Dockerfile

FROM python:3.10-slim

# Install Poppler, Tesseract, and other dependencies
RUN apt-get update && \
    apt-get install -y --no-install-recommends pkg-config poppler-utils
    tesseract-ocr \
    poppler-utils \
    libsm6 \
    libxext6 \
    libgl1-mesa-glx \
    && rm -rf /var/lib/apt/lists/*

# Add Poppler to PATH
ENV PATH="/usr/bin:$PATH"

# Set the working directory
WORKDIR /home/user/app

# Copy application files
COPY . /home/user/app

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Expose Streamlit port
EXPOSE 8501

# Run the application
CMD ["streamlit", "run", "app.py"]