Dockerfile.embedder.cpu

FROM python:3.12-slim

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    HF_HOME=/cache/huggingface \
    EMBEDDING_MODEL=Qwen/Qwen3-Embedding-0.6B \
    EMBEDDING_DEVICE=cpu \
    EMBEDDING_BATCH_SIZE=8 \
    EMBEDDING_MAX_LENGTH=512

WORKDIR /app
COPY pyproject.toml README.md ./
COPY justatom ./justatom
RUN python -m pip install --no-cache-dir --upgrade pip \
    && python -m pip install --no-cache-dir \
       --index-url https://download.pytorch.org/whl/cpu torch==2.8.0 \
    && python -m pip install --no-cache-dir '.[embedder]' \
    && useradd --create-home --uid 10001 justatom \
    && mkdir -p /cache/huggingface \
    && chown -R 10001:10001 /cache/huggingface

USER 10001:10001
EXPOSE 8000
HEALTHCHECK --interval=10s --timeout=3s --start-period=120s --retries=30 \
  CMD ["python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=2)"]
CMD ["python", "-m", "justatom.api.serve_embeddings"]