SurfSense/Dockerfile.allinone

# SurfSense All-in-One Docker Image
# This image bundles PostgreSQL+pgvector, Redis, Backend, and Frontend
# Usage: docker run -d -p 3000:3000 -v surfsense-data:/data --name surfsense ghcr.io/modsetter/surfsense:latest

FROM ubuntu:22.04 AS base

# Prevent interactive prompts during package installation
ENV DEBIAN_FRONTEND=noninteractive

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    # PostgreSQL dependencies
    postgresql-14 \
    postgresql-contrib-14 \
    # Build tools for pgvector
    build-essential \
    postgresql-server-dev-14 \
    git \
    # Redis
    redis-server \
    # Python
    python3.11 \
    python3.11-venv \
    python3.11-dev \
    python3-pip \
    # Node.js
    curl \
    ca-certificates \
    gnupg \
    # Supervisor for process management
    supervisor \
    # Additional dependencies for backend
    gcc \
    wget \
    unzip \
    espeak-ng \
    libsndfile1 \
    libgl1 \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender1 \
    dos2unix \
    && rm -rf /var/lib/apt/lists/*

# Install Node.js 20.x
RUN curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
    && apt-get install -y nodejs \
    && npm install -g pnpm \
    && rm -rf /var/lib/apt/lists/*

# Build and install pgvector
RUN cd /tmp \
    && git clone --branch v0.7.4 https://github.com/pgvector/pgvector.git \
    && cd pgvector \
    && make \
    && make install \
    && rm -rf /tmp/pgvector

# Set Python 3.11 as default
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.11 1 \
    && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1

# Update certificates and install SSL tools
RUN update-ca-certificates

# Create data directories
RUN mkdir -p /data/postgres /data/redis /data/surfsense \
    && chown -R postgres:postgres /data/postgres

# ====================
# Build Frontend
# ====================
WORKDIR /app/frontend

# Copy frontend source
COPY surfsense_web/package.json surfsense_web/pnpm-lock.yaml* ./
COPY surfsense_web/source.config.ts ./
COPY surfsense_web/content ./content

# Install frontend dependencies
RUN pnpm install --frozen-lockfile

# Copy rest of frontend
COPY surfsense_web/ ./

# Build frontend with default values (can be overridden at runtime via reverse proxy)
ARG NEXT_PUBLIC_FASTAPI_BACKEND_URL=http://localhost:8000
ARG NEXT_PUBLIC_FASTAPI_BACKEND_AUTH_TYPE=LOCAL
ARG NEXT_PUBLIC_ETL_SERVICE=DOCLING

ENV NEXT_PUBLIC_FASTAPI_BACKEND_URL=$NEXT_PUBLIC_FASTAPI_BACKEND_URL
ENV NEXT_PUBLIC_FASTAPI_BACKEND_AUTH_TYPE=$NEXT_PUBLIC_FASTAPI_BACKEND_AUTH_TYPE
ENV NEXT_PUBLIC_ETL_SERVICE=$NEXT_PUBLIC_ETL_SERVICE

RUN pnpm run build

# ====================
# Setup Backend
# ====================
WORKDIR /app/backend

# Copy backend source
COPY surfsense_backend/pyproject.toml surfsense_backend/uv.lock ./

# Install PyTorch based on architecture
RUN if [ "$(uname -m)" = "x86_64" ]; then \
        pip install --no-cache-dir torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu; \
    else \
        pip install --no-cache-dir torch torchvision torchaudio; \
    fi

# Install python dependencies
RUN pip install --no-cache-dir certifi pip-system-certs uv \
    && uv pip install --system --no-cache-dir -e .

# Set SSL environment variables
RUN CERTIFI_PATH=$(python -c "import certifi; print(certifi.where())") \
    && echo "export SSL_CERT_FILE=$CERTIFI_PATH" >> /etc/profile.d/ssl.sh \
    && echo "export REQUESTS_CA_BUNDLE=$CERTIFI_PATH" >> /etc/profile.d/ssl.sh

# Pre-download EasyOCR models
RUN mkdir -p /root/.EasyOCR/model \
    && wget --no-check-certificate https://github.com/JaidedAI/EasyOCR/releases/download/v1.3/english_g2.zip -O /root/.EasyOCR/model/english_g2.zip || true \
    && wget --no-check-certificate https://github.com/JaidedAI/EasyOCR/releases/download/pre-v1.1.6/craft_mlt_25k.zip -O /root/.EasyOCR/model/craft_mlt_25k.zip || true \
    && cd /root/.EasyOCR/model && (unzip -o english_g2.zip || true) && (unzip -o craft_mlt_25k.zip || true)

# Pre-download Docling models
RUN python -c "try:\n    from docling.document_converter import DocumentConverter\n    conv = DocumentConverter()\nexcept:\n    pass" || true

# Install Playwright browsers
RUN pip install playwright && playwright install chromium

# Copy backend source
COPY surfsense_backend/ ./

# ====================
# Configuration
# ====================
WORKDIR /app

# Copy supervisor configuration
COPY scripts/docker/supervisor-allinone.conf /etc/supervisor/conf.d/surfsense.conf

# Copy entrypoint script
COPY scripts/docker/entrypoint-allinone.sh /app/entrypoint.sh
RUN chmod +x /app/entrypoint.sh

# PostgreSQL initialization script
COPY scripts/docker/init-postgres.sh /app/init-postgres.sh
RUN chmod +x /app/init-postgres.sh

# Environment variables with defaults
ENV POSTGRES_USER=surfsense
ENV POSTGRES_PASSWORD=surfsense
ENV POSTGRES_DB=surfsense
ENV DATABASE_URL=postgresql+asyncpg://surfsense:surfsense@localhost:5432/surfsense
ENV CELERY_BROKER_URL=redis://localhost:6379/0
ENV CELERY_RESULT_BACKEND=redis://localhost:6379/0
ENV PYTHONPATH=/app/backend
ENV NEXT_FRONTEND_URL=http://localhost:3000
ENV AUTH_TYPE=LOCAL
ENV ETL_SERVICE=DOCLING
ENV EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2

# Data volume
VOLUME ["/data"]

# Expose ports
# 3000 - Frontend
# 8000 - Backend API  
EXPOSE 3000 8000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD curl -f http://localhost:3000 && curl -f http://localhost:8000/docs || exit 1

# Run entrypoint
CMD ["/app/entrypoint.sh"]