OVERVIEW
Virtual Assistants
Kore.ai Platform
Key Concepts
Natural Language Processing (NLP)
Accessing Platform
VIRTUAL ASSISTANTS
Virtual Assistant Builder
Virtual Assistant Types
Getting Started
Creating a Simple Bot
SKILLS
Storyboard
Dialog Task
Introduction
Dialog Builder (New)
Dialog Builder (Legacy)
User Intent Node
Dialog Node
Entity Node
Supported Entity Types
Composite Entities
Supported Colors
Supported Company Names
Form Node
Logic Node
Message Nodes
Confirmation Nodes
Bot Action Node
Service Node
Custom Authentication
2-way SSL for Service nodes
Script Node
Agent Transfer Node
WebHook Node
Grouping Nodes
Connections & Transitions
Manage Dialogs
User Prompts
Knowledge Graph
Terminology
Building
Generation
Importing and Exporting
Analysis
Knowledge Extraction
Build
Alert Tasks
Introduction
Ignore Words and Field Memory
How to Schedule a Smart Alert
Small Talk
Digital Views
Overview
Configuring Digital Views
Digital Forms
Overview
How to Configure Digital Forms
NATURAL LANGUAGE
Overview
Machine Learning
Introduction
Model Validation
Fundamental Meaning
Introduction
NLP Guidelines
Knowledge Graph
Traits
Introduction
How to Use Traits
Ranking and Resolver
Advanced NLP Configurations
INTELLIGENCE
Overview
Context Management
Overview
Session and Context Variables
Context Object
How to Manage Context Switching
Manage Interruptions
Dialog Management
Sub-Intents & Follow-up Intents
Amend Entity
Multi-Intent Detection
Sentiment Management
Tone Analysis
Sentiment Management
Event Based Bot Actions
Default Conversations
Default Standard Responses
TEST & DEBUG
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
CHANNELS
PUBLISH
ANALYZE
Overview
Dashboard
Custom Dashboard
Overview
How to Create Custom Dashboard
Conversation Flows
NLP Metrics
ADVANCED TOPICS
Universal Bots
Overview
Defining
Creating
Training
Customizing
Enabling Languages
Store
Smart Bots
Defining
koreUtil Libraries
SETTINGS
Authorization
Language Management
PII Settings
Variables
Functions
IVR Integration
General Settings
Management
Import & Export
Delete
Versioning
Collaborative Development
PLAN & USAGE
Overview
Usage Plans
Support Plans
Invoices
API GUIDE
API Overview
API List
API Collection
SDKs
SDK Overview
SDK Security
SDK App Registration
Web SDK Tutorial
Message Formatting and Templates
Mobile SDK Push Notification
Widget SDK Tutorial
Widget SDK – Message Formatting and Templates
Web Socket Connect & RTM
Using the BotKit SDK
Installing
Configuring
Events
Functions
BotKit SDK Tutorial – Agent Transfer
BotKit SDK Tutorial – Flight Search Sample Bot
Using an External NLP Engine
ADMINISTRATION
HOW TOs
Creating a Simple Bot
Creating a Banking Bot
Context Switching
Using Traits
Schedule a Smart Alert
Configure UI Forms
Add Form Data into Data Tables
Configuring Digital Views
Add Data to Data Tables
Update Data in Data Tables
Custom Dashboard
Custom Tags to filter Bot Metrics
Patterns for Intents & Entities
Build Knowledge Graph
Global Variables
Content Variables
Using Bot Functions
Configure Agent Transfer
Update Balance Task
Transfer Funds Task
RELEASE NOTES
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Builder
  5. Dialog Task
  6. Data as Service

Data as Service

Kore.ai’s Data offering lets you define Data Tables, Table Views, and manipulate them from your Virtual Assistant. This section deals with the manipulation aspect using the Service Node within a Dialog Task of your Virtual Assistant. For details on the data definition, refer here.

Service Call – Table

From the assigned bots for any given data table/table view, you can query and manipulate the data using the Service Node in the Dialog Tasks.

Steps to configure the Service node:

  1. Open the Bot and the Dialog Task where you want to access the data.
  2. Add a Service Node at the appropriate location in the process flow.
  3. Click here for details on Service Node. Here we will be listing the configurations for Data Table integration.
  4. Component Properties configuration
    • General Settings section
      • Name – enter a name for the node;
      • Display Name – enter a display name for the node;
      • Service Type – choose Data Service;
      • Type – select Table.

Request Definition – define the service request by clicking the Define Request link. In the slide-out page configure the following:

  • Choose a Data Table – You can choose from the list, these are the data tables assigned to this bot.
  • Actions – Select the action you would like to perform:

  • You can Test the service request. Remember testing with context reference will fail as they will be evaluated at run time and the data will not be available till then.
  • Save the service request definition
  • You can set the Instance and Connections properties as per your bot requirements.
  • The data returned from the data table can be accessed from the context object and used in your task as per your need.

Add Data

To add data, you need to:

  • provide values for each column in the data table;
  • these values can be static or a reference to a context object  for example {{context.entities.<entity-name>}}
  • The response from this call would be:
      "stringTable": {
        "response": {
          "body": {
            "CustId": 1,
            "Type": "Preferred",
            "Address": "New York",
            "CustomerName": "John Smith",
            "Updated_On": 1593687904111,
            "Created_On": 1593687904111,
            "Updated_By": "st-b1376ff2-1111-1111-aa34-973ef73212f5",
            "Created_By": "st-b1376ff2-1111-1111-aa34-973ef73212f5",
            "sys_Id": "sys-5c46e351-ee51-5c27-80cf-c6c1e8f8f066",
            "_id": "5efdbf602de5bb5f3f54f728"
          }
        }
      }

Get Data

To filter and fetch data from the table, you can:

  • Choose Filters to define filter criteria using:
    • the column names – pick from the drop-down list;
    • an operator – choose from the list;
    • comparison value – these values can be static or a reference to a context object  for example {{context.entities.<entity-name>}}.
    • Multiple filter criteria can be defined using AND/OR connectors.
    • In the absence of filter criteria, all rows are fetched limited by the limit and offset values mentioned below.
  • Limit property can be used to set a limit on the number of records to be fetched. If not specified then 10 records would be fetched by default;
  • Offset property can be used to specify the records to be skipped from the result data set.
  • Data values can be accessed using: {{context.<service_node_name>.response.body.queryResult[<index>].<column_name>}}
  • The response from this service call would be:
    "customerdetails": {
        "response": {
          "body": {
    	"hasMore": true,
    	"total": 4,
    	"metaInfo": [
              {
                "name": "City",
                "type": "string"
              },
              {
                "name": "Name",
                "type": "string"
              },
              {
                "name": "sys_Id",
                "type": "string"
              },
              {
                "name": "Created_On",
                "type": "date"
              },
              {
                "name": "Updated_On",
                "type": "date"
              },
              {
                "name": "Created_By",
                "type": "string"
              },
              {
                "name": "Updated_By",
                "type": "string"
              }
            ],
            "queryResult": [
              {
                "CustId": 1,
                "Type": "Preferred",
                "Address": "New York",
                "CustomerName": "John Smith",
                "sys_Id": "sys-b088ab59-7640-5a8f-8999-61a265dd2bee",
                "Created_On": 1593152119161,
                "Updated_On": 1593152119161,
                "Created_By": "st-b1376ff2-2384-5541-aa34-973ef73212f5",
                "Updated_By": "st-b1376ff2-2384-5541-aa34-973ef73212f5"
              },
              {
                "CustId": 2,
                "Type": "Privileged",
                "Address": "Chicago",
                "CustomerName": "Jane Doe",
                "sys_Id": "sys-632c69ef-f6dd-5d83-ab32-f7837c8b63f9",
                "Created_On": 1593152443035,
                "Updated_On": 1593152443035,
                "Created_By": "st-b1376ff2-2384-5541-aa34-973ef73212f5",
                "Updated_By": "st-b1376ff2-2384-5541-aa34-973ef73212f5"
              }
    	 ]
          }
        }
      }

Update Data

To modify existing you can:

  • Assign Values against each column to be updated.
    If any value is left blank, then the corresponding column original values will NOT be retained but will be set as empty.
  • These values can be static or a reference to a context object.
  • Choose Filters to define the filter criteria to specify the rows to be updated using
    • the column names,
    • an operator and
    • filter value – these values can be static or a reference to a context object  for example {{context.entities.<entity-name>}}.
    • Multiple filter criteria can be defined using AND/OR connectors.

  • The response from this service call would be:
      "customerdetails": {
        "response": {
          "body": {
            "records": []
          }
        }
      }

Delete data

To delete rows from the data table you need

  • to define filter criteria to specify the rows to be deleted using
    • the column names,
    • an operator and
    • filter value, these values can be static or a reference to a context object  for example {{context.entities.<entity-name>}}. Multiple filter criteria can be defined using AND/OR connectors.

  • The response from this service request would be:
      "customerdetails": {
        "response": {
          "body": {
            "nDeleted": 1
          }
        }
      }

Service Call – View

From the assigned bots for any given data table/table view, you can query and manipulate the data using the Service Node in the Dialog Tasks.

Steps to configure the Service node:

  1. Open the Bot and the Dialog Task where you want to access the data.
  2. Add a Service Node at the appropriate location in the process flow.
  3. Click here for details on Service Node. Here we will be listing the configurations for Data Table integration.
  4. Component Properties configuration
    • General Settings section
      • Name – enter a name for the node;
      • Display Name – enter a display name for the node;
      • Service Type – choose Data Service;
      • Type – select View.
    • Request Definition – define the service request by clicking the Define Request link.
    • In the slide-out page configure the following:
      • Choose a Table View – You can choose from the list, these are the table views assigned to this bot.
      • Filter the results – you can further define filter criteria using
        • the column names,
        • an operator and
        • filter value – these values can be static or a reference to a context object  for example {{context.entities.<entity-name>}}.
      • Multiple filter criteria can be defined using AND/OR connectors.
      • In the absence of filter criteria, all rows are fetched limited by the limit and offset values mentioned below.
    • You can set a limit on the number of records fetched and
    • You can choose to skip a few records from the result data set by specifying the offset value.
    • You can Test the service request. Remember testing with context reference will fail as they will be evaluated at run time and the data will not be available till then.
    • Save the service request definition
  5. You can set the Instance and Connections properties as per your bot requirements.
  6. The data returned from the data table can be accessed from the context object and used in your task as per your need, using: {{context.<service_node_name>.response.body.queryResult[<index>].<column_name>}}
  7. The response from this service call would be:
      "CustomerView": {
        "response": {
          "body": {
            "hasMore": true,
            "total": 4,
            "metaInfo": [
              {
                "name": "type",
                "type": "string"
              },
              {
                "name": "address",
                "type": "string"
              }
            ],
            "queryResult": [
              {
                "type": "Gold",
                "address": "New York"
              },
              {
                "type": "Gold",
                "address": "Chicago"
              },
              {
                "type": "Gold",
                "address": "Chicago"
              }
            ]
          }
        }
      }
Menu
Kore.ai Named a Leader in 2022 Gartner® Magic Quadrant™ for Enterprise Conversational AI PlatformsGet the Report