llm_vector_server/Dockerfile

FROM egs-registry.cn-hangzhou.cr.aliyuncs.com/egs/vllm:0.8.2-pytorch2.6-cu124-20250328

WORKDIR /app

ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1
ENV PIP_DISABLE_PIP_VERSION_CHECK=on
ENV TZ=Asia/Shanghai

RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone \

COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pillow

COPY . .

EXPOSE 8000

CMD ["python3", "-m", "vllm.entrypoints.openai.api_server",
     "--model", "/app/model/Qwen3-Embedding-4B",
     "--dtype", "float16",
     "--host", "0.0.0.0",
     "--port", "8000",
     "--trust-remote-code"]