ZStack Logo

ZStack AIOS

部署分布式模型服务 (DeployDistributedModelService)

面向开发者的 API 使用规范、SDK 调用方式和 AIOS 相关接口说明。

API请求

URLs
PUT zstack/v1/ai/model-services
Headers
Authorization: OAuth the-session-uuid
Body
{
  "deployDistributedModelService": {
    "modelServices": [
      {
        "isInitialNode": false,
        "uuid": "f1e135835fee363c9f57ed8232023886",
        "zoneUuid": "7a007a391d483c9f843bf1df4b7e5d8f",
        "cpuNum": 8,
        "name": "model-service",
        "type": "VirtualMachine",
        "memorySize": 17179869184,
        "timeout": 0
      }
    ],
    "serviceCreationStrategy": "parallel",
  "name": "distributed-model-service"
  },
  "systemTags": [],
  "userTags": []
}
说明: 上述示例中systemTagsuserTags字段可以省略。列出是为了表示body中可以包含这两个字段。
Curl示例
curl -H "Content-Type: application/json;charset=UTF-8" \
-H "Authorization: OAuth b86c9016b4f24953a9edefb53ca0678c" \
-X PUT -d '{"deployDistributedModelService":{"modelServices":[{"isInitialNode":false,"uuid":"f1e135835fee363c9f57ed8232023886","zoneUuid":"7a007a391d483c9f843bf1df4b7e5d8f","cpuNum":8,"name":"model-service","type":"VirtualMachine","memorySize":17179869184,"timeout":0}],"serviceCreationStrategy":"parallel","name":"distributed-model-service"}}' \
http://localhost:8080/zstack/v1/ai/model-services
参数列表
名字 类型 位置 描述 可选值 起始版本
modelServices List body(包含在deployDistributedModelService结构中) 模型服务部署信息 5.3.22
serviceCreationStrategy String body(包含在deployDistributedModelService结构中) 服务创建策略
  • parallel
  • sequential
5.3.22
name String body(包含在deployDistributedModelService结构中) 资源名称 5.3.22
description (可选) String body(包含在deployDistributedModelService结构中) 资源的详细描述 5.3.22
systemTags (可选) List body 系统标签 5.3.22
userTags (可选) List body 用户标签 5.3.22
resourceUuid (可选) String body(包含在deployDistributedModelService结构中) 资源UUID 5.3.46
tagUuids (可选) List body(包含在deployDistributedModelService结构中) 标签UUID列表 5.3.46

API返回

返回示例
{
  "inventory": {
    "uuid": "groupUuid",
    "name": "distributed-model-service",
    "status": "Running"
  }
}
返回字段
名字 类型 描述 起始版本
success Boolean 操作是否成功 5.1.8
error ErrorCode 错误码,操作成功时该字段为null 5.1.8
inventory ModelServiceInstanceGroupInventory 模型服务实例组清单 5.1.8
#inventory
名字 类型 描述 起始版本
uuid String 资源的UUID,唯一标识该资源 5.1.8
modelServiceUuid String 模型服务UUID 5.1.8
modelUuid String 模型UUID 5.1.8
instances List 模型服务实例列表 5.1.8
datasetRefInventories List 数据集引用列表 5.1.8
status String 实例组状态 5.1.8
modelServiceType String 模型服务类型 5.1.8
type String 实例组类型 5.1.8
name String 实例组名称 5.1.8
description String 实例组描述 5.1.8
yaml String YAML配置 5.1.8
supportMetrics List 支持的指标列表 5.1.8
exportPath String 导出路径 5.1.8
createDate Timestamp 创建时间 5.1.8
lastOpDate Timestamp 最后一次修改时间 5.1.8

SDK示例

Java SDK
DeployDistributedModelServiceAction action = new DeployDistributedModelServiceAction();
action.modelServices = asList([isInitialNode:false, uuid:f1e135835fee363c9f57ed8232023886, zoneUuid:7a007a391d483c9f843bf1df4b7e5d8f, cpuNum:8, name:model-service, type:VirtualMachine, memorySize:17179869184, timeout:0]);
action.serviceCreationStrategy = "parallel";
action.name = "distributed-model-service";
action.sessionId = "b86c9016b4f24953a9edefb53ca0678c";
DeployDistributedModelServiceAction.Result res = action.call();
Python SDK
DeployDistributedModelServiceAction action = DeployDistributedModelServiceAction()
action.modelServices = [[isInitialNode:false, uuid:f1e135835fee363c9f57ed8232023886, zoneUuid:7a007a391d483c9f843bf1df4b7e5d8f, cpuNum:8, name:model-service, type:VirtualMachine, memorySize:17179869184, timeout:0]]
action.serviceCreationStrategy = "parallel"
action.name = "distributed-model-service"
action.sessionId = "b86c9016b4f24953a9edefb53ca0678c"
DeployDistributedModelServiceAction.Result res = action.call()