Dockerfile

FROM ghcr.io/huggingface/text-embeddings-inference:cpu-1.7

ENV MODEL_ID=mixedbread-ai/mxbai-embed-large-v1
ENV DIMENSIONS=512
ENV MAX_BATCH_TOKENS=8192
ENV HUGGINGFACE_HUB_CACHE=/tmp/hf-cache
ENV PORT=7860

CMD ["--port","7860","--max-concurrent-requests","32"]