ocr-api / Dockerfile
Soumik Bose
go
8d66792
# Use official Python runtime as a parent image
FROM python:3.11-slim
WORKDIR /app
# Install system dependencies
RUN apt-get update && apt-get install -y \
curl \
tesseract-ocr \
tesseract-ocr-eng \
tesseract-ocr-deu \
tesseract-ocr-fra \
tesseract-ocr-spa \
tesseract-ocr-por \
tesseract-ocr-ita \
tesseract-ocr-rus \
tesseract-ocr-chi-sim \
tesseract-ocr-jpn \
tesseract-ocr-kor \
poppler-utils \
libgl1 \
libglib2.0-0 \
&& rm -rf /var/lib/apt/lists/*
# Fix: Ensure logs appear immediately in the console
ENV PYTHONUNBUFFERED=1
ENV PYTHONIOENCODING=UTF-8
ENV HF_HOME=/tmp/cache
ENV PORT=7860
COPY requirements.txt .
RUN pip install --upgrade pip setuptools wheel \
&& pip install --default-timeout=100 --retries=10 --no-cache-dir -r requirements.txt
COPY . .
RUN useradd -m appuser && chown -R appuser /app
USER appuser
RUN mkdir -p ${HF_HOME} && chmod 777 ${HF_HOME}
EXPOSE $PORT
CMD bash -c "\
(while true; do curl -s https://xce009-ocr-api.hf.space >/dev/null; sleep 300; done) & \
uvicorn main:app --host 0.0.0.0 --port ${PORT} --workers 4"