)
      - file-system:/app/file-system

  background:
    image: onyxdotapp/onyx-backend:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile
    command: >
      /bin/sh -c "
      if [ -f /etc/ssl/certs/custom-ca.crt ]; then
        update-ca-certificates;
      fi &&
      /app/scripts/supervisord_entrypoint.sh"
    depends_on:
      - relational_db
      - opensearch
      - cache
      - inference_model_server
      - indexing_model_server
    restart: unless-stopped
    environment:
      - AUTH_TYPE=${AUTH_TYPE:-oidc}
      - POSTGRES_HOST=relational_db
      - OPENSEARCH_HOST=${OPENSEARCH_HOST:-opensearch}
      - OPENSEARCH_ADMIN_PASSWORD=${OPENSEARCH_ADMIN_PASSWORD:-StrongPassword123!}
      - REDIS_HOST=cache
      - MODEL_SERVER_HOST=${MODEL_SERVER_HOST:-inference_model_server}
      - INDEXING_MODEL_SERVER_HOST=${INDEXING_MODEL_SERVER_HOST:-indexing_model_server}
      - USE_IAM_AUTH=${USE_IAM_AUTH}
      - AWS_REGION_NAME=${AWS_REGION_NAME-}
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID-}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY-}
      # MinIO configuration
      - S3_ENDPOINT_URL=${S3_ENDPOINT_URL:-http://minio:9000}
      - S3_AWS_ACCESS_KEY_ID=${S3_AWS_ACCESS_KEY_ID:?set a strong value in .env, not minioadmin}
      - S3_AWS_SECRET_ACCESS_KEY=${S3_AWS_SECRET_ACCESS_KEY:?set a strong value in .env, not minioadmin}
      - DISCORD_BOT_TOKEN=${DISCORD_BOT_TOKEN:-}
      - DISCORD_BOT_INVOKE_CHAR=${DISCORD_BOT_INVOKE_CHAR:-!}
      # API Server connection for Discord bot message processing
      - API_SERVER_PROTOCOL=${API_SERVER_PROTOCOL:-http}
      - API_SERVER_HOST=${API_SERVER_HOST:-api_server}
    env_file:
      - path: .env
        required: false
    # Uncomment the line below to use if IAM_AUTH is true and you are using iam auth for postgres
    # volumes:
    #   - ./bundle.pem:/app/bundle.pem:ro
    extra_hosts:
      - "host.docker.internal:host-gateway"
    volumes:
      - background_logs:/var/log/onyx
      # Shared volume for persistent document storage (Craft file-system mode)
      - file-system:/app/file-system
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "6"
    # Uncomment the following lines if you need to include a custom CA certificate
    # This section enables the use of a custom CA certificate
    # If present, the custom CA certificate is mounted as a volume
    # The container checks for its existence and updates the system's CA certificates
    # This allows for secure communication with services using custom SSL certificates
    # volumes:
    #   # Maps to the CA_CERT_PATH environment variable in the Dockerfile
    #   - ${CA_CERT_PATH:-./custom-ca.crt}:/etc/ssl/certs/custom-ca.crt:ro

  web_server:
    image: onyxdotapp/onyx-web-server:${IMAGE_TAG:-latest}
    build:
      context: ../../web
      dockerfile: Dockerfile
      args:
        - NEXT_PUBLIC_DISABLE_LOGOUT=${NEXT_PUBLIC_DISABLE_LOGOUT:-}
        - NEXT_PUBLIC_THEME=${NEXT_PUBLIC_THEME:-}
        - NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED=${NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED:-}
    depends_on:
      - api_server
    restart: unless-stopped
    environment:
      - INTERNAL_URL=http://api_server:8080
    env_file:
      - path: .env
        required: false
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "6"

  # Uncomment the block below to enable the MCP server for Onyx.
  # mcp_server:
  #   image: onyxdotapp/onyx-backend:${IMAGE_TAG:-latest}
  #   build:
  #     context: ../../backend
  #     dockerfile: Dockerfile
  #   command: >
  #     /bin/sh -c "if [ \"${MCP_SERVER_ENABLED:-}\" != \"True\" ] && [ \"${MCP_SERVER_ENABLED:-}\" != \"true\" ]; then
  #       echo 'MCP server is disabled (MCP_SERVER_ENABLED=false), skipping...';
  #       exit 0;
  #     else
  #       exec python -m onyx.mcp_server_main;
  #     fi"
  #   env_file:
  #     - path: .env
  #       required: false
  #   depends_on:
  #     - relational_db
  #     - cache
  #   restart: "no"
  #   environment:
  #     - POSTGRES_HOST=relational_db
  #     - REDIS_HOST=cache
  #     # MCP Server Configuration
  #     - MCP_SERVER_ENABLED=${MCP_SERVER_ENABLED:-false}
  #     - MCP_SERVER_PORT=${MCP_SERVER_PORT:-8090}
  #     - MCP_SERVER_CORS_ORIGINS=${MCP_SERVER_CORS_ORIGINS:-}
  #     - API_SERVER_PROTOCOL=${API_SERVER_PROTOCOL:-http}
  #     - API_SERVER_HOST=${API_SERVER_HOST:-api_server}
  #   extra_hosts:
  #     - "host.docker.internal:host-gateway"
  #   logging:
  #     driver: json-file
  #     options:
  #       max-size: "50m"
  #       max-file: "6"
  #   volumes:
  #     - mcp_server_logs:/var/log/onyx

  relational_db:
    image: postgres:15.2-alpine
    shm_size: 1g
    command: -c 'max_connections=250'
    restart: unless-stopped
    # POSTGRES_USER and POSTGRES_PASSWORD should be set in .env file
    env_file:
      - path: .env
        required: false
    volumes:
      - db_volume:/var/lib/postgresql/data
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "6"

  inference_model_server:
    image: onyxdotapp/onyx-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
    restart: unless-stopped
    environment:
      - MIN_THREADS_ML_MODELS=${MIN_THREADS_ML_MODELS:-}
      # Set to debug to get more fine-grained logs
      - LOG_LEVEL=${LOG_LEVEL:-info}
    volumes:
      # Not necessary, this is just to reduce download time during startup
      - model_cache_huggingface:/app/.cache/huggingface/
      # optional, only for debugging purposes
      - inference_model_server_logs:/var/log/onyx
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "6"

  indexing_model_server:
    image: onyxdotapp/onyx-model-server:${IMAGE_TAG:-latest}
    build:
      context: ../../backend
      dockerfile: Dockerfile.model_server
    restart: unless-stopped
    environment:
      - MIN_THREADS_ML_MODELS=${MIN_THREADS_ML_MODELS:-}
      - INDEXING_ONLY=True
      # Set to debug to get more fine-grained logs
      - LOG_LEVEL=${LOG_LEVEL:-info}
      - VESPA_SEARCHER_THREADS=${VESPA_SEARCHER_THREADS:-1}
    volumes:
      # Not necessary, this is just to reduce download time during startup
      - indexing_huggingface_model_cache:/app/.cache/huggingface/
      # optional, only for debugging purposes
      - indexing_model_server_logs:/var/log/onyx
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "6"

  opensearch:
    image: opensearchproject/opensearch:3.6.0
    restart: unless-stopped
    # OpenSearch is the search backend and is enabled by default. To run against
    # an external OpenSearch instance, set OPENSEARCH_HOST in your env and
    # remove this service from the compose file (or skip it via the service list
    # when running `docker compose up`).
    environment:
      # We need discovery.type=single-node so that OpenSearch doesn't try
      # forming a cluster and waiting for other nodes to become live.
      - discovery.type=single-node
      - OPENSEARCH_INITIAL_ADMIN_PASSWORD=${OPENSEARCH_ADMIN_PASSWORD:-StrongPassword123!}
      # This and the JVM config below come from the example in https://docs.opensearch.org/latest/install-and-configure/install-opensearch/docker/
      # We do this to avoid unstable performance from page swaps.
      - bootstrap.memory_lock=true # Disable JVM heap memory swapping.
      # Java heap should be ~50% of memory limit. For now we assume a limit of
      # 4g although in practice the container can request more than this.
      # See https://opster.com/guides/opensearch/opensearch-basics/opensearch-heap-size-usage-and-jvm-garbage-collection/
      # Xms is the starting size, Xmx is the maximum size. These should be the
      # same.
      - "OPENSEARCH_JAVA_OPTS=-Xms2g -Xmx2g"
    volumes:
      - opensearch-data:/usr/share/opensearch/data
    # These come from the example in https://docs.opensearch.org/latest/install-and-configure/install-opensearch/docker/
    ulimits:
      # Similarly to bootstrap.memory_lock, we don't want to impose limits on
      # how much memory a process can lock from being swapped.
      memlock:
        soft: -1 # Set memlock to unlimited (no soft or hard limit).
        hard: -1
      nofile:
        soft: 65536 # Maximum number of open files for the opensearch user - set to at least 65536.
        hard: 65536
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "6"

  nginx:
    image: nginx:1.25.5-alpine
    restart: unless-stopped
    # nginx will immediately crash with `nginx: [emerg] host not found in upstream`
    # if api_server / web_server are not up
    depends_on:
      - api_server
      - web_server
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ../data/nginx:/nginx-templates:ro
      - ../data/certbot/conf:/etc/letsencrypt
      - ../data/certbot/www:/var/www/certbot
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "6"
    command: >
      /bin/sh -c "rm -f /etc/nginx/conf.d/default.conf
      && cp -a /nginx-templates/. /etc/nginx/conf.d/
      && sed 's/\r$//' /etc/nginx/conf.d/run-nginx.sh > /tmp/run-nginx.sh
      && chmod +x /tmp/run-nginx.sh
      && /tmp/run-nginx.sh app.conf.template.prod"
    env_file:
      - .env.nginx
    environment:
      # Nginx proxy timeout settings (in seconds)
      - NGINX_PROXY_CONNECT_TIMEOUT=${NGINX_PROXY_CONNECT_TIMEOUT:-300}
      - NGINX_PROXY_SEND_TIMEOUT=${NGINX_PROXY_SEND_TIMEOUT:-300}
      - NGINX_PROXY_READ_TIMEOUT=${NGINX_PROXY_READ_TIMEOUT:-300}
    healthcheck:
      test:
        [
          "CMD",
          "wget",
          "--quiet",
          "--tries=1",
          "--spider",
          "http://127.0.0.1/nginx-health",
        ]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s

  # follows https://pentacent.medium.com/nginx-and-lets-encrypt-with-docker-in-less-than-5-minutes-b4b8a60d3a71
  certbot:
    image: certbot/certbot
    restart: unless-stopped
    volumes:
      - ../data/certbot/conf:/etc/letsencrypt
      - ../data/certbot/www:/var/www/certbot
    logging:
      driver: json-file
      options:
        max-size: "50m"
        max-file: "6"
    entrypoint: "/bin/sh -c 'trap exit TERM; while :; do certbot renew; sleep 12h & wait $${!}; done;'"

  minio:
    image: minio/minio:RELEASE.2025-07-23T15-54-02Z-cpuv1
    restart: unless-stopped
    environment:
      MINIO_ROOT_USER: ${MINIO_ROOT_USER:?set a strong value in .env, not minioadmin}
      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:?set a strong value in .env, not minioadmin}
      MINIO_DEFAULT_BUCKETS: ${S3_FILE_STORE_BUCKET_NAME:-onyx-file-store-bucket}
    volumes:
      - minio_data:/data
    command: server /data --console-address ":9001"
    healthcheck:
      test: ["CMD", "mc", "ready", "local"]
      interval: 30s
      timeout: 20s
      retries: 3

  cache:
    image: redis:7.4-alpine
    restart: unless-stopped
    # docker silently mounts /data even without an explicit volume mount, which enables
    # persistence. explicitly setting save and appendonly forces ephemeral behavior.
    command: redis-server --save "" --appendonly no
    # Use tmpfs to prevent creation of anonymous volumes for /data
    tmpfs:
      - /data

  code-interpreter:
    image: onyxdotapp/code-interpreter:${CODE_INTERPRETER_IMAGE_TAG:-latest}
    command: ["bash", "./entrypoint.sh", "code-interpreter-api"]
    restart: unless-stopped
    env_file:
      - path: .env
        required: false

    # Below is needed for the `docker-out-of-docker` execution mode
    user: root
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock

    # uncomment below + comment out the above to use the `docker-in-docker` execution mode
    # privileged: true

volumes:
  db_volume:
  minio_data:
  model_cache_huggingface:
  indexing_huggingface_model_cache:
  # for logs that we don't want to lose on container restarts
  api_server_logs:
  background_logs:
  inference_model_server_logs:
  indexing_model_server_logs:
  # mcp_server_logs:
  # Shared volume for persistent document storage (Craft file-system mode)
  file-system:
  # Persistent data for OpenSearch.
  opensearch-data: