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
SharePoint Connector
Confluence Cloud Connector
Confluence Server Connector
Zendesk Connector
ServiceNow Connector
Salesforce Connector
Azure Storage Connector
Google Drive Connector
Dropbox Connector
Oracle Knowledge Connector
DotCMS 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

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

Trait Management

Traits are specific entities or attributes that are extracted from the search users’ input. These give further insight into the search user’s intent. You can train the application to identify traits specific to your business and use them for better search results. You can extract traits from documents and search user queries that help to increase the relevance score. You can also use the traits added to the application in the index workbench and business rules.

For example, instead of a simple query How do I pay my bill, the user might say something like I was wondering if it would be possible to make payments. For the SearchAssist to understand that both the above queries must result in the same response, you can define a trait for these two utterances and tag the corresponding source with that trait.

Configure Traits

To configure Traits, follow the below steps:

  1. Click the Indices tab on the top.
  2. On the left pane, under the Index Configuration section, click Traits.
  3. Click Create New.
  4. On the Create New dialog box, enter a name in the Trait Group field.
  5. In the Traits field, enter the trait. Click Enter to add multiple traits.
  6. For each trait, you must add the utterance(s) that identifies the trait.
  7. Click Save.
  8. Once created, you must extract these traits from the source so that the traits identified in the user utterance are mapped to the source document. (Click here for more information).
  9. Include these traits in the business rules and assign the appropriate action. Click here for more information.

Ensure to Train your app each time you make changes to any index configuration. This builds the index based on the updated configurations.

Actions

Once added you can perform the following actions on traits:

  1. Search for a specific trait;
  2. Edit a trait group to change the name, add, modify, delete traits;
  3. Delete a trait group.

Ensure to Train your app each time you make changes to any index configuration. This builds the index based on the updated configurations.

Trait Management

Traits are specific entities or attributes that are extracted from the search users’ input. These give further insight into the search user’s intent. You can train the application to identify traits specific to your business and use them for better search results. You can extract traits from documents and search user queries that help to increase the relevance score. You can also use the traits added to the application in the index workbench and business rules.

For example, instead of a simple query How do I pay my bill, the user might say something like I was wondering if it would be possible to make payments. For the SearchAssist to understand that both the above queries must result in the same response, you can define a trait for these two utterances and tag the corresponding source with that trait.

Configure Traits

To configure Traits, follow the below steps:

  1. Click the Indices tab on the top.
  2. On the left pane, under the Index Configuration section, click Traits.
  3. Click Create New.
  4. On the Create New dialog box, enter a name in the Trait Group field.
  5. In the Traits field, enter the trait. Click Enter to add multiple traits.
  6. For each trait, you must add the utterance(s) that identifies the trait.
  7. Click Save.
  8. Once created, you must extract these traits from the source so that the traits identified in the user utterance are mapped to the source document. (Click here for more information).
  9. Include these traits in the business rules and assign the appropriate action. Click here for more information.

Ensure to Train your app each time you make changes to any index configuration. This builds the index based on the updated configurations.

Actions

Once added you can perform the following actions on traits:

  1. Search for a specific trait;
  2. Edit a trait group to change the name, add, modify, delete traits;
  3. Delete a trait group.

Ensure to Train your app each time you make changes to any index configuration. This builds the index based on the updated configurations.