NLMetricRecord
Properties
| Name | Description | Type |
|---|---|---|
| id |
Unique record id stored in database |
String (uuid) |
| createdBy |
Qlik sense user id who is interacting with insight advisor or insight advisor chat or third party api |
String |
| createdAt |
Record created date |
Date |
| updatedAt |
Record modified date |
Date |
| tenantId |
Qlik sense tenant Id |
String (uuid) |
| questionId |
Unique id assigned to user query |
String |
| queryText |
Query asked by user in insight advisor or insight advisor or third party api |
String |
| queryType |
Nature of query being asked during the conversation e.g. query, applist, measurelist, dimensionlist
One of:
|
String |
| channelId |
Source from which conversation is happening |
String |
| appId |
Qlik sense app id that is being used to answer the question |
String (uuid) |
| appName |
Qlik sense app name that is being used to answer the question |
String |
| lang |
language selected for query from insight advisor or insight advisor chat or third party api |
String |
| isContextualQuery |
Boolean value indicates whether given query is contextual or not. It would be false for insight advisor |
Boolean |
| queryOrigin |
Refers to source from where narrative request is called
One of:
|
String |
| stopWords |
Tokens from question parsed which are ignored |
Array of String |
| unmatchedEntities |
Tokens parsed as entities but not matched with app's field/dimension/measure |
Array of String |
| nluInfo | Array of PartialNluInfo | |
| recommendations | Array of NLMetricRecommendation | |
| apps | Array of AppMetadata | |
| responses |
Provides info what was included in response for given query |
NLResponses |
| chartType |
Chart type for given query. For insight advisor it would be 'native' and for insight advisor chat, it could be 'static' or 'responsive' |
String |
| queryError | Boolean | |
| feedback | Array of RecFeedback | |
| version |
Version of the metric model |
String |
Did this page help you?
If you find any issues with this page or its content – a typo, a missing step, or a technical error – let us know how we can improve!