Dockerfile

# FROM python:3.9-slim

# RUN apt-get update && apt-get install -y \
#     libpng-dev \
#     libjpeg-dev \
#     zlib1g-dev \
#     tesseract-ocr \
#     libtesseract-dev \
#     && rm -rf /var/lib/apt/lists/*

# RUN useradd -m -u 1000 user
# USER user
# ENV PATH="/home/user/.local/bin:$PATH"

# WORKDIR /app

# COPY --chown=user:user requirements.txt requirements.txt
# RUN pip install --no-cache-dir --upgrade pip && \
#     pip install --no-cache-dir -r requirements.txt

# COPY --chown=user:user . /app

# EXPOSE 7860

# # Increase timeout and reduce workers
# CMD ["gunicorn", "--workers", "1", "--timeout", "600", "--bind", "0.0.0.0:7860", "app:app"]

# Use an official Python runtime as the base image
FROM python:3.8-slim

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    libtesseract-dev \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

# Copy application code
COPY . /app

# Install Python dependencies
RUN pip install --no-cache-dir \
    flask \
    flask-cors \
    pdfplumber \
    pillow \
    pytesseract \
    numpy \
    torch \
    transformers \
    datasets \
    scikit-learn \
    gunicorn

# Create uploads and cache directories with proper permissions
RUN mkdir -p /app/uploads /app/cache && \
    chmod -R 777 /app/uploads /app/cache

# Set environment variable for Hugging Face cache
ENV TRANSFORMERS_CACHE=/app/cache

# Expose port
EXPOSE 5000

# Run with Gunicorn
CMD ["gunicorn", "--bind", "0.0.0.0:5000", "app:app"]