# DocProcesser Dockerfile
# Optimized for RTX 5080 GPU deployment

# Use NVIDIA CUDA base image with Python 3.11
FROM nvidia/cuda:12.8.0-runtime-ubuntu24.04

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.11 \
    python3.11-venv \
    python3.11-dev \
    python3-pip \
    libgl1-mesa-glx \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgomp1 \
    curl \
    && rm -rf /var/lib/apt/lists/* \
    && ln -sf /usr/bin/python3.11 /usr/bin/python \
    && ln -sf /usr/bin/python3.11 /usr/bin/python3

# Install uv for fast package management
RUN curl -LsSf https://astral.sh/uv/install.sh | sh
ENV PATH="/root/.local/bin:$PATH"

# Copy dependency files first for better caching
COPY pyproject.toml ./

# Create virtual environment and install dependencies
RUN uv venv /app/.venv
ENV PATH="/app/.venv/bin:$PATH"
ENV VIRTUAL_ENV="/app/.venv"

RUN uv pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -e .

# Copy application code
COPY app/ ./app/

# Create model directories (models should be mounted at runtime)
RUN mkdir -p /app/app/model/DocLayout /app/app/model/PP-DocLayout

# Expose port
EXPOSE 8053

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:8053/health || exit 1

# Run the application
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8053", "--workers", "1"]