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. Integrations
  3. Configuring the Azure OpenAI Action

Configuring the Azure OpenAI Action

The XO Platform lets you easily connect your Azure OpenAI instance to find answers to your general queries. The Platform supports all common actions on Azure with ready-to-use pre-built dialog templates.

This article explains how to authorize and enable the Azure OpenAI action and install the pre-built templates.

Authorizations Supported

The Kore.ai XO Platform supports basic authentication to allow Azure OpenAI integration to exchange data. For more information, read the Bot Authorization Overview article.

The Kore.ai XO Platform supports the following authorization types for the Azure OpenAI integration:

  • Pre-Authorize the Integration – To make the integration process smoother for developers and customers, you can pre-authorize it by providing the necessary authorization credentials to obtain the access token.
  • Allow Users to Authorize the Integration – This method requires the end user to provide credentials during the conversation for authorization. This authorization process involves requesting permission for Kore.ai’s Azure OpenAI app to access an access token at runtime. To learn more about Azure OpenAI account types, see Azure OpenAI Service.

Step 1: Create an Azure OpenAI App

Prerequisites:

Before enabling the Azure OpenAI action, complete the following prerequisites:

  • If you don’t have Azure OpenAI account credentials, create a developer account in Azure OpenAI and note down login credentials. Use the Azure OpenAI Service Documentation for more information.
  • Copy the API Key, User Sub Domain and Deployment ID values and keep them for future use to enable the integration.

Create an Azure OpenAI Service app and configure it on the Kore.ai XO Platform to establish a communication channel between Azure OpenAI and the Kore.ai XO Platform.

Steps to create an Azure OpenAI service:

  1. Log in to the Azure portal, and search for Azure OpenAI from the portal menu.
  2. On the Cognitive Services Azure OpenAI page, click Create.
  3. Fill in the following required details:
    • Select an existing Resource Group or create a new one.
    • Select the Region. For example, select the South Central US region.
    • Enter the Name of the Azure OpenAI service. For example, enter PlatformInegration.
    • Select the Pricing Tier option. For example, select the Standard option.

  4. Click Next and then click Review + Submit.
  5. Once the Validation Passed message appears, click Create.
  6. The Azure OpenAI service is now initialized and deployed in the portal with an endpoint URL and API Keys. Click Go to Resource to view the app details.
  7. In the Overview page, copy the User Domain Name as shown below.
  8. In the Left Navigation Pane, select the Keys and Endpoints menu and click Show Keys, and then copy the API Key as shown below.
  9. In the Left Navigation Pane, select Model Deployments and create a new deployment. For example, enter the model name as PlatformDeploy and select the Model as text-davinci-001. Click Save.
  10. Copy the Model Name of the newly created deployment as shown below.
  11. You can also copy the Azure OpenAI service credentials from the Azure OpenAI Studio > Playground > GPT- 3 > View Code, as shown below.

Step 2: Enable the Azure OpenAI Action

Once you have created an Azure OpenAI service and copied the required credentials, you can enable the integration.

Steps to enable the Azure OpenAI action:

  1. Go to Build > Integrations > Actions.
  2. Once you click the Actions menu, all integrations are shown in the Available region. Select the Azure OpenAI action.

Pre-authorize the Integration

Basic Auth

You can authorize the integration using your credentials. The developer authorization lets you authorize the integration with preconfigured Kore.ai’s app with the Basic Auth option.

Steps to authorize the Azure OpenAI action using developer credentials:

  1. Go to Build > Integrations > Actions and select the Azure OpenAI action.
  2. In the Configurations dialog, select the Authorization tab.
  3. Enter the following details:
    • Authorization Type – Select the Pre-authorize the Integration option, and then select the Basic Auth option.
    • API Key – The secret API key of your Azure OpenAI service, which you copied in Step 1.
      Note: The Platform uses the configured API Key to authorize and generate the suggestions from OpenAI.
    • User Sub Domain – The domain name of the Azure OpenAI service, which you copied in Step 1.
    • Deployment ID – The deployment ID/model name of the Azure OpenAI service, which you copied in Step 1.
  4. Click Enable. When you configure the action for the first time, the Integration Successful pop-up is displayed.

    Note: The Azure OpenAI action is moved from Available to Configured region.

Allow the End User to Authorize

You can authorize the integration at a user level with their login credentials. The user authorization process involves requesting permission for Kore.ai’s Azure OpenAI app to access an access token at runtime. You can also use the basic auth profile to let a user configure the integration at runtime.

Steps to authorize an Azure OpenAI action at a user level:

  1. Go to Build > Integrations > Actions and select the Azure OpenAI action in the Available Actions region.
  2. In the Configurations dialog, select the Authorization tab.
  3. Enter the following details:
    • Authorization Type – Select the Allow Users to Authorize the Integration option, and then select the Basic Auth option.
    • Create your authorization profile to obtain an access token and use it to complete integration without using Kore.ai’s Azure OpenAI app for authorization.
    • Click the Select Authorization drop-down and select the Create New option.
    • Select the type of authorization mechanism. For example, select the API Key option.

      To create Basic Auth profiles, see Bot Authorization Overview.
    • Enter the following authentication credentials for the Basic Auth mechanism:
      • Name – Enter the name for the Basic Auth profile.
      • Select Yes; some tasks will have tenancy URLs, and the user must provide the URLs to authenticate successfully.
      • Base URL – Enter the base tenant URL for the Azure OpenAI instance.
      • Authorization Check URL – Enter the authorization check URL for your Azure OpenAI instance.
      • Description – Enter the description of the basic authentication profile.
    • Click Save Auth to save the authorization profile.
    • Select the new Authorization Profile, which you created to complete integration.
  4. Click Enable. When you configure the action for the first time, the Integration Successful pop-up is displayed.

Step 3: Install the Azure OpenAI Action Templates

Once you have configured a Azure OpenAI integration, you can explore and install action templates.

Steps to install action templates:

  1. On the Integration Successful dialog, click the Explore Templates button to view the templates.
  2. In the Integration Templates dialog, click the Install button to begin the installation.
  3. Once the templates is installed, a dialog task is auto-created.
  4. When you create a dialog task, you can also select the task from the Azure OpenAI action templates and click Proceed. For example, select the General Query task.
  5. Once you click Proceed, the dialog task is auto-created, and the canvas opens with all required entity nodes, service nodes, and message scripts.
Menu