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
Record Conversations
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 Management
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. Using Session and Context Variables in Tasks

Using Session and Context Variables in Tasks

When you define tasks, you can access session variables provided by the Bots Platform, or custom variables that you define, as well as the context that defines the scope of the variable.

For example, some API requests may require you to set session variables before the request is executed, or a dialog task component may need to access a session variable to transition to the next node. In addition, a dialog task can access the context object with additional system variables. For more information, see the Context Object.

You can use session variables where you define JavaScript for tasks and the User Prompt editor on the JavaScript tab.

Session Variables

This section describes the context variables and the scope of the context variables that you can use in your custom JavaScript code for your tasks.

The JavaScript syntax to GET or PUT a key/value pair for each context type is:

   "EnterpriseContext" : {
       "get" : function(key){...},//get the specified key
       "put" : function(key, value, ttl){...} //put the value at the key for the specified ttl, ttl is in minutes
   },
   "BotContext" : {
       "get" : function(key){...},//get the specified key
       "put" : function(key, value, ttl){...} //put the value at the key for the specified ttl, ttl is in minutes
   },
   "UserContext" : {
       "get" : function(key){...},//get the specified key
   },
   "UserSession" : {
       "get" : function(key){...},//get the specified key
       "put" : function(key, value, ttl){...} //put the value at the key for the specified ttl, ttl is in minutes
   },
   "BotUserSession" : {
       "get" : function(key){...},//get the specified key
       "put" : function(key, value, ttl){...} //put the value at the key for the specified ttl, ttl is in minutes
   }

For example:

    BotContext.put("topicSessionVariable","music",2000);
    UserSession.put("firstName","Mary",20000);
    UserContext.get("firstName");

Session Variable Types

The following types of session variables are available on the Bots Platform:

  • EnterpriseContext – A key/value pair available to all bots and all users in an enterprise. For example, with the GitHub bot, a user will need to access one or more enterprise repositories. You can persist the repository data as Gitrepository (Enterprise Context) with the following JavaScript code:
    var userRepository = {
    "title": _labels_[repository],
    "value": repository
    };
    EnterpriseContext.put('Gitrepository', userRepository, 200000);
  • BotContext – A key/value pair available to all users of this specific bot. For example, you may want to set up a default currency for financial transactions for a session based on the location of a user. You can persist the default currency data as currency (Bot Context) with the following JavaScript code:
    var defaultCurrency = { TODO Custom JavaScript for location-based currency }
    BotContext.put('currency', defaultCurrency, 200000);
  • UserContext – A key/value pair available to all bots for a user. These keys are read-only and provided by the system as user data for:
      • UserContext.get(“_id”) – The Kore.ai user ID.
      • UserContext.get(“emailId”) – The email address associated with the user ID.
      • UserContext.get(“lastName”) – The last name of the user.
      • UserContext.get(“firstName”) – The first name of the user.
      • UserContext.get(“profImage”) – The image or avatar filename of the user.
      • UserContext.get(“profColor”) – The account color for the user.
      • UserContext.get(“activationStatus”) – The account status of the user. Can be:
        • active – The user is active and can interact with other Kore.ai users.
        • inactive – The user is not active, but user data is retained in the system.
        • suspended – The user is suspended by an administrator. The user cannot log on to Kore.ai, however, messages can still be sent to the suspended user.
        • locked – The user exceeded the maximum number of login attempts.
      • UserContext.get(“jTitle”) – The title of the user, if defined.
      • UserContext.get(“orgId”) – The organizational ID of the user account, if defined.
      • UserContext.get(“customData”) – Use this to pass user information to web channels, currently only for webSDK, see here for more.
      • UserContext.get(“identities”) – Alternate user IDs, if defined.
        • val – The alternate ID
        • type – The type of alternate ID.

    For example, you can PUT a value into the session using the UserSession variable where the key is defined as fullName based on the GET from the two UserContext variables.

    var name = UserContext.get("firstName")+UserContext.get("lastName");
    UserSession.put("fullName") = name;
  • UserSession – A key/value pair that you can define for this specific user for all bots in an enterprise. For example, you may want to store a user location to make it available to all Bots, such as a user home address for commerce, transportation, and home delivery services. For example, you can persist default location data as HomeLocation (UserSession) with the following JavaScript code:
    var location = {
     "title": labels[location],
     "value": {
     "latitude": location.latitude,
     "longitude": request.location.longitude
     }
    };
    UserSession.put('HomeLocation', location, '20000');
  • BotUserSession – A key/value pair that you can define to a specific bot based on the inputs by a specific user. For example, you may want to persist a user location for more than one task of a Bot. For a travel bot, the user may be able to book a flight and a hotel based on the same home and destination addresses. For example, you can persist the default home and destination data as HomeLocation (BotUserSession) and DestinationLocation (BotUserSession) with the following JavaScript code:
    var homelocation = {
     "title": labels[request.sourceLocation],
     "value": {
     "latitude": request.sourceLocation.latitude,
     "longitude": request.sourceLocation.longitude
     }
    };
    BotUserSession.put('HomeLocation', homelocation, '20000');
    var destlocation = {
     "title": labels[request.destLocation],
     "value": {
     "latitude": request.destLocation.latitude,
     "longitude": request.destLocation.longitude
     }
    };
    BotUserSession.put('DestinationLocation', destlocation, '20000’);

Standard Keys

In addition to session and context keys, there are Kore.ai variable placeholders for reusable data. Select one of:

  • _labels_ – Used to return the friendly label in place of a GUID. For example, when user data is requested from a web service API, the ID of a project or workspace returned is a GUID. You can use the _labels_ key to show the user-friendly name of the GUID to the end-user instead of the GUID. In Kore.ai, a drop-down control stores the response for the _labels_ key as, for example:
    {
        "_labels_": {
            "15379386734832": "roadlabs.com",
            "26377329985341": "Test Project",
            "workspace": "roadlabs.com",
            "project": "Test Project"
        },
        "_fields_": {
            "workspace": "15379386734832",
            "project": "26377329985341"
        }
    }

    To use the _labels_ key in a response:

    print('<a href="https://app.asana.com/0/' + workspace.id + '/' + id + '/f" target="_blank">' + title + '</a> in workspace '+_labels_[workspace.id]);
  • _tenant_ – Used to return the tenant for the enterprise when defined. For example, JIRA requires a tenant for URLs, such as koreteam, in https://koreteam.atlassian.net/browse/BBF-3265. You can use the _tenant_ key to build a link in a task response such as:
    var title = request.fields.issuetype.name + ' <a href ="https://' + _tenant_ + '/browse/' + response.key + '" target = "_blank">' + request.fields.summary + '</a>  has been created.';
  • _fields_ – Used to return an action task field input provided by the end-user that is not part of a payload response. For example, in a JIRA action task, the end-user is prompted to enter a workspace name. You can use the _fields_ key to store the end-user input as:
    _fields_["workspace"]
  • _last_run – Used to return the UTC date timestamp of a web service poll using ISO 8601 format, for example, 2016-03-05T12:44:38+00:00. For example, if a web service request returns all activity in a payload response, you can use the _last_run key to filter results displayed before or after the value for _last_run.
Menu