Dockerfile

FROM ubuntu:22.04
ENV DEBIAN_FRONTEND=noninteractive

# Install core system dependencies + Node.js LTS (>=16)
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
      curl ca-certificates gnupg build-essential git python3 \
      python3-pip python3-dev imagemagick fonts-liberation libpq-dev \
      default-libmysqlclient-dev pkg-config libmagic-dev libzbar0 poppler-utils \
      unpaper ghostscript icc-profiles-free qpdf liblept5 libxml2 pngquant \
      zlib1g tesseract-ocr tesseract-ocr-eng redis-server postgresql \
      postgresql-client supervisor nano && \
    rm -rf /var/lib/apt/lists/* && \
    curl -fsSL https://deb.nodesource.com/setup_18.x | bash - && \
    apt-get update && apt-get install -y nodejs && \
    npm install -g pnpm

# Verify Node and pnpm versions
RUN node --version && pnpm --version

# Install uv package installer
RUN curl -sSf https://astral.sh/uv/install.sh | bash

# Create the system user and prepare working directory
RUN adduser --system --home /opt/paperless --group paperless
WORKDIR /opt/paperless
RUN git config --global --add safe.directory /opt/paperless

# Clone repository & checkout specific version
RUN git clone https://github.com/paperless-ngx/paperless-ngx.git . && \
    git checkout v2.17.1

# Build frontend using pnpm—no production flag
RUN cd src-ui && pnpm install && pnpm exec ng build

# Install Python backend dependencies
RUN /root/.cargo/bin/uv pip install -r requirements.txt

# Initialize PostgreSQL
RUN service postgresql start && \
    su - postgres -c "psql -c \"CREATE USER paperless WITH PASSWORD 'your_db_password';\"" && \
    su - postgres -c "psql -c \"CREATE DATABASE paperless OWNER paperless;\"" && \
    service postgresql stop

# Create and take care of directories
RUN mkdir -p media data consume export && \
    chown -R paperless:paperless media data consume export

# Environment variables for Paperless‑ngx
ENV PAPERLESS_REDIS="redis://localhost:6379/0" \
    PAPERLESS_DBENGINE="postgresql" \
    PAPERLESS_DBHOST="localhost" \
    PAPERLESS_DBNAME="paperless" \
    PAPERLESS_DBUSER="paperless" \
    PAPERLESS_DBPASS="your_db_password" \
    PAPERLESS_SECRET_KEY="a_very_long_random_string" \
    PAPERLESS_CONSUMPTION_DIR="/opt/paperless/consume" \
    PAPERLESS_DATA_DIR="/opt/paperless/data" \
    PAPERLESS_MEDIA_ROOT="/opt/paperless/media" \
    PAPERLESS_PORT="7860" \
    PAPERLESS_BIND_ADDR="0.0.0.0" \
    PAPERLESS_WEBSERVER_WORKERS=1 \
    PAPERLESS_OCR_PAGES=1 \
    PAPERLESS_ENABLE_NLTK=false \
    PAPERLESS_OCR_CLEAN="none"

# Supervisord config to orchestrate services
RUN printf "[supervisord]\nnodaemon=true\n\n\
[program:postgresql]\ncommand=/usr/lib/postgresql/*/bin/postgres -D /var/lib/postgresql/*/main\nuser=postgres\n\n\
[program:redis]\ncommand=/usr/bin/redis-server\n\n\
[program:paperless-webserver]\ncommand=/opt/paperless/src/manage.py runserver 0.0.0.0:7860\nuser=paperless\n\n\
[program:paperless-consumer]\ncommand=/opt/paperless/src/manage.py document_consumer\nuser=paperless\n\n\
[program:paperless-scheduler]\ncommand=/opt/paperless/src/manage.py qcluster\nuser=paperless\n" > /etc/supervisor/conf.d/supervisord.conf

ENV PATH="/root/.cargo/bin:${PATH}"

# Startup script: launches DB, Redis, migrations, then supervisord
RUN printf "#!/bin/bash\n\
service postgresql start\n\
service redis-server start\n\
cd /opt/paperless\n\
python3 src/manage.py migrate\n\
python3 src/manage.py createsuperuser --noinput --username admin --email admin@example.com || true\n\
exec /usr/bin/supervisord -n -c /etc/supervisor/conf.d/supervisord.conf\n" > /startup.sh && chmod +x /startup.sh

EXPOSE 7860
CMD ["/startup.sh"]