GETTING STARTED
SearchAssist Overview
SearchAssist Introduction
Onboarding SearchAssist
Build your first App
Glossary
Release Notes
Current Version
Recent Updates
Previous Versions

CONCEPTS
Managing Sources
Introduction
Files
Web Pages
FAQs
Structured Data 
Connectors
Introduction to Connectors
SharePoint Connector
Confluence Connector
Zendesk Connector
ServiceNow Connector
Salesforce Connector
Azure Storage Connector
Google Drive Connector
Dropbox Connector
Oracle Knowledge Connector
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
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
Collaboration
Integrations
OpenAI Integration
Azure OpenAI Integration
Billing and Usage
Plan Details
Usage Logs
Order and Invoices

SearchAssist PUBLIC 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

How to Configure Business Rules for Generative Answers

Steps to configure

  1. Ingest Source content into the SearchAssist application. 
  2. Integrate LLM with your application.
  3. Enable Generative Model for Answer Snippets.
  4. Train the application. This will generate chunks from the ingested content.  
  5. Open Chunk Browser and view the Answer Index Fields. The Summary View shows some of the important Answer Index Fields like chunkTitle, chunkText, sourceType, sourceName, etc.  You can see all the fields in the JSON view.
  6. Add the chunk properties that you want to use for writing business rules as Index Fields under the Indices tab.  
  7. Go to Business Rules under the Indices tab and create a new rule. 
  8. Enter the name of the rule, add a condition for the rule to be triggered, the outcome of the rule, and click Add. Find more details on how to set the conditions and outcomes here.

Points to remember

  • The name of a business rule designed for Answers should always begin with ‘vi_’.
  • While adding Index Fields, you can also add nested fields, like chunkMeta.sourceUrl. Subsequently, these fields can then be used to define the outcome of the business rules.
  • When using the ‘contains’ operator in the outcome, provide the complete word. 
  • If there are any custom Answer Index Fields that you want to use in your business rule, use the meta_data feature. Meta_data information is available as a chunkMeta field. Find more info on meta_data here. You can also use nested fields to access the parameters in the chunkMeta field. 

Refer to this for detailed descriptions and examples of how to create business rules. 

How to Configure Business Rules for Generative Answers

Steps to configure

  1. Ingest Source content into the SearchAssist application. 
  2. Integrate LLM with your application.
  3. Enable Generative Model for Answer Snippets.
  4. Train the application. This will generate chunks from the ingested content.  
  5. Open Chunk Browser and view the Answer Index Fields. The Summary View shows some of the important Answer Index Fields like chunkTitle, chunkText, sourceType, sourceName, etc.  You can see all the fields in the JSON view.
  6. Add the chunk properties that you want to use for writing business rules as Index Fields under the Indices tab.  
  7. Go to Business Rules under the Indices tab and create a new rule. 
  8. Enter the name of the rule, add a condition for the rule to be triggered, the outcome of the rule, and click Add. Find more details on how to set the conditions and outcomes here.

Points to remember

  • The name of a business rule designed for Answers should always begin with ‘vi_’.
  • While adding Index Fields, you can also add nested fields, like chunkMeta.sourceUrl. Subsequently, these fields can then be used to define the outcome of the business rules.
  • When using the ‘contains’ operator in the outcome, provide the complete word. 
  • If there are any custom Answer Index Fields that you want to use in your business rule, use the meta_data feature. Meta_data information is available as a chunkMeta field. Find more info on meta_data here. You can also use nested fields to access the parameters in the chunkMeta field. 

Refer to this for detailed descriptions and examples of how to create business rules.