Decision Optimization REST API 部署 | IBM Cloud Pak for Data as a Service

Go back to the English version of the documentation

REST API 示例

Last updated: 2024年12月05日

Decision Optimization REST API 部署

您可以使用watsonx.aiRuntime REST API 部署Decision Optimization模型、创建和监控作业并获取解决方案。

准备工作

您必须拥有IBM Cloud帐户。 请参阅 https://www.ibm.com/cloud/。

登录 IBM Cloud。
创建 API 密钥。从打开的 "成功创建 API 密钥窗口中复制或下载（关闭该窗口后将无法再次访问）。
可选：创建watsonx.ai运行时服务。
从IBM Cloud资源列表视图中的人工智能/机器Machine Learning服务列表中选择一个watsonx.aiRuntime实例。
从信息窗格中复制watsonx.aiRuntime实例的名称、GUID 和CRN。 (要打开信息窗格，请单击watsonx.aiRuntime服务名称旁边行中的任意位置，但不要单击名称本身。然后在同一窗口中打开信息窗格）
可选：创建Cloud Object Storage。
从IBM Cloud资源列表视图中的存储资源列表中选择Cloud Object Storage实例。
从存储实例的信息窗格中复制名称和CRN。
可选：从https://dataplatform.cloud.ibm.com用户界面创建部署空间。您还可以使用 REST API 创建部署空间。请参阅使用 REST API 创建部署空间。
从部署列表中选择一个部署空间。
从"管理">"常规 "选项卡复制空间 GUID。有关更多信息，请参阅部署空间。

关于本任务

以下步骤将向您展示如何使用watsonx.aiRuntime REST API 部署Decision Optimization模型。 REST API 示例使用 curl，后者是一个命令行工具和库，用于以 URL 语法传输数据。您可以在http://curl.haxx.se 下载 curl 并了解更多相关信息。有关与 Decision Optimization相关的 REST API 的更多信息，请参阅以下部分:

对于 Windows 用户，请将用作多行分隔符的 \ 改为 ^，并在这些代码示例中使用双引号 "。另外，Windows 用户必须在标题行中至少使用一个空格字符的缩进。

为方便说明，此过程中的某些代码示例已放在 json 文件中，以使命令更容易阅读和使用。

使用 REST API 创建部署后，还可以通过https://dataplatform.cloud.ibm.com用户界面中的 "部署 > 空间"页面查看部署并向其发送作业。

过程

使用您的IBM CloudAPI 密钥 生成 IAM 令牌，如下所示。

curl "https://iam.cloud.ibm.com/identity/token" \
  -d "apikey=YOUR_API_KEY_HERE&grant_type=urn%3Aibm%3Aparams%3Aoauth%3Agrant-type%3Aapikey" \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -H "Authorization: Basic Yng6Yng="

输出示例：

{
   "access_token": "****** obtained IAM token ******************************",
   "refresh_token": "**************************************",
   "token_type": "Bearer",
   "expires_in": 3600,
   "expiration": 1554117649,
   "scope": "ibm openid"
}

在所有 API 调用中，使用以 Authorization 头中的单词 Bearer 和 ML-Instance-ID 头中的单词 watsonx.ai Runtime service GUID 为前缀的获取令牌 (access_token 值)。

可选: 如果未如前所述从用户界面获取 SPACE-ID ，那么可以使用 REST API 创建空间，如下所示。在所有 API 调用中，使用 Authorization 头中以词 bearer 开头的先前获取的令牌。

curl --location --request POST \
  "https://api.dataplatform.cloud.ibm.com/v2/spaces" \
  -H "Authorization: Bearer TOKEN-HERE" \
  -H "ML-Instance-ID: MACHINE-LEARNING-SERVICE-GUID-HERE" \
  -H "Content-Type: application/json" \
  --data-raw "{
  "name": "SPACE-NAME-HERE",
  "description": "optional description here",
  "storage": {
      "resource_crn": "COS-CRN-ID-HERE"
  },
  "compute": [{
    "name": "MACHINE-LEARNING-SERVICE-NAME-HERE",
    "crn": "MACHINE-LEARNING-SERVICE-CRN-ID-HERE"
  }]
}"

对于 Windows 用户，请将 --data-raw 命令置于一行上，并将此命令中所有的 " 替换为 \"，如下所示：

curl --location --request POST ^
  "https://api.dataplatform.cloud.ibm.com/v2/spaces" ^
  -H "Authorization: Bearer TOKEN-HERE" ^
  -H "ML-Instance-ID: MACHINE-LEARNING-SERVICE-GUID-HERE" ^
  -H "Content-Type: application/json" ^
  --data-raw "{\"name\": "SPACE-NAME-HERE",\"description\": \"optional description here\",\"storage\": {\"resource_crn\": \"COS-CRN-ID-HERE\"  },\"compute\": [{\"name\": "MACHINE-LEARNING-SERVICE-NAME-HERE\",\"crn\": \"MACHINE-LEARNING-SERVICE-CRN-ID-HERE\"  }]}"

或者，将数据置于单独的文件中。

SPACE-ID 会在 metadata 小节的 id 字段中返回。

输出示例：

{
  "entity": {
    "compute": [
      {
        "crn": "MACHINE-LEARNING-SERVICE-CRN",
        "guid": "MACHINE-LEARNING-SERVICE-GUID",
        "name": "MACHINE-LEARNING-SERVICE-NAME",
        "type": "machine_learning"
      }
    ],
    "description": "string",
    "members": [
      {
        "id": "XXXXXXX",
        "role": "admin",
        "state": "active",
        "type": "user"
      }
    ],
    "name": "name",
    "scope": {
      "bss_account_id": "account_id"
    },
    "status": {
      "state": "active"
    }
  },
  "metadata": {
    "created_at": "2020-07-17T08:36:57.611Z",
    "creator_id": "XXXXXXX",
    "id": "SPACE-ID",
    "url": "/v2/spaces/SPACE-ID"
  }
}

您必须等待部署空间状态为 "active"，然后再继续。可以进行轮询以检查状态，如下所示。

curl --location --request GET "https://api.dataplatform.cloud.ibm.com/v2/spaces/SPACE-ID-HERE" \
  -H "Authorization: bearer TOKEN-HERE" \
  -H "Content-Type: application/json"

创建 新 Decision Optimization 模型

所有 API 请求都需要 version 参数，该参数接受格式为 version=YYYY-MM-DD 的日期。此代码示例会发布一个模型，该模型使用文件 create_model.json。 URL 会根据您为watsonx.aiRuntime服务选择的地区/位置而有所不同。请参见端点 URL。

curl --location --request POST \
  "https://us-south.ml.cloud.ibm.com/ml/v4/models?version=2020-08-01" \
  -H "Authorization: bearer TOKEN-HERE" \
  -H "Content-Type: application/json" \
  -d @create_model.json

create_model.json 文件包含以下代码：

{
  "name": "ModelName",
  "description": "ModelDescription",
  "type": "do-docplex_22.1",
  "software_spec": {
    "name": "do_22.1"
  },
  "custom": {
      "decision_optimization": {
        "oaas.docplex.python": "3.11"
      }
  },
  "space_id": "SPACE-ID-HERE"
}

此处在 custom 块中显式声明 Python 版本 。这是可选操作。如果没有它，您的模型将使用默认版本，当前版本为 Python 3.11 。由于缺省版本将随时间演变，因此声明 Python 版本显式使您能够在稍后轻松更改该版本，或者在更新缺省版本时继续使用较旧的受支持版本。目前支持的版本是 3.11 和 3.10 （已废弃）。

如果您希望能够从用户界面针对此模型运行作业，而非只能使用 REST API，那么必须定义输入数据和输出数据的模式。如果创建模型时未定义模式，那么只能使用 REST API 来运行作业，无法从用户界面运行。

您还可以使用为优化模型中的输入和输出指定的模式:

{
  "name": "Diet-Model-schema",
  "description": "Diet",
  "type": "do-docplex_22.1",
  "schemas": {
    "input": [
      {
        "id": "diet_food_nutrients",
        "fields": [
          { "name": "Food",  "type": "string" },
          { "name": "Calories", "type": "double" },
          { "name": "Calcium", "type": "double" },
          { "name": "Iron", "type": "double" },
          { "name": "Vit_A", "type": "double" },
          { "name": "Dietary_Fiber", "type": "double" },
          { "name": "Carbohydrates", "type": "double" },
          { "name": "Protein", "type": "double" }
        ]
      },
      {
        "id": "diet_food",
        "fields": [
          { "name": "name", "type": "string" },
          { "name": "unit_cost", "type": "double" },
          { "name": "qmin", "type": "double" },
          { "name": "qmax", "type": "double" }
        ]
      },
      {
        "id": "diet_nutrients",
        "fields": [
          { "name": "name", "type": "string" },
          { "name": "qmin", "type": "double" },
          { "name": "qmax", "type": "double" }
        ]
      }
    ],
    "output": [
      {
        "id": "solution",
        "fields": [
          { "name": "name", "type": "string" },
          { "name": "value", "type": "double" }
        ]
      }
    ]
  },
  "software_spec": {
    "name": "do_22.1"
  },
  "space_id": "SPACE-ID-HERE"
}

发布模型时，您需提供信息，指出其模型类型以及所要使用的软件规范。

模型类型可以是以下示例类型：

OPL 模型的 do-opl_22.1
do-cplex_22.1 (对于 CPLEX 模型)
针对 CP 模型的 do-cpo_22.1
do-docplex_22.1 for Python 模型

版本 20.1 也可用于这些模型类型。

对于 软件规范，可以使用缺省规范的名称 do_22.1 或 do_20.1。另请参阅扩展软件规范笔记本，其中显示了如何扩展 Decision Optimization 软件规范 (带有 DOcplex 模型的其他 Python 库的运行时)。

MODEL-ID 会在 metadata 的 id 字段中返回。

输出示例：

{
  "entity": {
    "software_spec": {
      "id": "SOFTWARE-SPEC-ID"
    },
    "type": "do-docplex_20.1"
  },
  "metadata": {
    "created_at": "2020-07-17T08:37:22.992Z",
    "description": "ModelDescription",
    "id": "MODEL-ID",
    "modified_at": "2020-07-17T08:37:22.992Z",
    "name": "ModelName",
    "owner": "***********",
    "space_id": "SPACE-ID"
  }
}

上载可供部署的 Decision Optimization 模型阐述 。
首先将模型压缩成(tar.gz, .zip or .jar) 文件，然后上传至watsonx.aiRuntime服务进行部署。
此代码示例上载包含 Python 模型且不含主数据的名为 diet.zip 的模型：
```
curl --location --request PUT \
  "https://us-south.ml.cloud.ibm.com/ml/v4/models/MODEL-ID-HERE/content?version=2020-08-01&space_id=SPACE-ID-HERE&content_format=native" \
  -H "Authorization: bearer TOKEN-HERE" \
  -H "Content-Type: application/gzip" \
  --data-binary "@diet.zip"
```
您可以从DO-samples 下载此示例和其他模型。选择相应的产品和版本子文件夹。

部署模型

创建模型引用。请使用 SPACE-ID、您创建准备就绪可供部署的模型时获取的 MODEL-ID，以及硬件规范。例如：

curl --location --request POST "https://us-south.ml.cloud.ibm.com/ml/v4/deployments?version=2020-08-01" \
  -H "Authorization: bearer TOKEN-HERE" \
  -H "Content-Type: application/json" \
  -d @deploy_model.json

The deploy_model.json file contains the following
code:

{
  "name": "Test-Diet-deploy",
  "space_id": "SPACE-ID-HERE",
  "asset": {
    "id": "MODEL-ID-HERE"
  },
  "hardware_spec": {
    "name": "S"
  },
  "batch": {}
}

DEPLOYMENT-ID 会在 metadata 的 id 字段中返回。输出示例：

{
  "entity": {
    "asset": {
      "id": "MODEL-ID"
    },
    "custom": {},
    "description": "",
    "hardware_spec": {
      "id": "HARDWARE-SPEC-ID",
      "name": "S",
      "num_nodes": 1
    },
    "name": "Test-Diet-deploy",
    "space_id": "SPACE-ID",
    "status": {
      "state": "ready"
    }
  },
  "metadata": {
    "created_at": "2020-07-17T09:10:50.661Z",
    "description": "",
    "id": "DEPLOYMENT-ID",
    "modified_at": "2020-07-17T09:10:50.661Z",
    "name": "test-Diet-deploy",
    "owner": "**************",
    "space_id": "SPACE-ID"
  }
}

部署后，您可以 监视模型的部署状态。 请使用 DEPLOYMENT-ID。

例如：

curl --location --request GET "https://us-south.ml.cloud.ibm.com/ml/v4/deployments/DEPLOYMENT-ID-HERE?version=2020-08-01&space_id=SPACE-ID-HERE" \
  -H "Authorization: bearer TOKEN-HERE" \
  -H "Content-Type: application/json"

输出示例：

{
  "entity": {
    "asset": {
      "id": "MODEL-ID"
    },
    "custom": {},
    "description": "",
    "hardware_spec": {
      "id": "HARDWARE-SPEC-ID",
      "name": "S",
      "num_nodes": 1
    },
    "name": "Test-Diet-deploy",
    "space_id": "SPACE-ID",
    "status": {
      "state": "ready"
    }
  },
  "metadata": {
    "created_at": "2020-11-04T16:22:14.442Z",
    "description": "",
    "id": "DEPLOYMENT-ID",
    "modified_at": "2020-11-04T16:22:14.442Z",
    "name": "test-Diet-deploy",
    "owner": "**************",
    "space_id": "SPACE-ID"
  }
}

然后，您可以针对定义输入数据和输出 (优化求解的结果) 以及日志文件的已部署模型 提交作业 。

例如，以下显示名为 myjob.json 的文件的内容。其包含（内联）输入数据、一些求解参数，并指定输出将是 .csv 文件。更多信息，请参阅Decision Optimization批量部署和模型执行。

{
	"name":"test-job-diet",
	"space_id": "SPACE-ID-HERE",
	"deployment": {
		"id": "DEPLOYMENT-ID-HERE"
	},
	"decision_optimization" : {
		"solve_parameters" : {
			"oaas.logAttachmentName":"log.txt",
			"oaas.logTailEnabled":"true"
		},
		"input_data": [
			{
				"id":"diet_food.csv",
				"fields" : ["name","unit_cost","qmin","qmax"],
				"values" : [
					["Roasted Chicken", 0.84, 0, 10],
					["Spaghetti W/ Sauce", 0.78, 0, 10],
					["Tomato,Red,Ripe,Raw", 0.27, 0, 10],
					["Apple,Raw,W/Skin", 0.24, 0, 10],
					["Grapes", 0.32, 0, 10],
					["Chocolate Chip Cookies", 0.03, 0, 10],
					["Lowfat Milk", 0.23, 0, 10],
					["Raisin Brn", 0.34, 0, 10],
					["Hotdog", 0.31, 0, 10]
				]
			},
			{
				"id":"diet_food_nutrients.csv",
				"fields" : ["Food","Calories","Calcium","Iron","Vit_A","Dietary_Fiber","Carbohydrates","Protein"],
				"values" : [
					["Spaghetti W/ Sauce", 358.2, 80.2, 2.3, 3055.2, 11.6, 58.3, 8.2],
					["Roasted Chicken", 277.4, 21.9, 1.8, 77.4, 0, 0, 42.2],
					["Tomato,Red,Ripe,Raw", 25.8, 6.2, 0.6, 766.3, 1.4, 5.7, 1],
					["Apple,Raw,W/Skin", 81.4, 9.7, 0.2, 73.1, 3.7, 21, 0.3],
					["Grapes", 15.1, 3.4, 0.1, 24, 0.2, 4.1, 0.2],
					["Chocolate Chip Cookies", 78.1, 6.2, 0.4, 101.8, 0, 9.3, 0.9],
					["Lowfat Milk", 121.2, 296.7, 0.1, 500.2, 0, 11.7, 8.1],
					["Raisin Brn", 115.1, 12.9, 16.8, 1250.2, 4, 27.9, 4],
					["Hotdog", 242.1, 23.5, 2.3, 0, 0, 18, 10.4]
				]
			},
			{
				"id":"diet_nutrients.csv",
				"fields" : ["name","qmin","qmax"],
				"values" : [
					["Calories", 2000, 2500],
					["Calcium", 800, 1600],
					["Iron", 10, 30],
					["Vit_A", 5000, 50000],
					["Dietary_Fiber", 25, 100],
					["Carbohydrates", 0, 300],
					["Protein", 50, 100]
				]
			}
		],
		"output_data": [
			{
				"id":".*\\.csv"
			}
		]
	}
}

此代码示例发布使用此文件 myjob.json 的作业。

curl --location --request POST "https://us-south.ml.cloud.ibm.com/ml/v4/deployment_jobs?version=2020-08-01&space_id=SPACE-ID-HERE" \
  -H "Authorization: bearer TOKEN-HERE" \
  -H "Content-Type: application/json" \
  -H "cache-control: no-cache" \
  -d @myjob.json

JOB-ID 随即返回。输出示例：（作业排队）

{
  "entity": {
    "decision_optimization": {
      "input_data": [{
        "id": "diet_food.csv",
        "fields": ["name", "unit_cost", "qmin", "qmax"],
        "values": [["Roasted Chicken", 0.84, 0, 10], ["Spaghetti W/ Sauce", 0.78, 0, 10], ["Tomato,Red,Ripe,Raw", 0.27, 0, 10], ["Apple,Raw,W/Skin", 0.24, 0, 10], ["Grapes", 0.32, 0, 10], ["Chocolate Chip Cookies", 0.03, 0, 10], ["Lowfat Milk", 0.23, 0, 10], ["Raisin Brn", 0.34, 0, 10], ["Hotdog", 0.31, 0, 10]]
      }, {
        "id": "diet_food_nutrients.csv",
        "fields": ["Food", "Calories", "Calcium", "Iron", "Vit_A", "Dietary_Fiber", "Carbohydrates", "Protein"],
        "values": [["Spaghetti W/ Sauce", 358.2, 80.2, 2.3, 3055.2, 11.6, 58.3, 8.2], ["Roasted Chicken", 277.4, 21.9, 1.8, 77.4, 0, 0, 42.2], ["Tomato,Red,Ripe,Raw", 25.8, 6.2, 0.6, 766.3, 1.4, 5.7, 1], ["Apple,Raw,W/Skin", 81.4, 9.7, 0.2, 73.1, 3.7, 21, 0.3], ["Grapes", 15.1, 3.4, 0.1, 24, 0.2, 4.1, 0.2], ["Chocolate Chip Cookies", 78.1, 6.2, 0.4, 101.8, 0, 9.3, 0.9], ["Lowfat Milk", 121.2, 296.7, 0.1, 500.2, 0, 11.7, 8.1], ["Raisin Brn", 115.1, 12.9, 16.8, 1250.2, 4, 27.9, 4], ["Hotdog", 242.1, 23.5, 2.3, 0, 0, 18, 10.4]]
      }, {
        "id": "diet_nutrients.csv",
        "fields": ["name", "qmin", "qmax"],
        "values": [["Calories", 2000, 2500], ["Calcium", 800, 1600], ["Iron", 10, 30], ["Vit_A", 5000, 50000], ["Dietary_Fiber", 25, 100], ["Carbohydrates", 0, 300], ["Protein", 50, 100]]
      }],
      "output_data": [
        {
          "id": ".*\\.csv"
        }
      ],
      "solve_parameters": {
        "oaas.logAttachmentName": "log.txt",
        "oaas.logTailEnabled": "true"
      },
      "status": {
        "state": "queued"
      }
    },
    "deployment": {
      "id": "DEPLOYMENT-ID"
    },
    "platform_job": {
      "job_id": "",
      "run_id": ""
    }
  },
  "metadata": {
    "created_at": "2020-07-17T10:42:42.783Z",
    "id": "JOB-ID",
    "name": "test-job-diet",
    "space_id": "SPACE-ID"
  }
}

您还可以 监视作业状态。请使用 JOB-ID

例如：

curl --location --request GET \
  "https://us-south.ml.cloud.ibm.com/ml/v4/deployment_jobs/JOB-ID-HERE?version=2020-08-01&space_id=SPACE-ID-HERE" \
  -H "Authorization: bearer TOKEN-HERE" \
  -H "Content-Type: application/json"

输出示例（该作业已完成）：

{
  "entity": {
    "decision_optimization": {
      "input_data": [{
        "id": "diet_food.csv",
        "fields": ["name", "unit_cost", "qmin", "qmax"],
        "values": [["Roasted Chicken", 0.84, 0, 10], ["Spaghetti W/ Sauce", 0.78, 0, 10], ["Tomato,Red,Ripe,Raw", 0.27, 0, 10], ["Apple,Raw,W/Skin", 0.24, 0, 10], ["Grapes", 0.32, 0, 10], ["Chocolate Chip Cookies", 0.03, 0, 10], ["Lowfat Milk", 0.23, 0, 10], ["Raisin Brn", 0.34, 0, 10], ["Hotdog", 0.31, 0, 10]]
      }, {
        "id": "diet_food_nutrients.csv",
        "fields": ["Food", "Calories", "Calcium", "Iron", "Vit_A", "Dietary_Fiber", "Carbohydrates", "Protein"],
        "values": [["Spaghetti W/ Sauce", 358.2, 80.2, 2.3, 3055.2, 11.6, 58.3, 8.2], ["Roasted Chicken", 277.4, 21.9, 1.8, 77.4, 0, 0, 42.2], ["Tomato,Red,Ripe,Raw", 25.8, 6.2, 0.6, 766.3, 1.4, 5.7, 1], ["Apple,Raw,W/Skin", 81.4, 9.7, 0.2, 73.1, 3.7, 21, 0.3], ["Grapes", 15.1, 3.4, 0.1, 24, 0.2, 4.1, 0.2], ["Chocolate Chip Cookies", 78.1, 6.2, 0.4, 101.8, 0, 9.3, 0.9], ["Lowfat Milk", 121.2, 296.7, 0.1, 500.2, 0, 11.7, 8.1], ["Raisin Brn", 115.1, 12.9, 16.8, 1250.2, 4, 27.9, 4], ["Hotdog", 242.1, 23.5, 2.3, 0, 0, 18, 10.4]]
      }, {
        "id": "diet_nutrients.csv",
        "fields": ["name", "qmin", "qmax"],
        "values": [["Calories", 2000, 2500], ["Calcium", 800, 1600], ["Iron", 10, 30], ["Vit_A", 5000, 50000], ["Dietary_Fiber", 25, 100], ["Carbohydrates", 0, 300], ["Protein", 50, 100]]
      }],
      "output_data": [{
        "fields": ["Name", "Value"],
        "id": "kpis.csv",
        "values": [["Total Calories", 2000], ["Total Calcium", 800.0000000000001], ["Total Iron", 11.278317739831891], ["Total Vit_A", 8518.432542485823], ["Total Dietary_Fiber", 25], ["Total Carbohydrates", 256.80576358904455], ["Total Protein", 51.17372234135308], ["Minimal cost", 2.690409171696264]]
      }, {
        "fields": ["name", "value"],
        "id": "solution.csv",
        "values": [["Spaghetti W/ Sauce", 2.1551724137931036], ["Chocolate Chip Cookies", 10], ["Lowfat Milk", 1.8311671008899097], ["Hotdog", 0.9296975991385925]]
      }],
      "output_data_references": [],
      "solve_parameters": {
        "oaas.logAttachmentName": "log.txt",
        "oaas.logTailEnabled": "true"
      },
      "solve_state": {
        "details": {
          "KPI.Minimal cost": "2.690409171696264",
          "KPI.Total Calcium": "800.0000000000001",
          "KPI.Total Calories": "2000.0",
          "KPI.Total Carbohydrates": "256.80576358904455",
          "KPI.Total Dietary_Fiber": "25.0",
          "KPI.Total Iron": "11.278317739831891",
          "KPI.Total Protein": "51.17372234135308",
          "KPI.Total Vit_A": "8518.432542485823",
          "MODEL_DETAIL_BOOLEAN_VARS": "0",
          "MODEL_DETAIL_CONSTRAINTS": "7",
          "MODEL_DETAIL_CONTINUOUS_VARS": "9",
          "MODEL_DETAIL_INTEGER_VARS": "0",
          "MODEL_DETAIL_KPIS": "[\"Total Calories\", \"Total Calcium\", \"Total Iron\", \"Total Vit_A\", \"Total Dietary_Fiber\", \"Total Carbohydrates\", \"Total Protein\", \"Minimal cost\"]",
          "MODEL_DETAIL_NONZEROS": "57",
          "MODEL_DETAIL_TYPE": "LP",
          "PROGRESS_CURRENT_OBJECTIVE": "2.6904091716962637"
        },
        "latest_engine_activity": [
          "[2020-07-21T16:37:36Z, INFO] Model: diet",
          "[2020-07-21T16:37:36Z, INFO]  - number of variables: 9",
          "[2020-07-21T16:37:36Z, INFO]    - binary=0, integer=0, continuous=9",
          "[2020-07-21T16:37:36Z, INFO]  - number of constraints: 7",
          "[2020-07-21T16:37:36Z, INFO]    - linear=7",
          "[2020-07-21T16:37:36Z, INFO]  - parameters: defaults",
          "[2020-07-21T16:37:36Z, INFO]  - problem type is: LP",
          "[2020-07-21T16:37:36Z, INFO] Warning: Model: \"diet\" is not a MIP problem, progress listeners are disabled",
          "[2020-07-21T16:37:36Z, INFO] objective: 2.690",
          "[2020-07-21T16:37:36Z, INFO]   \"Spaghetti W/ Sauce\"=2.155",
          "[2020-07-21T16:37:36Z, INFO]   \"Chocolate Chip Cookies\"=10.000",
          "[2020-07-21T16:37:36Z, INFO]   \"Lowfat Milk\"=1.831",
          "[2020-07-21T16:37:36Z, INFO]   \"Hotdog\"=0.930",
          "[2020-07-21T16:37:36Z, INFO] solution.csv"
        ],
        "solve_status": "optimal_solution"
      },
      "status": {
        "completed_at": "2020-07-21T16:37:36.989Z",
        "running_at": "2020-07-21T16:37:35.622Z",
        "state": "completed"
      }
    },
    "deployment": {
      "id": "DEPLOYMENT-ID"
    }
  },
  "metadata": {
    "created_at": "2020-07-21T16:37:09.130Z",
    "id": "JOB-ID",
    "modified_at": "2020-07-21T16:37:37.268Z",
    "name": "test-job-diet",
    "space_id": "SPACE-ID"
  }
}

可选: 您可以 删除作业 ，如下所示:

curl --location --request DELETE "https://us-south.ml.cloud.ibm.com/ml/v4/deployment_jobs/JOB-ID-HERE?version=2020-08-01&space_id=SPACE-ID-HERE&hard_delete=true" \
  -H "Authorization: bearer TOKEN-HERE"

如果使用 API 来删除作业，那么它仍会显示在用户界面中。

可选: 您可以 删除部署 ，如下所示:

curl --location --request DELETE "https://us-south.ml.cloud.ibm.com/ml/v4/deployments/DEPLOYMENT-ID-HERE?version=2020-08-01&space_id=SPACE-ID-HERE" \
  -H "Authorization: bearer TOKEN-HERE"

如果使用 API 来删除包含作业的部署，那么这些作业仍会显示在用户界面中的部署空间中。

结果

在部署模型并执行作业后，将以内联方式或者在指定的文件和位置中提供解决方案结果，例如，使用 S3 引用。您可以使用 deployment-ID 发布新作业而无需重新部署模型。