# Use NVIDIA CUDA base image with Python 3.10 (CUDA 12.8 for RTX 5080)
FROM nvidia/cuda:12.8.0-cudnn-runtime-ubuntu22.04

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    CUDA_VISIBLE_DEVICES=0

# Install Python 3.10 and system dependencies
RUN apt-get update && apt-get install -y \
    python3.10 \
    python3.10-dev \
    python3-pip \
    git \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgomp1 \
    libgl1-mesa-glx \
    wget \
    && rm -rf /var/lib/apt/lists/*

# Set Python 3.10 as default
RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1 && \
    update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1

# Upgrade pip
RUN python3 -m pip install --upgrade pip setuptools wheel

# Set working directory
WORKDIR /app

# Copy project files
COPY . /app/

# Install PyTorch with CUDA support first (cu124 is compatible with CUDA 12.8)
RUN pip install torch==2.6.0 torchvision==0.21.0 --index-url https://download.pytorch.org/whl/cu124

# Install the package and dependencies
RUN pip install -e .

# Install additional dependencies for server
RUN pip install requests

# Expose port for Ray Serve
EXPOSE 8001

# Create cache directory for models
RUN mkdir -p /root/.cache/huggingface/hub

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD python3 -c "import requests; requests.get('http://localhost:8001/', timeout=5)" || exit 1

# Default command to start the server (port 8001)
CMD ["texteller", "launch", "server", "-p", "8001"]