PdfQnAUsingPinecone / Dockerfile
SoumyaJ's picture
Update Dockerfile
67252b8 verified
# Start from Python 3.9 image
FROM python:3.9
# Switch to root to install system dependencies
USER root
# Set non-interactive mode
ENV DEBIAN_FRONTEND=noninteractive
# Fix permission issues by using --allow-releaseinfo-change
RUN apt-get update --allow-releaseinfo-change && \
apt-get install -y --no-install-recommends \
tesseract-ocr \
libtesseract-dev \
poppler-utils \
wget && \
rm -rf /var/lib/apt/lists/* # Clean up
# Ensure the tessdata directory exists
RUN mkdir -p /usr/share/tesseract-ocr/4.00/tessdata
# Download English trained data manually
RUN wget -O /usr/share/tesseract-ocr/4.00/tessdata/eng.traineddata \
https://github.com/tesseract-ocr/tessdata_best/raw/main/eng.traineddata
# Add a non-root user
RUN useradd -m -u 1000 user
# Switch to the new user
USER user
ENV PATH="/home/user/.local/bin:$PATH"
# Set Tesseract OCR path
ENV TESSDATA_PREFIX="/usr/share/tesseract-ocr/4.00/tessdata"
# Set working directory
WORKDIR /app
# Copy requirements and install Python packages
COPY --chown=user ./requirements.txt requirements.txt
RUN pip install --no-cache-dir --upgrade -r requirements.txt
# Copy application files
COPY --chown=user . .
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]