DocsGPT/deployment/docker-compose-standalone.yaml

# DocsGPT from pre-built images, with no git checkout.
#
#   curl -fsSLO https://raw.githubusercontent.com/arc53/DocsGPT/main/deployment/docker-compose-standalone.yaml
#   printf 'LLM_PROVIDER=docsgpt\nVITE_API_STREAMING=true\nINTERNAL_KEY=%s\n' "$(openssl rand -hex 16)" > .env
#   docker compose -f docker-compose-standalone.yaml up -d
#
# INTERNAL_KEY is the shared secret the worker uses to hand finished indexes to
# the API; without it every ingest fails with a 401 (setup.sh generates one).
#   open http://localhost:5173
#
# Every release also attaches this file as an asset. Settings come from .env
# next to this file (any DocsGPT setting; the compose-internal service URLs
# below take precedence). Data lives in named volumes, so `docker compose
# down` keeps it and `docker compose down -v` removes it.
#
#   DOCSGPT_IMAGE_TAG      release to run, e.g. 0.20.0 (default: latest release);
#                          develop follows the main branch
#   DOCSGPT_IMAGE_VARIANT  empty (slim, default) or -docling: docling parser
#                          engine, its models, and tesseract baked in (OCR-ready)
#   EMBEDDINGS_NAME        defaults to granite here (this stack always starts on
#                          fresh volumes, so there is no older index to keep
#                          compatible); the code default stays mpnet for upgrades.
name: docsgpt

services:
  frontend:
    image: arc53/docsgpt-fe:${DOCSGPT_IMAGE_TAG:-latest}
    env_file:
      - path: .env
        required: false
    environment:
      # Every VITE_* the app reads. A bare name is passed through only when it is
      # set in the shell or the --env-file, so an unset one does not reach the
      # container as an empty string and override the image's own default.
      - VITE_API_HOST=${VITE_API_HOST:-http://localhost:7091}
      - VITE_API_STREAMING=${VITE_API_STREAMING:-true}
      - VITE_BASE_URL
      - VITE_GOOGLE_CLIENT_ID
      - VITE_GOOGLE_PICKER_API_KEY
      - VITE_SHARE_POINT_CLIENT_ID
      - VITE_CONFLUENCE_CLIENT_ID
      - VITE_NOTIFICATION_TEXT
      - VITE_NOTIFICATION_LINK
      - VITE_ENABLE_VOICE_INPUT
      - VITE_DISABLE_SOURCE_FE
      - VITE_USE_V
    ports:
      - "5173:5173"
    depends_on:
      - backend

  backend:
    image: arc53/docsgpt:${DOCSGPT_IMAGE_TAG:-latest}${DOCSGPT_IMAGE_VARIANT:-}
    # Same as docker-compose-hub.yaml: the data volumes are written by root so
    # any image tag works, including releases that predate the appuser-owned
    # /app/inputs, /app/indexes and /app/vectors directories.
    user: root
    env_file:
      - path: .env
        required: false
    environment:
      - CELERY_BROKER_URL=redis://redis:6379/0
      - CELERY_RESULT_BACKEND=redis://redis:6379/1
      - CACHE_REDIS_URL=redis://redis:6379/2
      - POSTGRES_URI=postgresql://docsgpt:docsgpt@postgres:5432/docsgpt
      - EMBEDDINGS_NAME=${EMBEDDINGS_NAME:-ibm-granite/granite-embedding-311m-multilingual-r2}
    ports:
      - "7091:7091"
    volumes:
      - indexes:/app/indexes
      - inputs:/app/inputs
      - vectors:/app/vectors
    depends_on:
      redis:
        condition: service_started
      postgres:
        condition: service_healthy
    restart: unless-stopped

  worker:
    image: arc53/docsgpt:${DOCSGPT_IMAGE_TAG:-latest}${DOCSGPT_IMAGE_VARIANT:-}
    user: root
    # Consumes the default queue plus `parsing` (read_document) and `embeddings`
    # (query embedding); without the latter every search times out.
    command: celery -A docsgpt.app.celery worker -l INFO -B -Q docsgpt,parsing,embeddings
    env_file:
      - path: .env
        required: false
    environment:
      - CELERY_BROKER_URL=redis://redis:6379/0
      - CELERY_RESULT_BACKEND=redis://redis:6379/1
      - CACHE_REDIS_URL=redis://redis:6379/2
      - POSTGRES_URI=postgresql://docsgpt:docsgpt@postgres:5432/docsgpt
      - API_URL=http://backend:7091
      - EMBEDDINGS_NAME=${EMBEDDINGS_NAME:-ibm-granite/granite-embedding-311m-multilingual-r2}
    volumes:
      - indexes:/app/indexes
      - inputs:/app/inputs
      - vectors:/app/vectors
    depends_on:
      redis:
        condition: service_started
      postgres:
        condition: service_healthy
    restart: unless-stopped

  redis:
    image: redis:6-alpine
    restart: unless-stopped

  postgres:
    image: postgres:16-alpine
    environment:
      - POSTGRES_USER=docsgpt
      - POSTGRES_PASSWORD=docsgpt
      - POSTGRES_DB=docsgpt
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U docsgpt -d docsgpt"]
      interval: 5s
      timeout: 5s
      retries: 10
    restart: unless-stopped

volumes:
  indexes:
  inputs:
  vectors:
  postgres_data: