# Use official lightweight Python image
FROM python:3.9-slim

# Install system dependencies
# tesseract-ocr: for pytesseract
# poppler-utils: for pdf2image
# libtesseract-dev: development headers
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    poppler-utils \
    libtesseract-dev \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Copy requirements first to leverage Docker cache
COPY requirements.txt .

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

# Copy the rest of the application code
COPY . .

# Expose port (default for Uvicorn)
EXPOSE 8000

# Run the application
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]