【大语言模型_5】xinference部署embedding模型和rerank模型

server/2025/3/19 2:46:15/

一、安装xinference

pip install xinference

二、启动xinference

./xinference-local  --host=0.0.0.0  --port=5544

三、注册本地模型

1、注册embedding模型
curl -X POST "http://localhost:5544/v1/models" \
-H "Content-Type: application/json" \
-d '{"model_type": "embedding","model_name": "bce-embedding-base_v1",  "model_uid": "bce-embedding-base_v1",   "model_path": "/root/embed_rerank/bce-embedding-base_v1/" 
}'验证：
curl -X POST "http://localhost:5544/v1/embeddings" \
-H "Content-Type: application/json" \
-d '{"model": "bce-embedding-base_v1","input": ["需要嵌入的文本1", "这是第二个句子"]
}'2、注册rerank模型curl -X POST "http://localhost:5544/v1/models" \
-H "Content-Type: application/json" \
-d '{"model_type": "rerank",              "model_name": "bce-reranker-base_v1",     "model_uid": "bce-reranker-base_v1",   "model_path": "/root/embed_rerank/bce-reranker-base_v1" 
}'验证
curl -X POST "http://localhost:5544/v1/rerank" \
-H "Content-Type: application/json" \
-d '{"model": "bge-reranker-v2-m3","query": "What is Python?","documents": ["Python is a programming language.","Java is another language.","Python is used for web development."]
}'3、执行./xinference list 查看运行模型

四、删除模型

curl -X DELETE "http://localhost:5544/v1/models/bge-reranker-v2-m3"

五、备注

1、在cpu运行

服务器有显卡但是选择用cpu加载

启动xinference之前设置

export CUDA_VISIBLE_DEVICES=""

服务器无显卡会自动在cpu加载模型

2、在gpu运行

启动服务器前设置环境变量

export CUDA_VISIBLE_DEVICES=""

curl -X POST "http://localhost:5544/v1/models" \
-H "Content-Type: application/json" \
-d '{"model_type": "embedding","model_name": "bce-embedding-base_v1",  "model_uid": "bce-embedding-base_v1",   "model_path": "/root/zml/embed_rerank/bce-embedding-base_v1/" "gpu_idx": 1"n_gpu" : 1
}'备注：
gpu_idx :选用的显卡index
n_gpu:选定的显卡总张数