Lindorm AI引擎提供了一系列RESTful风格的API,您可以通过curl命令调用这些API进行模型管理和推理等操作。本文提供使用curl命令调用RESTful API接口的示例。
前提条件
参数说明
说明
以下参数说明适用于本文所有示例。
参数 | 说明 |
url | AI引擎的连接地址。请联系Lindorm技术支持(钉钉号:s0s3eg3)获取。 |
username | 访问AI引擎的用户名和密码。获取方式,请参见访问实例。 |
password |
模型管理
创建模型
在AI引擎中创建模型bge_m3_model。
curl -X POST "http://<url>/v1/ai/models/create" \
-H "x-ld-ak: <username>" \
-H "x-ld-sk: <password>" \
-H "Content-Type: application/json" \
-d '{
"model_name": "bge_m3_model",
"model_path": "huggingface://BAAI/bge-m3",
"task": "FEATURE_EXTRACTION",
"algorithm": "BGE_M3"
}'
返回结果:
{"code": 0,"msg": "SUCCESS","data": null,"success": true}
查看所有模型信息
curl -X GET "http://<url>/v1/ai/models/list" \
-H "x-ld-ak: <username>" \
-H "x-ld-sk: <password>"
返回结果:
{
"code": 0,
"msg": "SUCCESS",
"data": {
"models": [{
"name": "bge_m3_model",
"status": "READY",
"created_time": "...",
"updated_time": "...",
...
}, {
"name": "bge_model",
"status": "READY",
...
}]
},
"success": true
"request_id":"..."
}
查看模型的详细信息
curl -X GET "http://<url>/v1/ai/models/bge_m3_model/status" \
-H "x-ld-ak: <username>" \
-H "x-ld-sk: <password>"
返回结果:
{
"code": 0,
"msg": "SUCCESS",
"data": {
"name": "bge_m3_model",
"status": "READY",
"task_type":"FEATURE_EXTRACTION",
"algorithm":"BGE_M3",
"settings": "...",
"error":"...",
"progress": "...",
...
},
"success": true
}
删除模型
删除模型bge_m3_model。
curl -X POST "http://<url>/v1/ai/models/bge_m3_model/drop" \
-H "x-ld-ak: <username>" \
-H "x-ld-sk: <password>"
返回结果:
{"code": 0,"msg": "SUCCESS","data": null,"success": true}
模型推理
使用已创建的模型推理
curl -X POST "http://<url>/v1/ai/models/bge_m3_model/infer" \
-H "x-ld-ak: <username>" \
-H "x-ld-sk: <password>" \
-H "Content-Type: application/json" \
-d '{"input":["你好","我们"]}' \
返回推理结果如下:
{
"code": 0,
"msg": "SUCCESS",
"data": [[0.027204733341932297,0.004229982383549213, ...],
[-0.05367295444011688,0.022600287571549416, ...]],
"success": true
}
参数调整
调整已部署模型的参数配置。
curl -X POST "http://<url>/v1/ai/models/bge_m3_model/update_config" \
-H "x-ld-ak: <username>" \
-H "x-ld-sk: <password>" \
-H "Content-Type: application/json" \
-d '{"instance_count": "2"}' \
调整成功将返回如下结果:
{"code": 0,"msg": "SUCCESS","data": null,"success": true}
文档内容是否对您有帮助?