pdf-ocr / Dockerfile
Ratnesh-dev's picture
Use all available CPUs for OCR
4f1b16a
Raw
History Blame Contribute Delete
707 Bytes
FROM python:3.12-slim
ENV PYTHONDONTWRITEBYTECODE=1 \
PYTHONUNBUFFERED=1 \
OMP_THREAD_LIMIT=1 \
OCR_DPI=220 \
OCR_PSM=6 \
OCR_LANG=eng \
MAX_UPLOAD_MB=300 \
HOME=/home/user
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
curl \
libglib2.0-0 \
libgomp1 \
tesseract-ocr \
tesseract-ocr-eng \
&& rm -rf /var/lib/apt/lists/* \
&& useradd -m -u 1000 user
WORKDIR /home/user/app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY --chown=user:user app.py .
USER user
EXPOSE 7860
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--timeout-keep-alive", "75"]