ARG BASE_IMAGE=ubuntu:24.04
ARG APT_MIRROR=""
ARG APT_PORTS_MIRROR=""

# BASE_IMAGE is either ubuntu:24.04 (for cpu builds) or nvidia/cuda:13.0.0-devel-ubuntu24.04
# (for cublas builds). Both ship apt + Ubuntu Noble packages; the nvidia/cuda base
# additionally provides /usr/local/cuda. Darwin (Metal) builds bypass this Dockerfile
# entirely via scripts/build/ds4-darwin.sh.
FROM ${BASE_IMAGE} AS builder
ARG BUILD_TYPE
ARG TARGETARCH
ARG TARGETVARIANT

ENV BUILD_TYPE=${BUILD_TYPE} \
    DEBIAN_FRONTEND=noninteractive \
    PATH=/usr/local/cuda/bin:${PATH}

WORKDIR /build

# Install build-time deps via plain apt - install-base-deps.sh's full pipeline
# (CUDA keyring + from-source gRPC) is unnecessary here:
#   - CUDA: when BASE_IMAGE=nvidia/cuda:*, /usr/local/cuda is already populated;
#     for the cpu build we don't need CUDA at all.
#   - gRPC/Protobuf: system apt packages are sufficient; ds4's wrapper only links
#     against them, it doesn't ship the gRPC source tree.
#   - nlohmann-json: dsml_renderer's only third-party dep.
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        git cmake build-essential pkg-config ca-certificates \
        libgrpc++-dev libprotobuf-dev protobuf-compiler protobuf-compiler-grpc \
        nlohmann-json3-dev && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*

COPY . /LocalAI

RUN --mount=type=cache,target=/root/.ccache,id=ds4-ccache-${TARGETARCH}-${BUILD_TYPE},sharing=locked \
    make -C /LocalAI/backend/cpp/ds4 BUILD_TYPE=${BUILD_TYPE} NATIVE=false grpc-server package

FROM scratch
COPY --from=builder /LocalAI/backend/cpp/ds4/package/. ./