Dockerfile

# Use the official Python 3.10 image as the base
FROM python:3.10-slim

# Install system dependencies, including Poppler and Tesseract
RUN apt-get update && apt-get install -y \
    git \
    git-lfs \
    ffmpeg \
    libsm6 \
    libxext6 \
    cmake \
    rsync \
    libgl1-mesa-glx \
    tesseract-ocr \
    poppler-utils \  # Poppler for pdf2image
    && rm -rf /var/lib/apt/lists/* \
    && git lfs install

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

# Copy application files to the container
COPY . /home/user/app

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

# Expose the port for Streamlit
EXPOSE 8501

# Command to run the Streamlit app
CMD ["streamlit", "run", "app.py"]