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

Introduction

SearchAssist is a conversational search assistant that combines cognitive search and virtual assistant competencies. It helps business users build a search assistant powered with AI and conversational UI that is smart enough to answer search user queries and perform tasks if needed. It understands the domain language and context to bring personalized and humanized results through multi-turn conversations.

Also, SearchAssist enables businesses to offer the best search and customer engagement experience by providing an enterprise-ready, simple-to-use solution. SearchAssist’s AI-powered search engine presents insights into the ways search users are interacting with the application that helps you serve them better.

Getting Started

To configure and implement a search assistant using SearchAssist, you first need to build a SearchAssist application and deploy it on your organization’s website or any channel of your choice. For this, you need to access SearchAssist.

Access

To access SearchAssist, you need valid credentials.

Sign Up

To sign up for an account, follow the below steps:

  1. Use the link https://app.searchassist.ai/ to access SearchAssist.
  2. On the SearchAssist by Kore.ai page, enter the email address and click Continue.
  3. On the corresponding page, enter the details in the First Name, Last Name, Company/Account Name, Password, and Confirm Password fields.
  4. Click Sign Up.
  5. On the corresponding page, it displays Almost done! Please verify your email. Check if you have received the verification email, else click Resend to resend the verification email.
  6. After verification, it lands you on the application.

Log In

Once you have signed up, you can log in to SearchAssist, following the below steps:

  1. Use the link https://app.searchassist.ai/home to access SearchAssist.
  2. Log in to the application with valid credentials.
  3. After you log in, on the Welcome to SearchAssist page, click Let’s Get Started.

Application

The first step in building a SearchAssist is creating an application.

A SearchAssist Application is a set of configurations and data from various sources. Once you have created and configured the application, you can deploy it on any channel to enable the search users to interact with it. Currently, SearchAssist supports only web SDK channels.

To create an application, follow the below steps:

  1. On the landing page, click + Create your first app.
  2. On the Create App dialog box, enter the name and description in the Name Your App and Description fields.
  3. Select the language from the Language drop-down list.
  4. Click Create.

You can have different applications for different environments, business purposes, regions, etc. When your application runs in different environments, you want to use different sets of data. For example, when you run your application on a staging website, you tend to use test data instead of production data. When you work on a staging version of your website, you tend to avoid hitting your production index for privacy reasons and to avoid skewing your analytics.

There are two ways you can split your search implementation for each environment:

  1. Separate your environments into different indices on the same application.
  2. Create several applications, and use one for an environment.

You can set the best approach depending on the isolation level you need between the environments.

Introduction

SearchAssist is a conversational search assistant that combines cognitive search and virtual assistant competencies. It helps business users build a search assistant powered with AI and conversational UI that is smart enough to answer search user queries and perform tasks if needed. It understands the domain language and context to bring personalized and humanized results through multi-turn conversations.

Also, SearchAssist enables businesses to offer the best search and customer engagement experience by providing an enterprise-ready, simple-to-use solution. SearchAssist’s AI-powered search engine presents insights into the ways search users are interacting with the application that helps you serve them better.

Getting Started

To configure and implement a search assistant using SearchAssist, you first need to build a SearchAssist application and deploy it on your organization’s website or any channel of your choice. For this, you need to access SearchAssist.

Access

To access SearchAssist, you need valid credentials.

Sign Up

To sign up for an account, follow the below steps:

  1. Use the link https://app.searchassist.ai/ to access SearchAssist.
  2. On the SearchAssist by Kore.ai page, enter the email address and click Continue.
  3. On the corresponding page, enter the details in the First Name, Last Name, Company/Account Name, Password, and Confirm Password fields.
  4. Click Sign Up.
  5. On the corresponding page, it displays Almost done! Please verify your email. Check if you have received the verification email, else click Resend to resend the verification email.
  6. After verification, it lands you on the application.

Log In

Once you have signed up, you can log in to SearchAssist, following the below steps:

  1. Use the link https://app.searchassist.ai/home to access SearchAssist.
  2. Log in to the application with valid credentials.
  3. After you log in, on the Welcome to SearchAssist page, click Let’s Get Started.

Application

The first step in building a SearchAssist is creating an application.

A SearchAssist Application is a set of configurations and data from various sources. Once you have created and configured the application, you can deploy it on any channel to enable the search users to interact with it. Currently, SearchAssist supports only web SDK channels.

To create an application, follow the below steps:

  1. On the landing page, click + Create your first app.
  2. On the Create App dialog box, enter the name and description in the Name Your App and Description fields.
  3. Select the language from the Language drop-down list.
  4. Click Create.

You can have different applications for different environments, business purposes, regions, etc. When your application runs in different environments, you want to use different sets of data. For example, when you run your application on a staging website, you tend to use test data instead of production data. When you work on a staging version of your website, you tend to avoid hitting your production index for privacy reasons and to avoid skewing your analytics.

There are two ways you can split your search implementation for each environment:

  1. Separate your environments into different indices on the same application.
  2. Create several applications, and use one for an environment.

You can set the best approach depending on the isolation level you need between the environments.