Dockerfile

FROM python:3.12-slim

WORKDIR /app

# Install system dependencies including those needed for OCR and ML models
RUN apt-get update && apt-get install -y \
    curl \
    poppler-utils \
    libgl1-mesa-glx \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgomp1 \
    && rm -rf /var/lib/apt/lists/*

# Install poetry
RUN pip install poetry

# Configure poetry
RUN poetry config virtualenvs.create false

# Copy dependency files
COPY pyproject.toml poetry.lock* /app/

# Install dependencies
RUN poetry install --only main --no-root

# Download spacy model
RUN python -m spacy download en_core_web_sm

# Create user
RUN useradd -m -u 1000 appuser

# Copy source code
COPY --chown=appuser src /app/src
COPY --chown=appuser main.py /app/

# Change ownership
RUN chown -R appuser /app

USER appuser

EXPOSE 8001

ENV PYTHONUNBUFFERED=1
ENV SPACY_MODEL_NAME=en_core_web_sm

CMD ["python", "main.py"]