# Intel GPU Ray Worker for danilo (Intel i915 iGPU)
# Used for: Reranker
#
# Build from llm-workflows root:
#   docker build -t git.daviestechlabs.io/daviestechlabs/ray-worker-intel:latest -f dockerfiles/Dockerfile.ray-worker-intel .
#
# Multi-stage build to ensure Python 3.11.11 matches Ray head node
FROM rayproject/ray:2.53.0-py311 AS base

LABEL maintainer="billy-davies-2"
LABEL description="Ray worker for Intel GPUs (Reranker)"
LABEL gpu.target="intel-xpu"

WORKDIR /app

# Install system dependencies for Intel GPU support
USER root
RUN apt-get update && apt-get install -y --no-install-recommends \
    git \
    curl \
    wget \
    gnupg2 \
    && rm -rf /var/lib/apt/lists/*

# Add Intel oneAPI repository for runtime libraries
RUN wget -qO - https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor -o /usr/share/keyrings/intel-oneapi-archive-keyring.gpg && \
    echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" > /etc/apt/sources.list.d/intel-oneapi.list

# Add Intel compute-runtime repository for Level Zero
RUN wget -qO - https://repositories.intel.com/gpu/intel-graphics.key | gpg --dearmor -o /usr/share/keyrings/intel-graphics-archive-keyring.gpg && \
    echo "deb [signed-by=/usr/share/keyrings/intel-graphics-archive-keyring.gpg arch=amd64] https://repositories.intel.com/gpu/ubuntu jammy client" > /etc/apt/sources.list.d/intel-gpu.list && \
    apt-get update && apt-get install -y --no-install-recommends \
    intel-oneapi-runtime-opencl \
    intel-oneapi-runtime-compilers \
    intel-level-zero-gpu \
    level-zero \
    && rm -rf /var/lib/apt/lists/*

USER ray

# Ensure Ray CLI is in PATH
ENV PATH="/home/ray/.local/bin:${PATH}"

# Install Intel Extension for PyTorch (IPEX) for Python 3.11
# This provides XPU support for Intel GPUs
RUN pip install --no-cache-dir \
    torch==2.5.1 \
    intel-extension-for-pytorch==2.5.10+xpu \
    --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/

# Install Ray Serve and AI inference dependencies
RUN pip install --no-cache-dir \
    sentence-transformers \
    FlagEmbedding \
    fastapi \
    uvicorn \
    httpx \
    pydantic \
    transformers \
    huggingface_hub

# Copy Ray Serve Python code
COPY ray-serve/ /app/ray_serve/
ENV PYTHONPATH=/app

# Copy Ray Serve entrypoint
COPY --chmod=755 dockerfiles/ray-entrypoint.sh /app/ray-entrypoint.sh

# Default environment variables
ENV RAY_HEAD_SVC="ai-inference-raycluster-head-svc"
ENV GPU_RESOURCE="gpu_intel"
ENV NUM_GPUS="1"
# Intel XPU settings
ENV ZE_AFFINITY_MASK=0
ENV SYCL_DEVICE_FILTER=level_zero:gpu

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