Dockerfile

FROM python:3.9-slim

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    poppler-utils \
    libgl1-mesa-glx \
    libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

# Create data directory
RUN mkdir -p /app/data && \
    chmod -R 777 /app/data

# Copy requirements and install dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application files
COPY . .

# Streamlit configuration
ENV STREAMLIT_SERVER_PORT=7860
ENV STREAMLIT_SERVER_ADDRESS=0.0.0.0

# Set up entry point
ENTRYPOINT ["streamlit", "run"]
CMD ["app.py"]