FROM python:3.9-slim

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

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

# Copy the application code
COPY . .

# Set the Tesseract executable path explicitly
ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata

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