Datasets

Get all datasets

/api/v1/datasets

Permissions required: View labels

• Bash

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

• Node

  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))

• Response

  {
    "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"
  }

Get datasets by project

/api/v1/datasets/<project>

Permissions required: View labels

Get a dataset by name

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

Permissions required: View labels

• Bash

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

• Node

  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))

• Response

  {
    "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"
  }

Get model tags for a dataset

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

Permissions required: Model Admin

• Bash

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

• Node

  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))

• Response

  {
    "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"
  }

Create a dataset

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

Permissions required: Datasets admin

• Bash

  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"
    }
  }'

• Node

  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))

• Response

  {
    "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"
  }

NAME	TYPE	REQUIRED	DESCRIPTION
title	string	no	One-line human-readable title for the dataset.
description	string	no	A longer description of the dataset.
source_ids	array<string>	no	An array of source ids to be included in this dataset.
model_family	string	no	Dataset model family, can be english or multilingual. Defaults to english. See here the languages that are supported by multilingual model family.
has_sentiment	boolean	no	Whether labels in the dataset should be applied with sentiment. Defaults to true.

Update a dataset

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

Permissions required: Datasets admin

• Bash

  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"
    }
  }'

• Node

  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))

• Response

  {
    "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"
  }

NAME	TYPE	REQUIRED	DESCRIPTION
title	string	no	One-line human-readable title for the dataset.
description	string	no	A longer description of the dataset.
source_ids	array<string>	no	An array of source ids to be included in this dataset.

Delete a dataset

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

Permissions required: Datasets admin

• Bash

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

• Node

  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))

• Response

  {
    "status": "ok"
  }

Export a dataset

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

Permissions required: Export datasets

• Bash

  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
  }'

• Node

  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))

• Response

  {
    "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": "[e-mail]",
              "sent_at": "2011-12-11T11:05:10Z",
              "subject": {
                "text": "Today's figures"
              },
              "to": ["[e-mail]"]
            }
          ],
          "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, see the comparison table.

Request Format

NAME	TYPE	REQUIRED	DESCRIPTION
comment_uids	array<string>	no	A list of at most 256 comment UIDs (in the format of source_id.comment_id). If provided, only these comments will be included in the response. No other filters may be passed with comment_uids.
source_ids	array<string>	no	A list of at most 1024 source IDs. If provided, only comments from these sources will be included in the response.
order_by	string	no	One of created_at or timestamp. If provided returns the comments sorted by either the API creation date of the comments (created_at), or the user defined comment timestamp (timestamp). The default is timestamp.
from	string	no	An ISO-8601 timestamp. If provided, returns comments only from this timestamp onwards. The related order_by field controls which timestamp will be used for filtering.
to	string	no	An ISO-8601 timestamp. If provided, returns comments only until this timestamp (inclusive). The related order_by field controls which timestamp will be used for filtering.
continuation	string	no	Pagination token (provided in the response). Should be used to fetch the next limit number of comments.
limit	number	no	Number of comments returned per response up to a maximum of 256. Default: 64.

Response Format

NAME	TYPE	DESCRIPTION
comments	array<Comment>	A list of comments with their assigned and predicted labels.
continuation	string	Pagination token to fetch the next limit number of comments. If there are no further comments, this field will not be present in the response.

Where Comment has the following format:

NAME	TYPE	DESCRIPTION
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.