Dockerfile

FROM python:3.11-slim

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1

WORKDIR /app

# System deps:
# - tesseract-ocr: OCR engine for pytesseract
# - poppler-utils: needed by pdf2image (pdftoppm/pdftocairo)
RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    tesseract-ocr-ind \
    tesseract-ocr-eng \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

COPY requirements.txt .
RUN pip install --upgrade pip && pip install -r requirements.txt

COPY . .

EXPOSE 7860

# Optional auth token for API requests:
# -e PYTHON_EXTRACTOR_TOKEN=your_token
CMD ["sh", "-c", "uvicorn api_server:app --host 0.0.0.0 --port ${PORT:-7860}"]