Configuration Guide

Revision Date:  05 December, 2022

This documentation has been created for software version 2022.4.0.0.

It is also valid for subsequent software versions as long as no new document version is shipped with the product.

Suite 105, 220 Davidson Ave, Somerset, NJ, USA 08873

Support: 

For more information, visit

https://www.whiz.ai/contact

Copyright © 2022 whiz.ai All Rights Reserved.

Trademarks owned by whiz.ai

Disclaimer

No Warranties and Limitation of Liability

Every effort has been made to ensure that this document is an accurate representation of the steps to deploy WHIZ.AI platform. However, the development of the software is a continuous process. So, small inconsistencies may occur. 

We would appreciate any feedback on this document 

Send comments via email 

To: assistant@whiz.ai 

Table of Contents

Introduction. 

Preface. 

About this Configuration Guide. 

Intended Audience. 

Related Documents. 

Contacting WhizAI 

Getting Started. 

Pre-requisites. 

Configurations in WhizAI 

Model Management Configurations. 

Configuring hierarchies for Info modal 

Configuring default time operator for Growing/Declining queries. 

Configuring Top N Additional Metadata. 

Configuring Top N threshold. 

Hiding metric for Top N response. 

Configuring cacheable/non-cacheable entities. 

Data Modeler - Moving existing Airflow driven solution pipeline configurations to Data Modeler UI solution. 

Visualization Configurations. 

Configuring the Title of the Response. 

Configuring timeline visualization for multidimensional query. 

Chart and Table Responses: Add hyperlinks to data values. 

Enabling Map Visualization. 

Configuring to Hide/show "Partial Data" bubble in visualization, table, and reports. 

Configuring action fields (Editable Columns) 

Configuring Smart Totals. 

Configuring Anomalies and Key Drivers Analysis. 

Configuring new layout for pinboards from User Interface. 

Natural Language Generation (NLG) Configurations. 

Configuring sample NLQs by languages. 

Introduction

WhizAI is the first and only purpose-built cognitive insights platform for life sciences, empowering users to get answers to their business questions by simply asking via voice, text on web and mobile. 

WhizAI is trained on the language and data of life sciences, enabling it to answer even the most complex questions from billions of records in seconds. Fast, easy and scalable, WhizAI is the trusted partner of choice at the top global life sciences companies. Asked. Answered. Instantly. 

Learn more at https://whiz.ai/        

Preface

About this Configuration Guide

This configuration guide details the prerequisites, configuration, and operation that you must perform while configuring the WhizAI application.

Intended Audience

This guide is intended for the customer’s IT team, WhizAI partners and development team seeking information on the different steps in the WhizAI configuration process.

Related Documents

Along with this configuration guide, you can refer to the WhizAI User Manual to know how to access WhizAI and its different features.

Contacting WhizAI

For any support, you can reach WhizAI support team through our:

• Website: https://whiz.ai
• Email: mailto:assistant@whiz.ai

Getting Started

This section describes how to perform configurations for the WhizAI application. To perform these configurations, you must ensure that the application service database or ZooKeeper is set up on your machine. A database is an organized collection of data where you can manage and store your data from a WhizAI application. Also, ZooKeeper is a centralized service for maintaining configuration information, naming, providing distributed synchronization, and providing group services.

For example, PostgreSQL is a relational database that stores data points in rows, with columns as different data attributes. Also, a table stores multiple related rows. It supports both SQL and JSON format. 

Pre-requisites

Before you begin configuring the WhizAI application, you need to ensure that you meet the following prerequisites to be installed on your machine:

Configurations in WhizAI

This guide will help you get started with configuring WhizAI application. This configuration guide explains the basic steps to perform while configuring the WhizAI application.

The configurations are divided into the following areas:

• Model Management Configurations
• Visualization Configurations
• Natural Language Generation (NLG) Configurations

Model Management Configurations

Configuring hierarchies for Info modal

Description

Using this configuration, you can add hierarchies to

• Info page: This info page can be accessed by clicking ‘Info’ from the Conversation box in WhizAI Explorer.
• Add Filters dialog for pinboards and cards and all the filters on a pinboard

The Info page lists the hierarchies, whereas, the Add Filters dialog and the filters on a pinboard shows the list of dimensions in the hierarchy. 

Procedure

To perform this configuration, you must add the following details to the application service database.

Adding configuration to Info page:

To add the configuration for Info page, go to application service database > hierarchy_info table.

Add details as shown in the following table:

 After this configuration is added, you can see the hierarchies on the Info page.

Adding configuration to Add Filters dialog, and the filters on a pinboard: 

To add the configuration to Add Filters dialog, and the filters on a pinboard, go to application service database > entity_hierarchy table.

Add details as shown in the following table:

After this configuration is added, you can see the list of dimensions in hierarchies.

Result

After you add the hierarchies to the Info page, it is displayed on the User Interface as shown in the following figure.

After you add the hierarchies to the Add Filters dialog and filters on the pinboard, it is displayed on the User Interface as shown in the following figure.

Add filters dialog:

Filters on pinboard:

Configuring default time operator for Growing/Declining queries.

Description

For growing/declining query, you can change the default behavior of the default time period which helps to calculate the growth. Suppose the default time behavior is Period over Period (PoP), and if you want to change it to Year over Year (YoY) then you can use this configuration.

Procedure

To perform this configuration, you must add configuration details to the application service database.

For example, if you ask WhizAI ‘Show me growing Region’, for which a default time behavior is Period over Period (PoP).

Now, you can change the default time behavior from Period over Period (PoP) to Year over Year (YoY).

To perform this configuration, follow the steps listed below: 

2.  In the data_sources table you can see the columns as mentioned in the table below:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

Result

After this configuration is performed, you can see default time behavior is changed to YOY for query ‘Show me growing Region’.

Configuring Top N Additional Metadata

Description

Using this configuration, you can enable the visualization for additional dimensions for higher levels of hierarchy in a Top N query.

Procedure

To perform this configuration, you must add the configuration details to the application service database.

For example, for dimension ‘Account’ you can add the additional dimension ‘Territory’ so that you can get an aggregate account territory information.

To perform this configuration, follow the steps listed below:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

The below table provides description for the key values: 

Result:

After performing this configuration, when you ask WhizAI ‘Show me Top accounts’, the response table displays the additional dimension territory as shown in the following figure:

Configuring Top N threshold

Description

Using this configuration, you can set out the default number of records on the response. Therefore, when you ask a query, WhizAI understands, and shows you the default number of records. 

Procedure

To perform this configuration, you must add configuration details to the application service database.

For example, if you set the property "default_threshold": 20, and ask a query such as ‘Show me top Customers’ then WhizAI understands by default and shows the list of top 20 customers

To perform this configuration, follow the steps listed below:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

 Result:

After performing this configuration, when you ask WhizAI ‘Show me top 20 customers’ then WhizAI understands by default and shows the list of top 20 customers.

Hiding metric for Top N response 

Description

Using this configuration, you can hide the metrics for the Top N response, when a certain dimension or group of dimensions are part of the response.

Procedure

To perform this configuration, you must add configuration details to the application service database.

For example, if you set the property ‘hide_metric_for_dimensions: [["contract"]]’ and ask a query ‘Show me list of contracts’ the response table will not show the metrics.

To perform this configuration, follow the steps listed below:

OR 

4.  Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

Result:

After performing this configuration, the response table does not display the metrics as show in the following figure:

Configuring cacheable/non-cacheable entities

Description

When you ask a question, WhizAI identifies the context such as metrics and filters from the previously used question. If you do not want the context, then use this configuration to see the result for follow up query. 

Procedure

To perform this configuration, you must add configuration details to the application service database.

For example, if you add the ‘Number of Writers’ metric as a non-cacheable entity, then it will not be set in the context. 

To perform this configuration, follow the below steps:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

Result

After you perform this configuration, it reflects on User Interface as shown in the below figure:

Data Modeler - Moving existing Airflow driven solution pipeline configurations to Data Modeler UI solution

(Configuration introduced in v2022.3.1.2)

Now, you can move existing Airflow driven solution pipeline configurations to Data Modeler and run the pipeline on the UI.

 Prerequisite: Make sure you have WhizDMimport dag available and enabled on the Airflow v2.2.5.

To move existing pipeline configurations:

Go to WhizDMimport dag:

1.  Click Trigger DAG .

After a successful DAG run, all the pipelines will be available on the Modeler UI. You can Edit, Configure, and Run these imported pipelines on the Data Modele UI.

Understanding the WhizDMimport configuration JSON

Following table explains different fields in the WhiDMimport configuration.

Visualization Configurations

Configuring the Title of the Response 

Description

Using this configuration, you can configure the text of a response title, i.e, add or change the words to be displayed in the title. Also, you can configure certain words to be displayed in a supported language within the response title, and so on.

Procedure

To perform this configuration, you must add configuration details to the application service database.

For example, when you ask WhizAI in Spanish language ‘Muéstrame las 10 mejores cuentas’  then it shows the response as shown in the following figure.

Now, for the response in Spanish you can change the word ‘Cima’ (in Spanish) as ‘Top’ (in English):

To perform this configuration, follow the step listed below:

You can enter the required values in the key column to get the appropriate response. The values are as given below:

Result

After applying the configuration, the title is displayed as Top in the response table.

Configuring timeline visualization for multidimensional query

Description:

Using this configuration, you can enable the timeline visualization on pinboards as well as on responses for multidimensional query. 

Procedure

To perform this configuration, you must add configuration details to the application service database.

For example, if you want to add the timeline visualization for dimensions ‘Response date’ and ‘Region’, then you have to add some key values into the data_sources table.

To perform this configuration, follow the steps listed below:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

Now, add the dimensions ‘Response date’ and, ‘Region’ and the given key values as shown in the following Insert statement:

The below table provides description for the key values: 

Result

After performing this configuration, when you ask WhizAI ‘Show me response date by regions’ then in the response you can see the timeline visualization option as shown in the following figure:

Chart and Table Responses: Add hyperlinks to data values

Description

Using this configuration, you can add the hyperlinks on cards associated with the corresponding dimension values. When you click on these links it redirects you to the external tab where you can view the data or image for further analysis.

Procedure:

To perform this configuration, you must add configuration details to the application service database.

For example, if you want to add the hyperlinks for dimensions ‘Region’, then you have to add some key values into the data_sources table.

To perform this configuration, follow the steps listed below:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

Now, add the dimensions ‘Region’ and the given key values as shown in the following Insert statement:

The below table provides description for the key values: 

Result:

After performing this configuration, when you ask WhizAI ‘Show me trx by region’, you see the following response. 

When you hover a cursor over any dimension value it shows the options for ‘View link’ and ‘View image’ as shown in the following image.

Enabling Map Visualization

Description

Using this configuration, you can enable the map visualization for states and countries. 

Procedure

To perform this configuration, you must add configuration details to the application service database.

Follow the steps listed below to enable the map visualization for states and countries.

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

The below table provides description for the key values: 

Result:

After adding this configuration, you can see the map visualization for states and countries.

Map for countries:

Map for states:

Configuring to Hide/show "Partial Data" bubble in visualization, table, and reports

Description

Using this configuration, you can hide or show ‘Partial Data’ text in the visualization.

Procedure

To perform this configuration, follow the steps listed below:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

Result:

After performing this configuration, you can hide/show the Partial data as shown in the following figure:

Configuring action fields (Editable Columns)

Description

Using this configuration, you can configure the certain cards on pinboards, so that they show an actionable metric column. 

Therefore, you can update the actions performed against a particular record from the dropdown lists in this column.

Procedure

To perform this configuration, you must add configuration details to the application service database.

For example, if you want to add actionable columns for the dimensions ‘Customer’, then you have to add some key values into the data_sources table.

To perform this configuration, follow the steps listed below:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

Result:

After performing this configuration when you ask ‘Show me customer by status’ the response table displays the actionable columns as shown in the following figure:

Configuring Smart Totals

Description

Using this configuration, you can configure the totals for computed metrics for all the applicable responses. The totals are calculated based on computational calculations.

For example, if you perform this configuration for computation TRx Marketshare and ask WhizAI ‘Show me region by brand for TRx marketshare’ then in the response table, you will see the total percentage of each brand against all the regions.

Procedure

To perform this configuration, you must add configuration details to the application service database.

To perform this configuration, follow the below steps:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

The below table provides description for the required parameters: 

Result:

After performing this configuration when you ask ‘Show me region by brand for TRx marketshare’ the response table displays the smart total as shown in the following figure:

Configuring Anomalies and Key Drivers Analysis 

(Enabled in v2022.4.0.0)

Description

Using this configuration, you can enable the Anomalies and Key Drivers analysis tabs from Insight Workbench.

The ‘Insight Workbench’ interface has the following two tabs:

Anomalies: Helps identify the anomalous behavior of your business metric.

Key Drivers: Helps find out the top driving factor of your business metric. 

Procedure

You can configure the Anomalies and Key Drivers analysis using the below-mentioned steps:

• Enabling Anomalies and Key Drivers tab 
• Enabling the Contributors tab for Key Drivers Analysis
• Insight Workbench role-based access
• Configuring Anomalies and Key Drivers Analysis from User Interface

Enabling Anomalies and Key Drivers tab 

Using this configuration, you can enable the Anomalies and Key Drivers analysis tab. Also, you can run anomaly detection on a response that shows a trendline with weekly, monthly, quarterly, and yearly data for metrics and scope.

To enable the Anomalies and Key Drivers analysis follow the steps listed below:

OR 

Click the Panels button from the top right corner of the data_sources table. The Value section opens to the right-hand side. 

The below table provides a description for the key values: 

Result:

After performing this configuration, the Anomaly and Key Drivers analysis tabs are displayed on the User Interface as shown in the following figure.

Enabling the Contributors tab for Key Drivers Analysis

When you add the configuration details into the entity_configurations table and perform the Key Drivers analysis, you can view the data for computations Average and Contribution under the Contributor tab.

To view the details for computations Average and Contributions on Key Drivers analysis:

Result:

After performing this configuration, you can view the details for computations Average and Contributions on Key Drivers analysis.

Insight Workbench role-based access

Using this configuration, an admin user can enable or disable the Insights Workbench option and Advanced Option for board users (other than admin user/s).

To perform this configuration, follow the steps listed below:

The below table provides a description for the key values: 

Result: After performing this configuration, you can see the result as shown in the following figures:

Insights Workbench Enable:

Advanced Option Enable:

Insights Workbench not available

Advanced Option not available

Configuring Anomalies and Key Drivers Analysis from User Interface

After making the changes in the application service database, you can enable or disable the anomalies or key drivers analysis from the user interface.

To enable the anomaly or key drivers analysis from the user interface follow the steps listed below:

As you can see Anomaly and Key Drivers are enabled.

Configuring new layout for pinboards from User Interface

To enable the new layout for pinboards from user interface follow the steps listed below:

1. Go to Admin console > Users & Security > Users.
2. For the user's profile name, click the Edit User icon.
3. Add the ‘system’ tag and then click Save.

As you can see the Pinboard Managers is enabled.

Natural Language Generation (NLG) Configurations

Configuring sample NLQs by languages

Description

Using this configuration, you can add Natural Language Questions (NLQs) to be displayed on the ‘Info’ page on WhizAI Explorer. These NLQs help you get started with understanding the data model. 

As a part of this configuration, you have to add certain details to the statements table in the application service database. The “statements” table defines the list of sample queries that will be displayed when you click the Info page. 

 Procedure

To perform this configuration, you must make changes to the application service database.

For example, if you have to display the NLQ: 'Show me sales by region’ on the Info page, then you have to add certain details to the statements table in the application service database. 

To perform this configuration, follow the steps listed below:

Add the details from the table below:

Result

After you perform this configuration the NLQ ‘Show me sales by region’ is displayed in the ‘Info’ page on WhizAI Explorer as shown in the following figure.