ixp

latest

false

Communications Mining 用户指南

上次更新日期 2025年8月11日

数据集

获取所有数据集

/api/v1/datasets

所需权限：查看标签

重击
```
curl -X GET 'https://<my_api_endpoint>/api/v1/datasets' \
    -H "Authorization: Bearer $REINFER_TOKEN"curl -X GET 'https://<my_api_endpoint>/api/v1/datasets' \
    -H "Authorization: Bearer $REINFER_TOKEN"
```

节点

const request = require("request");

request.get(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);const request = require("request");

request.get(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);

Python

import json
import os

import requests

response = requests.get(
    "https://<my_api_endpoint>/api/v1/datasets",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))import json
import os

import requests

response = requests.get(
    "https://<my_api_endpoint>/api/v1/datasets",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))

响应

{
  "datasets": [
    {
      "created": "2018-10-15T15:48:49.603000Z",
      "description": "An optional long form description.",
      "has_sentiment": true,
      "id": "18ba5ce699f8da1f",
      "last_modified": "2018-10-15T15:48:49.603000Z",
      "model_family": "english",
      "name": "example",
      "owner": "<project>",
      "source_ids": ["18ba5ce699f8da1f"],
      "title": "An Example Dataset"
    }
  ],
  "status": "ok"
}{
  "datasets": [
    {
      "created": "2018-10-15T15:48:49.603000Z",
      "description": "An optional long form description.",
      "has_sentiment": true,
      "id": "18ba5ce699f8da1f",
      "last_modified": "2018-10-15T15:48:49.603000Z",
      "model_family": "english",
      "name": "example",
      "owner": "<project>",
      "source_ids": ["18ba5ce699f8da1f"],
      "title": "An Example Dataset"
    }
  ],
  "status": "ok"
}

按项目获取数据集

/api/v1/datasets/<project>

所需权限：查看标签

按名称获取数据集

/api/v1/datasets/<project>/<dataset_name>

所需权限：查看标签

重击

curl -X GET 'https://<my_api_endpoint>/api/v1/datasets/<project>/example' \
    -H "Authorization: Bearer $REINFER_TOKEN"curl -X GET 'https://<my_api_endpoint>/api/v1/datasets/<project>/example' \
    -H "Authorization: Bearer $REINFER_TOKEN"

节点

const request = require("request");

request.get(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);const request = require("request");

request.get(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);

Python

import json
import os

import requests

response = requests.get(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))import json
import os

import requests

response = requests.get(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))

响应

{
  "dataset": {
    "created": "2018-10-15T15:48:49.603000Z",
    "description": "An optional long form description.",
    "has_sentiment": true,
    "id": "18ba5ce699f8da1f",
    "last_modified": "2018-10-15T15:48:49.603000Z",
    "model_family": "english",
    "name": "example",
    "owner": "<project>",
    "source_ids": ["18ba5ce699f8da1f"],
    "title": "An Example Dataset"
  },
  "status": "ok"
}{
  "dataset": {
    "created": "2018-10-15T15:48:49.603000Z",
    "description": "An optional long form description.",
    "has_sentiment": true,
    "id": "18ba5ce699f8da1f",
    "last_modified": "2018-10-15T15:48:49.603000Z",
    "model_family": "english",
    "name": "example",
    "owner": "<project>",
    "source_ids": ["18ba5ce699f8da1f"],
    "title": "An Example Dataset"
  },
  "status": "ok"
}

获取数据集的模型标签

/api/v1/datasets/<project>/<dataset>/model-tags

所需权限：模型管理员

重击

curl -X GET 'https://<my_api_endpoint>/api/v1/datasets/<project>/model-tags' \
    -H "Authorization: Bearer $REINFER_TOKEN"curl -X GET 'https://<my_api_endpoint>/api/v1/datasets/<project>/model-tags' \
    -H "Authorization: Bearer $REINFER_TOKEN"

节点

const request = require("request");

request.get(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/model-tags",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);const request = require("request");

request.get(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/model-tags",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);

Python

import json
import os

import requests

response = requests.get(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/model-tags",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))import json
import os

import requests

response = requests.get(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/model-tags",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))

响应

{
  "model_tags": [
    {
      "name": "prod",
      "updated_at": "2021-11-16T12:31:00.123Z",
      "version": 5
    },
    {
      "name": "staging",
      "updated_at": "2021-11-15T12:30:00.123Z",
      "version": 7
    }
  ],
  "status": "ok"
}{
  "model_tags": [
    {
      "name": "prod",
      "updated_at": "2021-11-16T12:31:00.123Z",
      "version": 5
    },
    {
      "name": "staging",
      "updated_at": "2021-11-15T12:30:00.123Z",
      "version": 7
    }
  ],
  "status": "ok"
}

创建数据集

/api/v1/datasets/<project>/<dataset>

所需权限：修改数据集

重击

curl -X PUT 'https://<my_api_endpoint>/api/v1/datasets/<project>/example' \
    -H "Authorization: Bearer $REINFER_TOKEN" \
    -H "Content-Type: application/json" \
    -d '{
  "dataset": {
    "description": "An optional long form description.",
    "model_family": "english",
    "source_ids": [
      "18ba5ce699f8da1f"
    ],
    "title": "An Example Dataset"
  }
}'curl -X PUT 'https://<my_api_endpoint>/api/v1/datasets/<project>/example' \
    -H "Authorization: Bearer $REINFER_TOKEN" \
    -H "Content-Type: application/json" \
    -d '{
  "dataset": {
    "description": "An optional long form description.",
    "model_family": "english",
    "source_ids": [
      "18ba5ce699f8da1f"
    ],
    "title": "An Example Dataset"
  }
}'

节点

const request = require("request");

request.put(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
    json: true,
    body: {
      dataset: {
        description: "An optional long form description.",
        model_family: "english",
        source_ids: ["18ba5ce699f8da1f"],
        title: "An Example Dataset",
      },
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);const request = require("request");

request.put(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
    json: true,
    body: {
      dataset: {
        description: "An optional long form description.",
        model_family: "english",
        source_ids: ["18ba5ce699f8da1f"],
        title: "An Example Dataset",
      },
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);

Python

import json
import os

import requests

response = requests.put(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
    json={
        "dataset": {
            "title": "An Example Dataset",
            "description": "An optional long form description.",
            "source_ids": ["18ba5ce699f8da1f"],
            "model_family": "english",
        }
    },
)

print(json.dumps(response.json(), indent=2, sort_keys=True))import json
import os

import requests

response = requests.put(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
    json={
        "dataset": {
            "title": "An Example Dataset",
            "description": "An optional long form description.",
            "source_ids": ["18ba5ce699f8da1f"],
            "model_family": "english",
        }
    },
)

print(json.dumps(response.json(), indent=2, sort_keys=True))

响应

{
  "dataset": {
    "created": "2018-10-15T15:48:49.603000Z",
    "description": "An optional long form description.",
    "has_sentiment": true,
    "id": "b9a1fd75f6133bce",
    "last_modified": "2018-10-15T15:48:49.603000Z",
    "model_family": "english",
    "name": "example",
    "owner": "<project>",
    "source_ids": ["18ba5ce699f8da1f"],
    "title": "An Example Dataset"
  },
  "status": "ok"
}{
  "dataset": {
    "created": "2018-10-15T15:48:49.603000Z",
    "description": "An optional long form description.",
    "has_sentiment": true,
    "id": "b9a1fd75f6133bce",
    "last_modified": "2018-10-15T15:48:49.603000Z",
    "model_family": "english",
    "name": "example",
    "owner": "<project>",
    "source_ids": ["18ba5ce699f8da1f"],
    "title": "An Example Dataset"
  },
  "status": "ok"
}

名称	类型	必填	说明
`title`	字符串	否	数据集的单行人类可读标题。
`description`	字符串	否	数据集的详细说明。
`source_ids`	array<string>	否	要包含在此数据集中的源 ID 数组。
`model_family`	字符串	否	数据集模型系列，可以是English或多语言。默认为English 。要查看多语言模型系列支持的语言，请访问多语言来源和数据集。
`has_sentiment`	boolean	否	数据集中的标签是否应与情感一起应用。默认为true 。

更新数据集

/api/v1/datasets/<project>/<dataset>

所需权限： Datasets admin

重击

curl -X POST 'https://<my_api_endpoint>/api/v1/datasets/<project>/example' \
    -H "Authorization: Bearer $REINFER_TOKEN" \
    -H "Content-Type: application/json" \
    -d '{
  "dataset": {
    "title": "An Alternative Title"
  }
}'curl -X POST 'https://<my_api_endpoint>/api/v1/datasets/<project>/example' \
    -H "Authorization: Bearer $REINFER_TOKEN" \
    -H "Content-Type: application/json" \
    -d '{
  "dataset": {
    "title": "An Alternative Title"
  }
}'

节点

const request = require("request");

request.post(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
    json: true,
    body: { dataset: { title: "An Alternative Title" } },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);const request = require("request");

request.post(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
    json: true,
    body: { dataset: { title: "An Alternative Title" } },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);

Python

import json
import os

import requests

response = requests.post(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
    json={"dataset": {"title": "An Alternative Title"}},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))import json
import os

import requests

response = requests.post(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
    json={"dataset": {"title": "An Alternative Title"}},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))

响应

{
  "dataset": {
    "created": "2018-10-15T15:48:49.603000Z",
    "description": "An optional long form description.",
    "has_sentiment": true,
    "id": "b9a1fd75f6133bce",
    "last_modified": "2018-10-15T15:53:08.479000Z",
    "model_family": "english",
    "name": "example",
    "owner": "<project>",
    "source_ids": ["18ba5ce699f8da1f"],
    "title": "An Alternative Title"
  },
  "status": "ok"
}{
  "dataset": {
    "created": "2018-10-15T15:48:49.603000Z",
    "description": "An optional long form description.",
    "has_sentiment": true,
    "id": "b9a1fd75f6133bce",
    "last_modified": "2018-10-15T15:53:08.479000Z",
    "model_family": "english",
    "name": "example",
    "owner": "<project>",
    "source_ids": ["18ba5ce699f8da1f"],
    "title": "An Alternative Title"
  },
  "status": "ok"
}

名称	类型	必填	说明
`title`	字符串	否	数据集的单行人类可读标题。
`description`	字符串	否	数据集的详细说明。
`source_ids`	array<string>	否	要包含在此数据集中的源 ID 数组。

删除数据集

/api/v1/datasets/<project>/<dataset_name>

所需权限： Datasets admin

重击

curl -X DELETE 'https://<my_api_endpoint>/api/v1/datasets/<project>/example' \
    -H "Authorization: Bearer $REINFER_TOKEN"curl -X DELETE 'https://<my_api_endpoint>/api/v1/datasets/<project>/example' \
    -H "Authorization: Bearer $REINFER_TOKEN"

节点

const request = require("request");

request.delete(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);const request = require("request");

request.delete(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);

Python

import json
import os

import requests

response = requests.delete(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))import json
import os

import requests

response = requests.delete(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))

响应

{
  "status": "ok"
}{
  "status": "ok"
}

导出数据集

/api/v1/datasets/<project>/<dataset_name>/export

所需权限：导出数据集

重击

curl -X POST 'https://<my_api_endpoint>/api/v1/datasets/<project>/example/export' \
    -H "Authorization: Bearer $REINFER_TOKEN" \
    -H "Content-Type: application/json" \
    -d '{
  "limit": 1
}'curl -X POST 'https://<my_api_endpoint>/api/v1/datasets/<project>/example/export' \
    -H "Authorization: Bearer $REINFER_TOKEN" \
    -H "Content-Type: application/json" \
    -d '{
  "limit": 1
}'

节点

const request = require("request");

request.post(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example/export",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
    json: true,
    body: { limit: 1 },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);const request = require("request");

request.post(
  {
    url: "https://<my_api_endpoint>/api/v1/datasets/<project>/example/export",
    headers: {
      Authorization: "Bearer " + process.env.REINFER_TOKEN,
    },
    json: true,
    body: { limit: 1 },
  },
  function (error, response, json) {
    // digest response
    console.log(JSON.stringify(json, null, 2));
  }
);

Python

import json
import os

import requests

response = requests.post(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example/export",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
    json={"limit": 1},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))import json
import os

import requests

response = requests.post(
    "https://<my_api_endpoint>/api/v1/datasets/<project>/example/export",
    headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
    json={"limit": 1},
)

print(json.dumps(response.json(), indent=2, sort_keys=True))

响应

{
  "comments": [
    {
      "annotations": {
        "labels": {
          "assigned": [
            {
              "name": "Parent Label",
              "sentiment": "positive"
            },
            {
              "name": "Parent Label > Child Label",
              "sentiment": "positive"
            }
          ]
        }
      },
      "comment": {
        "context": "1596721237668",
        "created_at": "2020-08-06T13:20:28.531000Z",
        "has_annotations": true,
        "id": "0123456789abcdef",
        "last_modified": "2020-08-06T13:40:37.668000Z",
        "messages": [
          {
            "body": {
              "text": "Alice,\n\nHere are the figures for today.\n\nRegards,\nBob"
            },
            "from": "bob@organisation.org",
            "sent_at": "2011-12-11T11:05:10Z",
            "subject": {
              "text": "Today's figures"
            },
            "to": ["alice@company.com"]
          }
        ],
        "source_id": "47194279497e141e",
        "text_format": "plain",
        "thread_id": "123456",
        "timestamp": "2011-12-11T11:05:10Z",
        "uid": "47194279497e141e.0123456789abcdef",
        "user_properties": {
          "string:Recipient Domain": "company.com",
          "string:Sender Domain": "organisation.org"
        }
      },
      "predictions": {
        "labels": [
          {
            "name": "Another Parent Label",
            "probability": 0.954979807138443,
            "sentiment": -0.4281917143125379
          },
          {
            "name": "Another Parent Label > Another Child Label",
            "probability": 0.7726812064647675,
            "sentiment": -0.6603664430231163
          }
        ]
      }
    }
  ],
  "continuation": "2021-02-16T10:55:05Z.c060a787c0b2bbf95526ad5cf28bf582",
  "status": "ok"
}{
  "comments": [
    {
      "annotations": {
        "labels": {
          "assigned": [
            {
              "name": "Parent Label",
              "sentiment": "positive"
            },
            {
              "name": "Parent Label > Child Label",
              "sentiment": "positive"
            }
          ]
        }
      },
      "comment": {
        "context": "1596721237668",
        "created_at": "2020-08-06T13:20:28.531000Z",
        "has_annotations": true,
        "id": "0123456789abcdef",
        "last_modified": "2020-08-06T13:40:37.668000Z",
        "messages": [
          {
            "body": {
              "text": "Alice,\n\nHere are the figures for today.\n\nRegards,\nBob"
            },
            "from": "bob@organisation.org",
            "sent_at": "2011-12-11T11:05:10Z",
            "subject": {
              "text": "Today's figures"
            },
            "to": ["alice@company.com"]
          }
        ],
        "source_id": "47194279497e141e",
        "text_format": "plain",
        "thread_id": "123456",
        "timestamp": "2011-12-11T11:05:10Z",
        "uid": "47194279497e141e.0123456789abcdef",
        "user_properties": {
          "string:Recipient Domain": "company.com",
          "string:Sender Domain": "organisation.org"
        }
      },
      "predictions": {
        "labels": [
          {
            "name": "Another Parent Label",
            "probability": 0.954979807138443,
            "sentiment": -0.4281917143125379
          },
          {
            "name": "Another Parent Label > Another Child Label",
            "probability": 0.7726812064647675,
            "sentiment": -0.6603664430231163
          }
        ]
      }
    }
  ],
  "continuation": "2021-02-16T10:55:05Z.c060a787c0b2bbf95526ad5cf28bf582",
  "status": "ok"
}

This route lets you export a dataset. It returns a list of comments with assigned labels and latest available predictions. Other ways to export a dataset are CSV download in the browser and JSONL download via the CLI. For a detailed comparison, check the comparison table.

请求格式

名称	类型	必填	说明
`comment_uids`	array<string>	否	至多包含 256 个注释 UID 的列表 (格式为 source_id.comment_id)。如果提供，则响应中将仅包含这些注释。不能使用`comment_uids`传递其他筛选条件。
`source_ids`	array<string>	否	至多包含 1024 个来源 ID 的列表。如果提供，则响应中将仅包含这些来源的注释。
`order_by`	字符串	否	`created_at`或`timestamp`之一。如果提供，则返回按注释的 API 创建日期 ( `created_at` ) 或用户定义的注释时间戳 ( `timestamp` ) 排序的注释。默认值为`timestamp` 。
`from`	字符串	否	ISO-8601 时间戳。如果提供，则仅返回此时间戳之后的注释。相关的`order_by`字段控制将用于筛选的时间戳。
`to`	字符串	否	ISO-8601 时间戳。如果提供，则仅返回此时间戳 (含) 之前的注释。相关的`order_by`字段控制将用于筛选的时间戳。
`continuation`	字符串	否	分页令牌（在响应中提供）。应该用于获取接下来的`limit`条注释。
`limit`	数字	否	每个响应返回的注释数，最大值为 256。默认值: 64。

响应格式

名称	类型	说明
`comments`	array<Comment>	注释列表，其中包含分配的标签和预测的标签。
`continuation`	字符串	用于获取接下来`limit`条注释的分页令牌。如果没有进一步的注释，则响应中将不会显示此字段。

其中Comment具有以下格式：

名称	类型	说明
`comment`	object	Comment object. The format is described in the Comment Reference.
`annotations`	object	An object containing a single field `labels.assigned` which is a list of labels assigned to this comment. The format is described in the Labels Reference. Note that it won't include predictions as these labels are assigned, not predicted.
`predictions`	object	An object containing a single field `labels` which is a list of labels predicted for this comment. The format is described in the Labels Reference.