Dockerfile

FROM python:3.10-slim

WORKDIR /app

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

# Copy requirements first for better caching
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy the rest of the application
COPY . .

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1

# Expose the port Streamlit runs on
EXPOSE 8501

# Command to run the application
CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]