FROM ubuntu:24.04

ENV DEBIAN_FRONTEND=noninteractive

RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.12 python3.12-venv python3.12-dev python3-pip \
    libpoppler-cpp-dev poppler-utils \
    libgl1 libglib2.0-0 \
    build-essential curl \
    && rm -rf /var/lib/apt/lists/*

COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv

WORKDIR /app

# Install CPU torch first, on its own, from the CPU index.
#
# Order matters: anything that depends on torch (sentence-transformers) will
# otherwise resolve the default CUDA build and pull ~2.7GB of nvidia-* wheels.
# Reinstalling torch afterwards replaces torch but leaves those wheels behind,
# orphaned and unused — which is how the CPU image ended up larger than the
# CUDA one. Installing CPU torch up front means nothing ever requests CUDA.
#
# Keeping it in its own layer also bounds the blob size: the registry drops
# uploads that take longer than 60s, so no single layer should approach ~3GB.
# Placing it before the source COPYs keeps this expensive layer cached when
# only application code changes.
RUN uv venv .venv && \
    . .venv/bin/activate && \
    UV_HTTP_TIMEOUT=600 uv pip install torch torchvision \
        --index-url https://download.pytorch.org/whl/cpu

COPY pyproject.toml ./
COPY kb/ kb/
COPY main.py ./
COPY VERSION ./

# Remaining dependencies resolve against the CPU torch already present.
RUN . .venv/bin/activate && \
    uv pip install "sentence-transformers[onnx]" && \
    uv pip install -e .

ENV PATH="/app/.venv/bin:$PATH"
ENV VIRTUAL_ENV="/app/.venv"
ENV KB_DEVICE=cpu
ENV KB_INGEST_DEVICE=cpu
ENV KB_DATA_DIR=/data

EXPOSE 8000
VOLUME ["/data"]

CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]