Dockerfile

FROM python:3.10-slim
# Switch to root for system installations
USER root

# Install Tesseract and language data
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    && rm -rf /var/lib/apt/lists/*

# Find tessdata directory and set permissions
RUN tessdata_dir=$(find /usr -name "tessdata" -type d | grep "tesseract") && \
    echo "Found tessdata at: $tessdata_dir" && \
    mkdir -p /usr/share/tesseract-ocr/4.00/tessdata && \
    cp -r $tessdata_dir/* /usr/share/tesseract-ocr/4.00/tessdata/ && \
    chmod -R 755 /usr/share/tesseract-ocr && \
    chown -R root:root /usr/share/tesseract-ocr

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

# Verify tessdata files are present
RUN ls -la $TESSDATA_PREFIX

# Create user and set up environment
RUN useradd -m -u 1000 user && \
    chown -R user:user /usr/share/tesseract-ocr/4.00/tessdata


USER user

ENV HOME=/home/user \
	PATH=/home/user/.local/bin:$PATH

WORKDIR $HOME/app

COPY --chown=user ./ $HOME/app

RUN pip install -r requirements.txt

CMD fastapi run --reload --host=0.0.0.0 --port=7860