Dockerfile

FROM python:3.12-slim AS runtime

WORKDIR /app

RUN apt-get update && apt-get install -y --no-install-recommends \
        libgl1 \
        libglib2.0-0 \
        libsm6 \
        libxext6 \
        libxrender1 \
        libgomp1 \
        poppler-utils \
    && rm -rf /var/lib/apt/lists/*

COPY requirements-prod.txt .
RUN pip install --no-cache-dir --index-url https://download.pytorch.org/whl/cpu torch torchvision \
    && pip install --no-cache-dir -r requirements-prod.txt

RUN useradd -m -u 1000 -s /bin/bash appuser

COPY --chown=appuser:appuser src/ ./src/
COPY --chown=appuser:appuser .streamlit/ ./.streamlit/

ENV HF_HOME=/data/huggingface \
    HUGGINGFACE_HUB_CACHE=/data/huggingface/hub \
    TRANSFORMERS_CACHE=/data/huggingface/hub \
    HF_XET_HIGH_PERFORMANCE=1 \
    LIGHTONOCR_MODEL_ID=PetaniHandal/LightOnOCR-2-1B-1025-ft-iam-handwriting-vllm \
    CUDA_VISIBLE_DEVICES="" \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    STREAMLIT_SERVER_PORT=7860 \
    STREAMLIT_SERVER_ADDRESS=0.0.0.0 \
    STREAMLIT_BROWSER_GATHER_USAGE_STATS=false

EXPOSE 7860

USER appuser

HEALTHCHECK --interval=30s --timeout=10s --start-period=180s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:7860/_stcore/health')" || exit 1

CMD ["python", "-m", "streamlit", "run", "src/app.py", \
     "--server.port=7860", \
     "--server.address=0.0.0.0", \
     "--server.headless=true", \
     "--server.enableXsrfProtection=false", \
     "--server.maxUploadSize=20"]