FROM python:3.12-slim

# System dependencies for parsers and OCR
RUN apt-get update && apt-get install -y --no-install-recommends \
    libmagic1 \
    tesseract-ocr \
    tesseract-ocr-eng \
    tesseract-ocr-chi-sim \
    tesseract-ocr-chi-tra \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Install Python dependencies first (cache layer)
COPY pyproject.toml .
RUN pip install --no-cache-dir .

# Copy application code
COPY . .

# Create data directory
RUN mkdir -p /data

ENV FILEDB_FILE_STORAGE_PATH=/data

EXPOSE 8000

CMD ["uvicorn", "opendb_core.main:app", "--host", "0.0.0.0", "--port", "8000"]
