GETTING STARTED
SearchAssist Overview
SearchAssist Introduction
Onboarding SearchAssist
Build your first App
Glossary
Release Notes
What's new in SearchAssist
Previous Versions

CONCEPTS
Managing Sources
Introduction
Files
Web Pages
FAQs
Structured Data 
Connectors
Introduction to Connectors
Azure Storage Connector
Confluence Cloud Connector
Confluence Server Connector
Custom Connector
DotCMS Connector
Dropbox Connector
Google Drive Connector
Oracle Knowledge Connector
Salesforce Connector
ServiceNow Connector
SharePoint Connector
Zendesk Connector
RACL
Virtual Assistants
Managing Indices
Introduction
Index Fields
Traits
Workbench
Introduction to Workbench
Field Mapping
Entity Extraction
Traits Extraction
Keyword Extraction
Exclude Document
Semantic Meaning
Snippet Extraction
Custom LLM Prompts
Index Settings
Index Languages
Managing Chunks
Chunk Browser
Managing Relevance
Introduction
Weights
Highlighting
Presentable
Synonyms
Stop Words
Search Relevance
Spell Correction
Prefix Search
Custom Configurations
Personalizing Results
Introduction
Answer Snippets
Introduction
Extractive Model
Generative Model
Enabling Both Models
Simulation and Testing
Debugging
Best Practices and Points to Remember
Troubleshooting Answers
Answer Snippets Support Across Content Sources
Result Ranking
Facets
Business Rules
Introduction
Contextual Rules
NLP Rules
Engagement
Small Talk
Bot Actions
Designing Search Experience
Introduction
Search Interface
Result Templates
Testing
Preview and Test
Debug Tool
Running Experiments
Introduction
Experiments
Analyzing Search Performance
Overview
Dashboard
User Engagement
Search Insights
Result Insights
Answer Insights

ADMINISTRATION
General Settings
Credentials
Channels
Team
Collaboration
Integrations
OpenAI Integration
Azure OpenAI Integration
Custom Integration
Billing and Usage
Plan Details
Usage Logs
Order and Invoices
Smart Hibernation

SearchAssist APIs
API Introduction
API List

SearchAssist SDK

HOW TOs
Use Custom Fields to Filter Search Results and Answers
Add Custom Metadata to Ingested Content
Write Painless Scripts
Configure Business Rules for Generative Answers

Bot Actions

User queries sometimes lead to performing an action. For example, let us consider a banking customer searching for How to pay bills from his bank account. Instead of just answering the query, the user experience can be enhanced if the search assistant provided an option to pay the bill. You can accomplish this by linking the search application with a virtual assistant or a chatbot from the Kore.ai bots platform.

Prerequisites

You can link virtual assistants build on the Kore.ai platform with the SearchAssist application. The following are the setup steps you need to complete from the Kore.ai platform:

  1. Build a virtual assistant catering to your needs, refer here for how.
  2. Enable the Webhook channel for the virtual assistant using the access token and post URL as shown in the below section. Refer here for enabling Webhook channel
  3. Make a note of the Client Id and Secret Id from the Kore.ai virtual assistant, after enabling the Webhook channel.

Link Bots

To perform the bot actions on the SearchAssist, you need your bots from the Kore.ai bots platform linked to the SearchAssist application. 

To link bots from the Actions tab, follow the below steps:

  1. On the left pane, under the Sources section, click the Actions tab.
  2. On the Bot Actions page, click Link a Bot.
  3. On the Link Bot dialog box, click the Link Bot button against the bot you wish to link.
  4. Enter the Client Id and the Secret Id from the virtual assistant as described in the previous section.
  5. Click Link.

Note: You can link only one bot with an application.

Actions

Once you have linked a bot, you can

  • View the bot and the associated tasks.
  • You can open the virtual assistant in the Kore.ai platform.
  • Edit Configuration in case of any changes from the Kore.ai platform.
  • Unlink bot.

Bot Actions

User queries sometimes lead to performing an action. For example, let us consider a banking customer searching for How to pay bills from his bank account. Instead of just answering the query, the user experience can be enhanced if the search assistant provided an option to pay the bill. You can accomplish this by linking the search application with a virtual assistant or a chatbot from the Kore.ai bots platform.

Prerequisites

You can link virtual assistants build on the Kore.ai platform with the SearchAssist application. The following are the setup steps you need to complete from the Kore.ai platform:

  1. Build a virtual assistant catering to your needs, refer here for how.
  2. Enable the Webhook channel for the virtual assistant using the access token and post URL as shown in the below section. Refer here for enabling Webhook channel
  3. Make a note of the Client Id and Secret Id from the Kore.ai virtual assistant, after enabling the Webhook channel.

Link Bots

To perform the bot actions on the SearchAssist, you need your bots from the Kore.ai bots platform linked to the SearchAssist application. 

To link bots from the Actions tab, follow the below steps:

  1. On the left pane, under the Sources section, click the Actions tab.
  2. On the Bot Actions page, click Link a Bot.
  3. On the Link Bot dialog box, click the Link Bot button against the bot you wish to link.
  4. Enter the Client Id and the Secret Id from the virtual assistant as described in the previous section.
  5. Click Link.

Note: You can link only one bot with an application.

Actions

Once you have linked a bot, you can

  • View the bot and the associated tasks.
  • You can open the virtual assistant in the Kore.ai platform.
  • Edit Configuration in case of any changes from the Kore.ai platform.
  • Unlink bot.