Dockerfile

FROM python:3.9

# Set environment variable for Tesseract data directory
ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata/

# Install system dependencies
RUN apt-get update && apt-get install -y \
    libleptonica-dev \
    && rm -rf /var/lib/apt/lists/*

# Install Tesseract and its language data files
RUN apt-get update && apt-get install -y tesseract-ocr tesseract-ocr-chi-sim
RUN apt-get update && apt-get install -y tesseract-ocr tesseract-ocr-msa

# Set environment variable for Tesseract executable path
ENV PATH="${PATH}:/usr/bin/"

WORKDIR /code

COPY ./requirements.txt /code/requirements.txt

RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt

COPY . .

CMD ["gunicorn", "-b", "0.0.0.0:7860", "main:app"]