# syntax=docker/dockerfile:1.7
# NVIDIA GPU Ray Worker for elminster (RTX 2070)
# Used for: Whisper STT, XTTS Text-to-Speech
#
# Build:
#   docker build -t git.daviestechlabs.io/daviestechlabs/ray-worker-nvidia:latest \
#     -f dockerfiles/Dockerfile.ray-worker-nvidia .

FROM docker.io/rayproject/ray:2.53.0-py312-cu121

# OCI Image Spec labels
LABEL org.opencontainers.image.title="Ray Worker - NVIDIA GPU"
LABEL org.opencontainers.image.description="Ray Serve worker for NVIDIA GPUs (Whisper STT, XTTS TTS)"
LABEL org.opencontainers.image.vendor="DaviesTechLabs"
LABEL org.opencontainers.image.source="https://git.daviestechlabs.io/daviestechlabs/kuberay-images"
LABEL org.opencontainers.image.licenses="MIT"
LABEL gpu.target="nvidia-cuda-12.1"
LABEL ray.version="2.53.0"

WORKDIR /app

# Install system dependencies in a single layer with cleanup
USER root
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
    --mount=type=cache,target=/var/lib/apt,sharing=locked \
    apt-get update && apt-get install -y --no-install-recommends \
        ffmpeg \
        libsndfile1 \
    && rm -rf /var/lib/apt/lists/*

# Install uv for fast Python package management (ADR-0014)
COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv

# Switch back to non-root ray user
USER ray

# Install Python dependencies with uv cache mount (10-100x faster than pip)
# Pinned versions for reproducibility
RUN --mount=type=cache,target=/home/ray/.cache/uv,uid=1000,gid=1000 \
    uv pip install --system \
        'faster-whisper>=1.0.0,<2.0' \
        'coqui-tts>=0.27.0,<1.0' \
        'soundfile>=0.12.0,<1.0' \
        'pydub>=0.25.0,<1.0' \
        'librosa>=0.10.0,<1.0' \
        'torch>=2.0.0,<3.0' \
        'torchaudio>=2.0.0,<3.0' \
        'fastapi>=0.100.0,<1.0' \
        'uvicorn>=0.23.0,<1.0' \
        'httpx>=0.27.0,<1.0' \
        'pydantic>=2.0.0,<3.0'

# Copy entrypoint script (ray-serve-apps is installed from PyPI at runtime)
COPY --chown=1000:100 --chmod=755 dockerfiles/ray-entrypoint.sh /app/ray-entrypoint.sh

# Environment configuration
ENV PYTHONPATH=/app \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    CUDA_VISIBLE_DEVICES=0 \
    RAY_HEAD_SVC="ai-inference-raycluster-head-svc" \
    GPU_RESOURCE="gpu_nvidia" \
    NUM_GPUS="1"

# Health check - verify Ray worker can connect
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD ray status --address=localhost:6379 || exit 1

ENTRYPOINT ["/app/ray-entrypoint.sh"]