FROM nvidia/cuda:12.1.0-devel-ubuntu22.04

WORKDIR /app

# Install Python and system dependencies
RUN apt-get update && apt-get install -y \
    python3.11 \
    python3.11-dev \
    python3-pip \
    build-essential \
    cmake \
    git \
    && rm -rf /var/lib/apt/lists/*

# Set Python 3.11 as default
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.11 1 && \
    update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1

# Upgrade pip
RUN python -m pip install --upgrade pip

# Copy requirements and install
COPY requirements.txt .

# Install llama-cpp-python with CUDA support
RUN CMAKE_ARGS="-DLLAMA_CUDA=on" pip install llama-cpp-python --no-cache-dir

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

# Copy application code
COPY . .

# Create data directory for persistence
RUN mkdir -p /data

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV MODEL_REPO=daskalos-apps/phi4-cybersec-Q4_K_M
ENV MODEL_FILENAME=phi4-mini-instruct-Q4_K_M.gguf
ENV USE_RAG=false
ENV CACHE_ENABLED=true

# Expose port
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
  CMD python -c "import requests; requests.get('http://localhost:8000/health')"

# Run the application
CMD ["python", "main.py"]