steve
2030976b85
- Add configurable device selection for embeddings (embedding.device) and Docling ingestion (ingestion.device) with env var overrides (KB_DEVICE, KB_INGEST_DEVICE) to control GPU/CPU usage per component - Add `kb doctor` command for safe GPU diagnostics - Add Dockerfile (NVIDIA CUDA) and compose.yaml for containerised GPU usage - Add OpenSpec v2 change (kb-v2-client-server): proposal, design, specs, and tasks for client-server architecture with Go CLI, FastAPI engine, async ingestion queue, and GPU-vendor-agnostic Docker deployment - Add uv.lock for reproducible installs - Gitignore examples/ directory (test data only) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
45 lines
1.1 KiB
Docker
45 lines
1.1 KiB
Docker
FROM nvidia/cuda:13.0.1-runtime-ubuntu24.04
|
|
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
|
|
# System deps for docling (poppler for PDF, build tools for native wheels)
|
|
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/*
|
|
|
|
# Install uv for fast dependency resolution
|
|
COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
|
|
|
|
WORKDIR /app
|
|
|
|
# Copy project files
|
|
COPY pyproject.toml uv.lock ./
|
|
COPY src/ src/
|
|
|
|
# Create venv, install deps, overlay onnxruntime-gpu
|
|
RUN uv venv .venv && \
|
|
. .venv/bin/activate && \
|
|
uv sync && \
|
|
uv pip install --no-deps onnxruntime-gpu
|
|
|
|
# Put venv on PATH
|
|
ENV PATH="/app/.venv/bin:$PATH"
|
|
ENV VIRTUAL_ENV="/app/.venv"
|
|
|
|
# GPU enabled by default in the container
|
|
ENV KB_DEVICE=auto
|
|
ENV KB_INGEST_DEVICE=auto
|
|
|
|
# Model cache persisted via volume
|
|
ENV HF_HOME=/data/hf_cache
|
|
ENV KB_DATA_DIR=/data/kb
|
|
|
|
VOLUME ["/data"]
|
|
|
|
ENTRYPOINT ["kb"]
|
|
CMD ["--help"]
|