AutoML real-time predictions

Use your ML deployment to generate real-time results returned as JSON in a synchronous manner to predict future outcomes on new data.

Download specification

Generate predictions

Generates predictions in a synchronous request and response.

Facts

Rate limit Special (300 requests per minute)
Categories build

Query Parameters

  • includeNotPredictedReasonboolean

    If true, will include a column with the reason why a prediction was not produced.

  • includeShapboolean

    If true, the shapley values will be included in the response.

  • includeSourceboolean

    If true, the source data will be included in the response

  • indexstring

    The name of the feature in the source data to use as an index in the response data. The column will be included with its original name and values. This is intended to allow the caller to join results with source data.

Path Parameters

  • deploymentIdstring
    Required

    The ID of the ML deployed model that will be employed to produce predictions.

Request Body

application/json

  • application/jsonobject
    Show application/json properties
    • rowsarray of arrays

      The rows of the dataset to produce predictions from.

    • schemaarray of objects

      The schema of the input dataset.

      Show schema properties
      • namestring

        The name of a feature in the dataset.

Responses

200

Stream of combined prediction output returned successfully.

400

application/json

Received a bad argument

  • application/jsonobject
    Show application/json properties
    • errorsarray of objects

401

application/json

Unauthorized

  • application/jsonobject
    Show application/json properties
    • errorsarray of objects

403

application/json

Access forbidden

  • application/jsonobject
    Show application/json properties
    • errorsarray of objects

404

application/json

Resource not found.

  • application/jsonobject
    Show application/json properties
    • errorsarray of objects

409

application/json

Resource conflict

  • application/jsonobject
    Show application/json properties
    • errorsarray of objects

503

application/json

Resource unavailable

  • application/jsonobject
    Show application/json properties
    • errorsarray of objects
POST /v1/automl-deployments/{deploymentId}/realtime-predictions
curl "https://your-tenant.us.qlikcloud.com/api/v1/automl-deployments/{deploymentId}/realtime-predictions" \
-X POST \
-H "Content-type: application/json" \
-H "Authorization: Bearer <API-key>" \
-d '{"rows":[["string"]],"schema":[{"name":"string"}]}'
const https = require('https')
  const data = JSON.stringify({"rows":[["string"]],"schema":[{"name":"string"}]})
  const options =   {
    'hostname': 'https://your-tenant.us.qlikcloud.com',
    'port': 443,
    'path': '/api/v1/automl-deployments/{deploymentId}/realtime-predictions',
    'method': 'POST',
    'headers': {
      'Content-type': 'application/json',
      'Authorization': 'Bearer <API-key>'
    }
  }
  const req = https.request(options)
  req.write(data)
  
This API is not included yet in qlik-cli

Request

{
  "rows": [
    [
      "string"
    ]
  ],
  "schema": [
    {
      "name": "string"
    }
  ]
}