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

Configuring Traits

Traits are characteristics that can be identified and extracted from the search user’s input. They provide insight into the search user’s intent. In natural conversations, it is common for a user to provide background or relevant information when describing a specific scenario.

You can also identify traits in jargon (i.e. usage in a trade or profession). For example, pax in the travel industry, checkout in the hospitality industry, and discharge summary in health care.

Traits are specific entities, attributes, or details that users express in their conversations. The utterance may not directly convey any specific intent, but a trait in an utterance can lead to intent detection and drive bot conversation flow.

You can extract traits from documents. SearchAssist can then map those traits to user queries and use the information to help to increase the relevance score. Use the traits added to the SearchAssist app to fine-tune an index workbench and configure business rules.

For example, instead of a simple query, “How do I pay my bill”, the user might say, “I was wondering if it would be possible to make payments.”  To ensure the SearchAssist app generates the same result for either query, manually define a common trait for these two utterances. Tag the corresponding content source or answer with that trait so that future queries generate the most effective search result.

Adding Traits

Follow these steps:

  1. Click the Indices menu tab.
  2. In the left pane, click Traits.
  3. Click the Add Traits button.
  4. In the Create New dialog box, enter a name in the Trait Group field.
  5. Enter a word or phrase in the Traits field.
  6. Hit Enter on your keyboard.
  7. Repeat steps to add multiple traits.

Adding Utterances

After creating a list of traits, open a trait file and add utterances. An utterance is a word or phrase that is likely to be used in a conversation about the trait by the end-user.

  1. Locate a trait and click + Add Utterances.
  2. On the next page, enter an utterance.
  3. Hit Enter.
  4. Repeat steps.
  5. Click Add.
  6. Click Save.

After creating traits, you must extract these traits from the source content so that the traits are identified in the user utterance and are mapped to the source document.

Include these traits in the business rules as required and assign the appropriate action.

Managing Traits

You can perform the following actions on traits:

  1. Search for a specific trait.
  2. On the Traits page, hover over the corresponding row on the far right to see the edit and delete options.

Note: Make sure you click the Train your App icon each time you make changes to any index configuration. This builds the index based on the updated configurations.

Configuring Traits

Traits are characteristics that can be identified and extracted from the search user’s input. They provide insight into the search user’s intent. In natural conversations, it is common for a user to provide background or relevant information when describing a specific scenario.

You can also identify traits in jargon (i.e. usage in a trade or profession). For example, pax in the travel industry, checkout in the hospitality industry, and discharge summary in health care.

Traits are specific entities, attributes, or details that users express in their conversations. The utterance may not directly convey any specific intent, but a trait in an utterance can lead to intent detection and drive bot conversation flow.

You can extract traits from documents. SearchAssist can then map those traits to user queries and use the information to help to increase the relevance score. Use the traits added to the SearchAssist app to fine-tune an index workbench and configure business rules.

For example, instead of a simple query, “How do I pay my bill”, the user might say, “I was wondering if it would be possible to make payments.”  To ensure the SearchAssist app generates the same result for either query, manually define a common trait for these two utterances. Tag the corresponding content source or answer with that trait so that future queries generate the most effective search result.

Adding Traits

Follow these steps:

  1. Click the Indices menu tab.
  2. In the left pane, click Traits.
  3. Click the Add Traits button.
  4. In the Create New dialog box, enter a name in the Trait Group field.
  5. Enter a word or phrase in the Traits field.
  6. Hit Enter on your keyboard.
  7. Repeat steps to add multiple traits.

Adding Utterances

After creating a list of traits, open a trait file and add utterances. An utterance is a word or phrase that is likely to be used in a conversation about the trait by the end-user.

  1. Locate a trait and click + Add Utterances.
  2. On the next page, enter an utterance.
  3. Hit Enter.
  4. Repeat steps.
  5. Click Add.
  6. Click Save.

After creating traits, you must extract these traits from the source content so that the traits are identified in the user utterance and are mapped to the source document.

Include these traits in the business rules as required and assign the appropriate action.

Managing Traits

You can perform the following actions on traits:

  1. Search for a specific trait.
  2. On the Traits page, hover over the corresponding row on the far right to see the edit and delete options.

Note: Make sure you click the Train your App icon each time you make changes to any index configuration. This builds the index based on the updated configurations.