Cant not request

[wanzhixiao]

System Info

CUDA Version: 12.0 , with A10 GPU
CentOS: 7.9

Information

• Docker
• The CLI directly

Tasks

• An officially supported command
• My own modifications

Reproduction

I run the text-embedding-inference program by the following script

volume=/data/pretrain_model
model=/data/pretrain_model/bge-small-zh-v1.5
revision=refs/pr/5

docker run -d --restart=always --gpus all\
            -p 8070:80 \
            -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:86-1.2 \
            --model-id $model \
            --tokenization-workers 2

and the docker has successfully run, however, when i try the following command for caculate embedding:

curl 127.0.0.1:8070/embed_sparse \
    -X POST \
    -d '{"inputs":"I like you."}' \
    -H 'Content-Type: application/json'

the error ocurred:
curl: (56) Recv failure: Connection reset by peer, how can i solve it?

docker logs

Expected behavior

return the embedding

[CharleyXu]

You can refer to #207