Dockerfile

# FROM python:3.10

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

# # Create a user and set up the environment
# RUN useradd -m -u 1000 user
# USER user
# ENV PATH="/home/user/.local/bin:$PATH"

# # Set the working directory
# WORKDIR /app

# # Copy and install Python dependencies
# COPY --chown=user ./requirements.txt requirements.txt
# RUN pip install --no-cache-dir --upgrade -r requirements.txt

# # Copy the application code
# COPY --chown=user . /app

# # Run Gunicorn with timeout and workers
# CMD ["gunicorn", "--timeout", "120", "-w", "2", "-b", "0.0.0.0:7860", "app:app"]


FROM python:3.10

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

# Create a user and set up the environment
RUN useradd -m -u 1000 user
USER user
ENV PATH="/home/user/.local/bin:$PATH"

# Set the working directory
WORKDIR /app

# Copy and install Python dependencies
COPY --chown=user ./requirements.txt requirements.txt
RUN pip install --no-cache-dir --upgrade -r requirements.txt

# Copy the application code
COPY --chown=user . /app

# Run Gunicorn with timeout and workers
CMD ["gunicorn", "--timeout", "120", "-w", "2", "-b", "0.0.0.0:7860", "app:app"]