Upload Qwen3-Embedding-0.6B Int8 ONNX + tokenizer + inference example

89a70b4 verified about 1 month ago

207 Bytes

	FROM python:3.12


	RUN mkdir /app
	WORKDIR /app
	COPY requirements.txt /app/
	RUN pip install -r requirements.txt

	COPY . /app

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