# Build stage - install dependencies that require compilation
FROM python:3.11-slim as builder

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1

WORKDIR /app

# Install build dependencies only
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        build-essential \
        curl \
    && rm -rf /var/lib/apt/lists/*

# Copy and install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir --user -r requirements.txt && \
    pip cache purge

# Download SpaCy English model
RUN python -m spacy download en_core_web_sm

# Runtime stage - minimal image with only runtime dependencies
FROM python:3.11-slim

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PYTHONPATH=/app/src \
    PATH=/root/.local/bin:$PATH \
    MULTI_DOC_STORAGE_ROOT=/app/storage \
    MULTI_DOC_CLAUDE_MODEL=claude-3-5-haiku-latest \
    CLAUDE_MODEL=claude-3-5-haiku-latest \
    PORT=8024

WORKDIR /app

# Install only runtime dependencies (no build tools)
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        poppler-utils \
        tesseract-ocr \
        ffmpeg \
        libmagic1 \
        curl \
        # Required for some Python packages at runtime
        libgomp1 \
        libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/* \
    && apt-get clean

# Copy Python packages from builder stage (includes spacy model)
COPY --from=builder /root/.local /root/.local

# Copy application code
COPY src ./src

EXPOSE 8024

CMD ["sh", "-c", "uvicorn multi_document_upload_service.main:app --host 0.0.0.0 --port ${PORT:-8024}"]