FROM python:3.10-slim

# Install system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    poppler-utils \
    ffmpeg \
    && 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 application code
COPY . .

# Create necessary directories with proper permissions
RUN mkdir -p /data/uploads /tmp/huggingface /tmp/torch /tmp/whisper && \
    chmod -R 777 /data /tmp

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV HF_HOME=/tmp/huggingface
ENV TRANSFORMERS_CACHE=/tmp/huggingface
ENV XDG_CACHE_HOME=/tmp
ENV TORCH_HOME=/tmp/torch
ENV WHISPER_CACHE=/tmp/whisper
ENV PYTHONPATH=/app

# Expose port
EXPOSE 7860

# Run the application with gunicorn
CMD ["gunicorn", "--bind", "0.0.0.0:7860", "--workers", "1", "--threads", "8", "--timeout", "0", "ai_med_extract.app:app"]