# Build image for DocVerse FastAPI Backend on Hugging Face Spaces
FROM python:3.10-slim

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1

# Install system dependencies (For EasyOCR & SciSpacy)
RUN apt-get update && apt-get install -y \
    build-essential \
    libpq-dev \
    gcc \
    tesseract-ocr \
    libtesseract-dev \
    && rm -rf /var/lib/apt/lists/*

# Hugging Face Spaces require running as a non-root user
RUN useradd -m -u 1000 user
USER user
ENV PATH="/home/user/.local/bin:$PATH"

# Set working directory
WORKDIR /app

# Install Python dependencies
COPY --chown=user requirements.txt /app/
RUN pip install --upgrade pip
RUN pip install --no-cache-dir -r requirements.txt

# Download SciSpacy models (Example: en_core_sci_sm for biomedical lit)
# RUN pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_sm-0.5.1.tar.gz

# Copy application code with correct ownership
COPY --chown=user ./app /app/app

# Expose Hugging Face's required port
EXPOSE 7860

# Start FastAPI application on port 7860
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]