GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Navigating the Kore.ai XO Platform
Building a Virtual Assistant
Help & Learning Resources
Release Notes
Current Major Version
Recent Updates
Previous Versions
Deprecations
Request a Feature
CONCEPTS
Design
Storyboard
Overview
FAQs
Conversation Designer
Overview
Dialog Tasks
Mock Scenes
Dialog Tasks
Overview
Navigate Dialog Tasks
Build Dialog Tasks
Node Types
Overview
Intent Node
Dialog Node
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Process Node
Agent Transfer
Node Connections
Node Connections Setup
Sub-Intent Scoping
Entity Types
Entity Rules
User Prompts or Messages
Voice Call Properties
Knowledge AI
Introduction
Knowledge Graph
Introduction
Build a Knowledge Graph
Manage FAQs
Knowledge Extraction
Import or Export Knowledge Graph
Prepare Data for Import
Importing Knowledge Graph
Exporting Knowledge Graph
Auto-Generate Knowledge Graph
Knowledge Graph Analysis
Answer from Documents
Alert Tasks
Small Talk
Digital Skills
Overview
Digital Forms
Digital Views
Introduction
Widgets
Panels
Session and Context Variables
Context Object
Intent Discovery
Train
NLP Optimization
ML Engine
Overview
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
Training Validations
NLP Configurations
NLP Guidelines
LLM and Generative AI
Intelligence
Introduction
Event Handlers
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentinment Management
Tone Analysis
Default Standard Responses
Ignore Words & Field Memory
Test & Debug
Overview
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
Conversation Testing Overview
Create a Test Suite
Test Editor
Test Case Assertion
Test Case Execution Summary
Glossary
Health and Monitoring
NLP Health
Flow Health
Integrations
Actions
Actions Overview
Azure OpenAI
Overview
Templates
BambooHR
Overview
Templates
Freshdesk
Overview
Templates
Freshservice
Overview
Templates
HubSpot
Overview
Templates
JIRA
Overview
Templates
Microsoft Graph
Overview
Templates
Open AI
Overview
Templates
Salesforce
Overview
Templates
ServiceNow
Overview
Templates
Stripe
Overview
Templates
Twilio
Overview
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
Salesforce
ServiceNow
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
Deploy
Channels
Publishing
Versioning
Analyze
Introduction
Dashboard Filters
Overview Dashboard
Conversations Dashboard
Users Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Custom Meta Tags
Create Custom Dashboard
Create Custom Dashboard Filters
NLP Insights
Conversations History
Conversation Flows
Conversation Insights
Feedback Analytics
Usage Metrics
Containment Metrics
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Plan & Usage
Overview
Usage Plans
Support Plans
Invoices
Authorization
Multilingual Virtual Assistants
Get Started
Supported Components & Features
Manage Languages
Manage Translation Services
Multiingual Virtual Assistant Behavior
Feedback Survey
Masking PII Details
Variables
Collections
IVR Settings
General Settings
Assistant Management
Manage Namespace
Data
Overview
Data Table
Table Views
App Definitions
Data as Service
HOW TOs
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking Assistant
Design Conversation Skills
Create a Sample Banking Assistant
Create a Transfer Funds Task
Create a Update Balance Task
Create a Knowledge Graph
Set Up a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Add Data to Data Tables
Update Data in Data Tables
Add Data from Digital Forms
Train the Assistant
Composite Entities
Use Traits
Use Patterns for Intents & Entities
Manage Context Switching
Deploy the Assistant
Configure an Agent Transfer
Use Assistant Functions
Use Content Variables
Use Global Variables
Intent Scoping using Group Node
Analyze the Assistant
Create a Custom Dashboard
Use Custom Meta Tags in Filters
Migrate External Bots
Google Dialogflow Bot
APIs & SDKs
API Reference
API Introduction
API List
API Collection
koreUtil Libraries
SDK Reference
SDK Introduction
SDK Security
SDK Registration
Web Socket Connect and RTM
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
Widget SDK Tutorial
Web SDK Tutorial
ADMINISTRATION
Introduction to Admin Console
Administration Dashboard
User Management
Add Users
Manage Groups
Manage Roles
Data Tables and Views
Assistant Management
Enrollment
Invite Users
Send Bulk Invites
Import User Data
Synchronize Users from AD
Security & Control
Using Single-Sign On (SSO)
Two-Factor Authentication (2FA)
Security Settings
Cloud Connector
Analytics
Billing
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Channel Enablement
  5. Adding the Unblu Channel

Adding the Unblu Channel

Unblu is a Conversational Platform for Financial Services.

To setup Unblu as a channel, you will need to create an External Integration bot in Unblu, create a ‘Named Area’ and map this Named Area to your Kore.ai assistant.

Channel Integration

Step 1: Create a Named Area

Named Areas in Unblu are used to identify the origins of the chat requests from your website. The Kore.ai assistant should be associated with a Named Area to ensure that it responds to users only when the chat has originated from the sections of your website associated with this Named Area. This mapping is optional if you are enabling the Unblu channel for a single kore.ai bot alone. 

  1. Login to your Unblu Account Administration.
  2. Under the Named Areas module, select the ‘New named area’ option.
  3. Provide all the requested information.
  4. Make a note of the name of the Named Area you have created.

Step 2: Create Unblu Bot

A assistant should be created in your Unblu account for integrating it with your current Kore.ai assistant.

The Unblu Bot can be directly created from the Kore.ai XO Platform.

  1. Create or Open the assistant in the XO platform.
  2. Go to Deploy > Channels and select Unblu..
  3. Proceed to the Configurations tab and provide the following details for creating an assistantin your Unblu account:
    • Unblu Host URL -the URL of your Unblu application. For example, use https://www.unblu.com/ for the Unblu cloud.
    • Unblu Account UsernameProvide your Unblu account username.
    • Unblu Account Password – Provide the password associated with your Unblu username.
    • Unblu Bot Name – Provide a name you would like to use for your Unblu bot
    • Unblu Bot DescriptionProvide a short description of your Unblu bot
    • Bot Person – Provide a Name to represent the Unblu bot to your users
    • Secret Key – Provide a confidential key to secure the communication between Unblu and Kore.ai bots
    • Named Area – Provide the Named Area you would like to associate with your Kore.ai assistant. Kore.ai will respond only to the user chats that have originated in the Named Area that you have selected here. This field is optional if you are enabling Unblu channel for a single kore.ai assistant alone. 
    • Select to Enable the channel and Save your settings.
  4. Enable the channel.

After the channel is enabled and all configurations are verified, you can optionally publish

the assistant to make it available for end-users, with the new channel. Learn more about Publishing your Virtual Assistant.

To learn more about working with Channels within the Kore.ai XO Platform, please see Channel Enablement.

Additional Instructions

For the seamless exchange of information from Unblu to Kore.ai, a few additional steps need to be performed.
For a detailed document on the implementation, refer here.

  • The host URL where the Unblu SDK would be hosted needs to be added to the Domain section of your Unblu Account.
  • From your Unblu Account, API Keys section, make a note of the API Key.
  • Configure the Unblu SDK to give access to Kore.ai assistant, following the steps given below.
  • Open the Unblu SDK HTML file. Ensure that the following attributes are set:
    • In the <head> the meta tag should look thus: <meta name="unblu:named-area" content="<your-namedArea-Id>" /> This is the named area that you created in Step 1 above.
    • Script tag to populate the visitor information needs point to the Unblu host: <script src="<your-unblu-host>/unblu/js-api/v2/visitor/visitor-api.min.js"></script>
    • Invoke the function setVisitorData to pass the visitor data to Kore.ai assistant. Note that the visitorData should be in string format and if you need to pass an object use Stringify.
      • Locate the following section and populate the apiKey and serverUrl fields with the above-mentioned values.
        window.unblu.api
        .configure({
           apiKey: "<your-unblu-apikey>",
           serverUrl: "<your-unblu-host>"
          })
    • In the following Script tag, add Unblu host URL and the API key: <script type="text/javascript" defer="defer" src="<your-unblu-host>/unblu/visitor.js?x-unblu-apikey=<your-unblu-apikey>"></script>
    • The entire Unblu SDK HTML file would look like this:
      <!DOCTYPE html>
      <html>
      
      <head>
      
         <meta name="unblu:named-area" content="<your-namedArea-Id>" />
      
         <script src="https://cdn.jsdelivr.net/npm/promise-polyfill@8/dist/polyfill.min.js"></script>
         <script src="<your-unblu-host>/unblu/js-api/v2/visitor/visitor-api.min.js"></script>
      
       <script>
         function setVisitorData(engagementType, visitorData) { 
            return Promise.resolve(JSON.stringify({ name: "John", about: "Tester" })); 
             }
           window.unblu.api
            .configure({
               apiKey: "<your-unblu-apikey>",
               serverUrl: "<your-unblu-host>"
             })
            .initialize().then(function (api) {
              console.log("API initialized successfully!");
              api.setNewConversationInterceptor(setVisitorData);
       
                  }).catch(e => {
                      console.log("------error : ", e);
                      if (e.type === 'INITIALIZATION_TIMEOUT') {
                        //retry
                       } else if (e.type === 'UNSUPPORTED_BROWSER') {
                        // display unsupported browser dialog
                      } else {
                       // show generic error message
                       }
                 });
      
      </script>
      
      <script type="text/javascript" defer="defer"
      src="<your-unblu-host>/unblu/visitor.js?x-unblu-apikey=<your-unblu-apikey>"></script>
      </head>
      
      <body>
      </body>
      
      </html>
    • You can access the Visitor Data from the usercontext.customData  along with the user information for each message from Unblu,
    • Following is the structure of the usercontext.customData
      {
      "timestamp" : 1594113137065.0,
      "eventType" : "bot.dialog.opened",
      "accountId" : "wZvcAnbBSpOps9oteH-Oxw",
      "dialogToken" : "qG8dFE7ZQPW1p6qcI293hQ-c-QY7P7MNqTCuM6FHT-m-FSQ",
      "dialogType" : "ONBOARDING",
      "counterpartPerson" : {
         "type" : "PersonData",
         "id" : "xZHnVmhxQNKvyf5ybxyLoQ",
         "accountId" : "wZvcAnbBSpOps9oteH-Oxw",
         "personSource" : "VIRTUAL",
         "sourceId" : "awhFjUq1RQCvdMDoV5OW2Q",
         "sourceData" : null,
         "firstName" : null,
         "lastName" : null,
         "username" : null,
         "nickname" : null,
         "displayName" : "Visitor - xZHnV",
         "personType" : "VISITOR",
         "authorizationRole" : "ANONYMOUS_USER",
         "email" : null,
         "phone" : null,
         "teamId" : null,
         "teamName" : null,
         "avatar" : null
         },
      "conversation" : {
         "type" : "ConversationData",
         "id" : "qG8dFE7ZQPW1p6qcI293hQ",
         "accountId" : "wZvcAnbBSpOps9oteH-Oxw",
         "topic" : null,
         "recipient" : {
         "type" : "NamedAreaData", 
         "id" : "WkUGFqcORCCor3bxHa3I5A",
         "accountId" : "wZvcAnbBSpOps9oteH-Oxw",
         "displayName" : "testlocal",
         "avatar" : null
        },
      "participants" : [
       {
         "type" : "ParticipantData",
         "state" : "ACTIVE",
         "personId" : "yb8ALAiGQOWlCoBahUCfgQ",
         "connectedViaExternalMessenger" : false,
         "hidden" : true
       }
       ],
       "assigneePersonId" : null,
       "contextPersonId" : "xZHnVmhxQNKvyf5ybxyLoQ",
       "state" : "ONBOARDING",
       "initialEngagementType" : "CHAT_REQUEST",
       "locale" : "en",
       "tokboxSessionId" : null,
       "visitorData" : "{\"name\":\"John\",\"about\":\"Tester\"}",
       "conversationTemplateId" : "R6W3x2uzQ1KXzARnIqdNZw",
       "links" : [
       {
         "type" : "OPEN_IN_VISITOR_DESK",
         "url" : "https://kore.dev.unblu-test.com/unblu/visitordesk/#/conversation/qG8dFE7ZQPW1p6qcI293hQ"
       },
       {
        "type" : "OPEN_IN_AGENT_DESK",
        "url" : "https://kore.dev.unblu-test.com/unblu/desk/#/conversation/qG8dFE7ZQPW1p6qcI293hQ"
       },
      {
        "type" : "OPEN_IN_AGENT_SINGLE_VIEW",
        "url" : "https://kore.dev.unblu-test.com/unblu/single/#/conversation/qG8dFE7ZQPW1p6qcI293hQ"
       }
       ],
       "externalMessengerChannelId" : null,
       "sourceId" : null,
       "configuration" : null,
       "text" : null
      },
      "presencePersonInfo" : {
        "id" : "OuG04Q0WSFe3-iaIA1GlLw",
        "creationTimestamp" : 1594112743472.0,
        "modificationTimestamp" : 1594112743472.0,
        "accountId" : "wZvcAnbBSpOps9oteH-Oxw",
        "joinedTimestamp" : 1594112743472.0,
        "leftTimestamp" : null,
        "personId" : "xZHnVmhxQNKvyf5ybxyLoQ",
        "deviceInfo" : {
          "id" : "fx7Q8qZyQXmnf62xpoePWg",
          "creationTimestamp" : 1594112743454.0,
          "modificationTimestamp" : 1594112743454.0,
          "accountId" : "wZvcAnbBSpOps9oteH-Oxw",
          "osName" : "Ubuntu",
          "osVersion" : "Other",
          "browserName" : "Chromium",
          "browserVersion" : "81.0",
          "userAgent" : null,
          "screenWidth" : null,
          "screenHeight" : null,
          "screenPixelRatio" : null,
          "type" : "DESKTOP",
          "identifier" : "awhFjUq1RQCvdMDoV5OW2Q",
          "identifierSource" : "COOKIE",
          "pushToken" : null,
          "ownerPersonId" : "xZHnVmhxQNKvyf5ybxyLoQ"
        },
       "touchTimestamp" : 1594113153628.0,
       "impersonationType" : "NONE",
       "impersonatedFromUserId" : null,
       "impersonatedFromAccountId" : null,
       "additionalInfo" : null,
       "authInfo" : null,
       "propagated" : false
       }
      }

Special Notes

There are multiple functionalities that can be achieved by the integration of Unblu channel with Kore.ai assistant

  • When mapping named area to a bot, multiple named areas can be mapped. This way a single Kore.ai assistant has the ability to accept Unblu dialog offer requests from different origins like SDKs or namedAreas.
  • Also, the named area mapping is optional if you are enabling the Unblu channel for a single Kore.ai assistant. 
  • You can redirect user conversations to agents by adding an agent transfer node in the dialog flow, note that you need not enable the Agent Transfer or BotKit specifically for this Channel. Having an agent transfer node is sufficient.
  • The user information for each message from Unblu is available in the usercontext.customData and you can use it for further processing. This information includes deviceInfo, authInfo, joinedTime of the user. See here for how to use context object.

Using Unblu supported message templates

By default, the following message templates are used – Button/multi-choice, List template. You can override templates like card message, List message, multi-choice/Button message.

Following is a code example for how to use the above mentioned templates, change it to suit your requirements:

  • Card Template:
    var unbluCardTemplate = {
        "$_type": "CardPostMessageData",
        "type": "CARD",
        "imageUrl": "data:image/png;base64,",
        "imageAltText": "test image",
        "title": "Title",
        "body": "This is the **body text** with markdown",
        "bodyTextType": "MARKDOWN",
        "actions": [
          {
            "$_type": "MessageAction",
            "actionType": "LINK_INTERNAL",
            "label": "Unblu homepage",
            "value": "https://unblu.com"
          },
          {
            "$_type": "MessageAction",
            "actionType": "LINK_EXTERNAL",
            "label": "Wikipedia",
            "value": "https://www.wikipedia.org/"
          },
          {
            "$_type": "MessageAction",
            "actionType": "REPLY_MESSAGE",
            "label": "More info",
            "value": "Could you provide me with more info?"
          }
        ]
      };
    
    print(JSON.stringify(unbluCardTemplate));
    
  • List Template:
    var unbluListTemplate = {
        "$_type": "ListPostMessageData",
        "type": "LIST",
        "header": {
          "$_type": "MessageHeader",
          "imageUrl": "data:image/png;base64,",
          "imageAltText": "test image",
          "title": "Title",
          "body": "This is the **body text** with markdown",
          "bodyTextType": "MARKDOWN"
        },
        "items": [
          {
            "$_type": "PostListMessageCardItemData",
            "imageUrl": "data:image/png;base64,",
            "imageAltText": "test image",
            "title": "Title",
            "body": "This is the **body text** with markdown",
            "bodyTextType": "MARKDOWN",
            "action": null
          },
          {
            "$_type": "PostListMessageCardItemData",
            "imageUrl": "data:image/png;base64,",
            "imageAltText": "test image",
            "title": "Title",
            "body": "This is the **body text** with markdown",
            "bodyTextType": "MARKDOWN",
            "action": {
              "$_type": "MessageAction",
              "actionType": "LINK_INTERNAL",
              "label": "Unblu homepage",
              "value": "https://unblu.com"
            }
          }
        ],
        "actions": [
          {
            "$_type": "MessageAction",
            "actionType": "LINK_INTERNAL",
            "label": "Unblu homepage",
            "value": "https://unblu.com"
          },
          {
            "$_type": "MessageAction",
            "actionType": "LINK_EXTERNAL",
            "label": "Wikipedia",
            "value": "https://www.wikipedia.org/"
          },
          {
            "$_type": "MessageAction",
            "actionType": "REPLY_MESSAGE",
            "label": "More info",
            "value": "Could you provide me with more info?"
          }
        ]
    }
    print(JSON.stringify(unbluListTemplate));
    
  • Multi Choice Template:
    var unbluMultiChoiceTemplate =  {
        "$_type": "MultichoiceQuestionPostMessageData",
        "type": "MULTICHOICE_QUESTION",
        "text": "Choose one of the options",
        "textType": "MARKDOWN",
        "options": [
          {
            "$_type": "MultichoiceQuestionOption",
            "label": "Option 1",
            "value": "1",
            "primary": true
          },
          {
            "$_type": "MultichoiceQuestionOption",
            "label": "Option 2",
            "value": "2",
            "primary": false
          }
        ]
      };
    print(JSON.stringify(unbluMultiChoiceTemplate));
    
Menu