FROM python:3.11-slim

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    curl \
    git \
    && rm -rf /var/lib/apt/lists/*

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1 \
    TRANSFORMERS_CACHE=/app/.cache \
    HF_HOME=/app/.cache

# Copy requirements first (for caching)
COPY requirements.txt .

# Upgrade pip and install dependencies
RUN pip install --upgrade pip setuptools wheel && \
    pip install --no-cache-dir -r requirements.txt

# Copy project files
COPY step2_load_model.py step3_encode_dataset.py step5_api.py ./
COPY dataset ./dataset
COPY startup.sh ./

# Create necessary directories
RUN mkdir -p models artifacts .cache

# Make startup script executable
RUN chmod +x startup.sh

# Pre-download model and encode dataset (optional, comment out if build times out)
# RUN python step2_load_model.py && python step3_encode_dataset.py

# Expose port
EXPOSE 7860

# Health check with longer startup period
HEALTHCHECK --interval=30s --timeout=10s --start-period=300s --retries=3 \
    CMD curl -f http://localhost:7860/health || exit 1

# Run the API
CMD ["./startup.sh"]