# Use official Python 3.12 image with slim variant
FROM python:3.12-slim as builder

# 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/*

# Create model cache directory
RUN mkdir -p /tmp/huggingface && chmod -R 777 /tmp/huggingface

# Set environment variables for Hugging Face cache
ENV TRANSFORMERS_CACHE=/tmp/huggingface
ENV HF_HOME=/tmp/huggingface

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

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

# Install spaCy model
RUN python -m spacy download en_core_web_sm

# Pre-download models and tokenizers (both deberta and distilbert)
RUN python -c "\
from transformers import AutoTokenizer, AutoModel; \
print('Downloading deepset/deberta-v3-base-squad2...'); \
AutoTokenizer.from_pretrained('deepset/deberta-v3-base-squad2'); \
AutoModel.from_pretrained('deepset/deberta-v3-base-squad2'); \
print('Downloading distilbert-base-uncased...'); \
AutoTokenizer.from_pretrained('distilbert-base-uncased'); \
AutoModel.from_pretrained('distilbert-base-uncased')"

# --- Runtime stage ---
FROM python:3.12-slim

WORKDIR /app

# Copy only necessary files from builder
COPY --from=builder /tmp/huggingface /tmp/huggingface
COPY --from=builder /usr/local/lib/python3.12/site-packages /usr/local/lib/python3.12/site-packages
COPY --from=builder /usr/local/bin /usr/local/bin

# Create required directories
RUN mkdir -p /tmp/uploads && chmod -R 777 /tmp/uploads /tmp/huggingface

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV UPLOAD_FOLDER=/tmp/uploads
ENV TRANSFORMERS_CACHE=/tmp/huggingface
ENV HF_HOME=/tmp/huggingface

# Streamlit config
RUN mkdir -p .streamlit && \
    echo '[server]\n\
enableCORS=false\n\
enableXsrfProtection=false\n' > .streamlit/config.toml

# Copy application code
COPY . .

# Expose port
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:7860/_stcore/health || exit 1

# Run the application
CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]