Create entities

This page describes how to create individual entities and multiple entities at the same time using the Management API.

For more information about the Entity Detection feature, see Entity Detection.

Entity Detection - Management API

This section provides basic examples of how to create an entity and how to create multiple entities at one time using the Management API.

Authentication

These requests require an access token, as described in Authenticate.

Create an entity

To create a custom entity, use the POST <https://api.symbl.ai/v1/manage/entities> operation.

import fetch from 'node-fetch';

const accessToken = '<ACCESS_TOKEN>';
const entityParams = {
  'type': '<TYPE>',
  'subType': '<SUBTYPE>',
  'category': 'Custom',
  'values': [
    '<ENTITY_VOCAB>',
    '<ENTITY_VOCAB>',
    ...
  ]
}

const fetchResponse = await fetch('https://api.symbl.ai/v1/manage/entities', {
  method: 'post',
  body: JSON.stringify(entityParams),
  headers: {
    'Authorization': `Bearer ${accessToken}`,
    'Content-Type': 'application/json'
  }
});

const responseBody = await fetchResponse.json();

console.log(responseBody);

Where:

• <ACCESS_TOKEN> is a valid API access token.
• <TYPE> describes the type of entity. For example, Vehicle. You can have multiple entities of the same type.
• <SUBTYPE> describes a subset of the entity. For example, TeslaModel. Subtypes must be unique for each type of entity. For example, there may be only one TeslaModel subtype for the Vehicle type.
• <ENTITY_VOCAB> is a string to match in a conversation. The vocabulary you provide only returns entities if the string exactly matches a word or phrase in a conversation. For example, ["Model X", "Model S", "Model 3", "Model Y"].

For additional details about the request body parameters for this request, see Request body parameters.

Create multiple entities

To create multiple custom entities at the same time, use the POST htt://api.symbl.ai/v1/manage/entities/bulk operation.

import fetch from 'node-fetch';

const accessToken = '<ACCESS_TOKEN>';
const entities = [
  {
    'type': '<TYPE>',
    'subType': '<SUBTYPE>',
    'category': 'Custom',
    'values': [
      '<ENTITY_VOCAB>',
      '<ENTITY_VOCAB>',
      ...
    ]
  },
  {
    'type': '<TYPE>',
    'subType': '<SUBTYPE>',
    'category': 'Custom',
    'values': [
      '<ENTITY_VOCAB>',
      '<ENTITY_VOCAB>',
      ...
    ]
  },
  ...
]

const fetchResponse = await fetch('https://api.symbl.ai/v1/manage/entities/bulk', {
  method: 'post',
  body: JSON.stringify(entities),
  headers: {
    'Authorization': `Bearer ${accessToken}`,
    'Content-Type': 'application/json'
  }
});

const responseBody = await fetchResponse.json();

console.log(responseBody);

Where:

• <ACCESS_TOKEN> is a valid API access token.
• <TYPE> describes the type of entity. For example, Vehicle. You can have multiple entities of the same type.
• <SUBTYPE> describes a subset of the entity. For example, TeslaModel. Subtypes must be unique for each type of entity. For example, there may be only one TeslaModel subtype for the Vehicle type.
• <ENTITY_VOCAB> is a string to match in a conversation. The vocabulary you provide only returns entities if the string exactly matches a word or phrase in a conversation. For example, ["Model X", "Model S", "Model 3", "Model Y"].

For additional details about the request body parameters for this request, see Request body parameters.

Request body parameters

The following table describes the body parameters that can be used with this request.

Response

The following table describes the response body that is returned by this request.

Example response for an entity

{
  "id": "4476908732794496",
  "type": "Vehicle",
  "subType": "TeslaModel",
  "category": "Custom",
  "values": [
    "Model X",
    "Model S",
    "Model 3",
    "Model Y"
  ]
}

Example response for multiple entities

{
  "entities": [
    {
      "id": "4476908732794496",
      "type": "Vehicle",
      "subType": "TeslaModel",
      "category": "Custom",
      "values": [
        "Model X",
        "Model S",
        "Model 3",
        "Model Y"
      ]
    },
    {
      "id": "3242908732344496",
      "type": "Vehicle",
      "subType": "TeslaTruck",
      "category": "Custom",
      "values": [
        "Cyber truck",
        "Semi truck"
      ]
    }
  ]
}