接口请求域名: tione.intl.tencentcloudapi.com 。
列举在线推理服务组
默认接口请求频率限制:20次/秒。
以下请求参数列表仅列出了接口请求参数和部分公共参数,完整公共参数列表见 公共请求参数。
| 参数名称 | 必选 | 类型 | 描述 |
|---|---|---|---|
| Action | 是 | String | 公共参数,本接口取值:DescribeModelServiceGroups。 |
| Version | 是 | String | 公共参数,本接口取值:2021-11-11。 |
| Region | 是 | String | 公共参数,详见产品支持的 地域列表。 |
| TiProjectId | 否 | String | TI工作空间ID 仅用于“工作空间”白名单功能。如需使用,请联系TI管理员开通白名单。 |
| Offset | 否 | Integer | 偏移量,默认为0 |
| Limit | 否 | Integer | 返回数量,默认为20,最大值为100 |
| Order | 否 | String | 输出列表的排列顺序。取值范围:ASC:升序排列 DESC:降序排列 |
| OrderField | 否 | String | 排序的依据字段, 取值范围 "CreateTime" "UpdateTime" |
| Filters.N | 否 | Array of Filter | 分页参数,支持的分页过滤Name包括: |
| TagFilters.N | 否 | Array of TagFilter | 标签过滤参数 |
| 参数名称 | 类型 | 描述 |
|---|---|---|
| TotalCount | Integer | 推理服务组数量。 |
| ServiceGroups | Array of ServiceGroup | 服务组信息 |
| GlobalTotalCount | Integer | 当前uin和region下全量服务组数量 |
| RequestId | String | 唯一请求 ID,由服务端生成,每次请求都会返回(若请求因其他原因未能抵达服务端,则该次请求不会获得 RequestId)。定位问题时需要提供该次请求的 RequestId。 |
POST / HTTP/1.1
Host: tione.intl.tencentcloudapi.com
Content-Type: application/json
X-TC-Action: DescribeModelServiceGroups
<公共请求参数>
{
"Limit": 10,
"Offset": 0,
"Filters": []
}
{
"Response": {
"ServiceGroups": [
{
"ServiceGroupId": "ms-vzd8qdk5",
"ServiceGroupName": "llm_test",
"CreatedBy": "100032054859",
"CreateTime": "2023-08-05T05:46:58Z",
"UpdateTime": "2023-08-08T14:27:02Z",
"Uin": "100005348929",
"ServiceCount": 1,
"RunningServiceCount": 0,
"Services": [
{
"ServiceGroupId": "ms-vzd8qdk5",
"ServiceId": "ms-vzd8qdk5-1",
"ServiceGroupName": "llm_test",
"ServiceDescription": "",
"ServiceInfo": {
"Replicas": 0,
"ImageInfo": {
"ImageType": "PRE_SET",
"ImageUrl": "tione.tencentcloudcr.com/qcloud-ti-platform/chatglm-demo:latest",
"RegistryRegion": "",
"RegistryId": ""
},
"Env": [],
"Resources": {
"Cpu": 12000,
"Memory": 45056,
"Gpu": 100,
"RealGpu": 100,
"GpuType": "A10",
"RealGpuDetailSet": [
{
"Name": "A10",
"Value": 100
}
]
},
"InstanceType": "TI.GNV4.3XLARGE44.POST",
"ModelInfo": {
"ModelId": "m-838176671237008128",
"ModelName": "chatglm-6b-tiacc-ft",
"ModelVersionId": "mv-v1-838176671237008129",
"ModelVersion": "v1",
"ModelSource": "COS",
"ModelType": "NORMAL",
"CosPathInfo": {
"Bucket": "danerli-guangzhou-1256580188",
"Region": "ap-guangzhou",
"Paths": [
"output/ai_market_algo_test_thu_tiacc_ft/train-793371624977165056/output/adgen-chatglm-6b-ft-1e-8/checkpoint-500/model_service.py"
]
},
"AlgorithmFramework": "PYTORCH",
"ModelFormat": "PYTORCH"
},
"InferCodeInfo": {
"CosPathInfo": {
"Bucket": "danerli-guangzhou-1256580188",
"Region": "ap-guangzhou",
"Paths": [
"output/ai_market_algo_test_thu_tiacc_ft/train-793371624977165056/output/adgen-chatglm-6b-ft-1e-8/checkpoint-500/model_service.py"
]
}
},
"VolumeMount": {
"VolumeSourceType": "CFS",
"CFSConfig": {
"Id": "cfs-mpjk7vit",
"Path": "/",
"MountType": "",
"Protocol": ""
}
},
"LogEnable": false,
"LogConfig": null,
"AuthorizationEnable": false,
"ScaleMode": "",
"HorizontalPodAutoscaler": null,
"CronScaleJobs": [],
"ScaleStrategy": "",
"ScheduledAction": null,
"Status": {
"Replicas": 0,
"UpdatedReplicas": 0,
"ReadyReplicas": 0,
"AvailableReplicas": 0,
"UnavailableReplicas": 0,
"Status": "Stopped",
"Reason": "",
"Conditions": [
{
"Message": "Deployment has minimum availability.",
"Reason": "MinimumReplicasAvailable",
"Status": "True",
"Type": "Available",
"LastTransitionTime": "2023-08-08T22:27:01+08:00",
"LastUpdateTime": "2023-08-08T22:27:01+08:00"
},
{
"Message": "ReplicaSet \"ms-vzd8qdk5-1-7456b4cc97\" has successfully progressed.",
"Reason": "NewReplicaSetAvailable",
"Status": "True",
"Type": "Progressing",
"LastTransitionTime": "2023-08-08T22:27:02+08:00",
"LastUpdateTime": "2023-08-08T22:27:02+08:00"
}
]
},
"Weight": 0,
"PodList": [],
"Pods": null,
"PodInfos": [],
"ResourceTotal": null,
"OldReplicas": 1,
"HybridBillingPrepaidReplicas": 0,
"OldHybridBillingPrepaidReplicas": 0,
"ServiceLimit": null,
"ModelHotUpdateEnable": false,
"ModelTurboEnable": false
},
"ClusterId": "",
"Region": "ap-guangzhou",
"Namespace": "infer-100005348929",
"ChargeType": "POSTPAID_BY_HOUR",
"ResourceGroupId": "",
"ResourceGroupName": "",
"Tags": [],
"IngressName": "user-ingress-1",
"CreatedBy": "100032054859",
"CreateTime": "2023-08-05T05:46:58Z",
"UpdateTime": "2023-08-08T14:27:02Z",
"Uin": "100005348929",
"SubUin": "",
"AppId": 0,
"BusinessStatus": "CREATE_SUCCEED",
"CreateFailedReason": "CREATE_SUCCEED",
"Status": "Stopped",
"BillingInfo": "",
"Weight": 100,
"CreateSource": "DEFAULT",
"Version": "1",
"LatestVersion": "",
"ServiceLimit": null,
"ScheduledAction": null
}
],
"Status": "Stopped",
"Tags": [],
"BusinessStatus": "",
"WeightUpdateStatus": "",
"CreateSource": "DEFAULT",
"BillingInfo": "",
"LatestVersion": ""
}
],
"TotalCount": 1,
"GlobalTotalCount": 100,
"RequestId": "e5daa146-abed-4d31-ab15-ac9e251fc13c"
}
}
云 API 3.0 提供了配套的开发工具集(SDK),支持多种编程语言,能更方便的调用 API。
以下仅列出了接口业务逻辑相关的错误码,其他错误码详见 公共错误码。
| 错误码 | 描述 |
|---|---|
| AuthFailure | CAM签名/鉴权错误。 |
| AuthFailure.CamException | CAM系统异常。 |
| AuthFailure.UnauthorizedOperation | 未授权操作。 |
| FailedOperation | 操作失败。 |
| FailedOperation.ApiGatewayQueryFailed | API网关访问失败,请重试。 |
| FailedOperation.BillingQueryFailed | 计费模块访问失败。 |
| FailedOperation.ClusterQueryFailed | 集群访问失败。 |
| FailedOperation.DuplicateName | 名称重复。 |
| FailedOperation.ExecDatabaseFail | 数据库执行错误。 |
| FailedOperation.ExecTagFail | 标签操作失败。 |
| FailedOperation.NoPermission | 没有权限。 |
| FailedOperation.NotAllow | 操作不允许。 |
| FailedOperation.QueryDatabaseFail | 数据库查询错误。 |
| FailedOperation.QueryTagFail | 查询标签服务失败。 |
| FailedOperation.StsQueryFailed | 密钥服务访问失败,请重试。 |
| FailedOperation.UnknownInstanceType | 未知的实例规格。 |
| FailedOperation.UnmarshalData | 数据解析失败。 |
| InternalError | 内部错误。 |
| InvalidParameter | 参数错误。 |
| InvalidParameterValue | 参数取值错误。 |
| InvalidParameterValue.BadName | 名称不合法。 |
| MissingParameter | 缺少参数错误。 |
| OperationDenied | 操作被拒绝。 |
| OperationDenied.BalanceInsufficient | 余额不足,创建/更新失败。 |
| ResourceNotFound | 资源不存在。 |
文档反馈