POST
/
v4
/
training-datasets
JavaScript
import SGPClient from 'sgp';

const client = new SGPClient({
  apiKey: 'My API Key',
});

const trainingDataset = await client.trainingDatasets.create({
  account_id: 'account_id',
  file: fs.createReadStream('path/to/file'),
  name: 'name',
  schema_type: 'GENERATION',
});

console.log(trainingDataset.id);
{
  "name": "<string>",
  "schema_type": "GENERATION",
  "data_source": "S3",
  "id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "account_id": "<string>",
  "created_by_user_id": "<string>",
  "created_by_identity_type": "user"
}

Authorizations

x-api-key
string
header
required

Body

multipart/form-data
account_id
string
required

The ID of the account that owns the given entity.

name
string
required

The name of the dataset

schema_type
enum<string>
required

The schema type of the dataset, currently only GENERATION is supported

Available options:
GENERATION,
RERANKING_QUESTIONS
file
file
required

The file to upload as the training dataset

Response

Successful Response

name
string
required

The name of the dataset

schema_type
enum<string>
required

The schema type of the dataset, currently only GENERATION is supported

Available options:
GENERATION,
RERANKING_QUESTIONS
data_source
enum<string>
required

The data source of the dataset, used to determine how to parse the location

Available options:
S3,
SharePoint,
LocalFile,
LocalChunks,
GoogleDrive,
AzureBlobStorage,
Confluence,
Slack
id
string
required

The unique identifier of the entity.

created_at
string<date-time>
required

The date and time when the entity was created in ISO format.

account_id
string
required

The ID of the account that owns the given entity.

created_by_user_id
string
required

The user who originally created the entity.

created_by_identity_type
enum<string>
required

The type of identity that created the entity.

Available options:
user,
service_account