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

Index Fields

Searching for relevant content in the ingested data can be a slow and inefficient process. But SearchAssist indexes the source data. Indexing is like organizing the data for quick and relevant search retrieval.  It stores the ingested data as field and value pairs. Index fields are like the schema of a database and define the data stored with SearchAssist. You can customize index configuration to train SearchAssist to return results as per your requirements. 

Based on the difference in the way ingested content is indexed for search results and answers, there are two sets of pre-defined index fields – one for the Search Index and one for the Answer Index (corresponding to the chunks generated). You can find the list of default index fields here. You can modify and delete existing fields or add new fields relevant to your ingested data. For your unstructured data, it is recommended to add the index fields so that content from those fields can be searched and displayed in the results. 

To view the existing index fields, go to the Index Fields in the Index Configuration page under the Indices tab. 

Add Index Fields

To add a new field, use the Add Field button on the top right corner and enter the following fields.

Field Description
Field Name Name of the field. Naming conventions: 

  • A field name must start with a letter or an underscore character (_).
  • A field name cannot start with a digit.
  • A field name can only contain alpha-numeric characters and underscores (a-z, A-Z, 0-9, and _ ).
  • Field names are case-sensitive (age, Age, and AGE are three different variables).
  • A field name length cannot be more than 30 characters.
  • A field name cannot contain spaces.
Field Type Select the type of the field. 
Searchable Select if the content of the field is to be made searchable. It is important to determine the set of fields that are to be made as searchable as too many searchable fields can reduce the efficiency of the search process as well as affect the quality of the search. For example, it may be useful to add the name and description fields for a product as searchable. At the same time, a URL pointing to the image of the product may not be relevant as a searchable field but may be required to display the image in the results. 
Auto Suggest Select if the content of the field is to be used for autosuggestions. Auto-suggest displays query suggestions to the user based on the inputs so far. It is recommended to enable the auto-suggest feature for fields like product name, brand, etc. where the value can be one from the given set or catalog. Marking fields like URLs for autosuggest may not be useful as these kinds of fields are unique and auto-suggest may result in too many results for the user.

 

Click Add to save the field. 

Edit Index Fields

To edit or delete an existing field, go to the field and use the buttons against the field name to take the action. 

Note that you cannot edit or delete the system fields (index fields with the prefix sys_).

Index Fields

Searching for relevant content in the ingested data can be a slow and inefficient process. But SearchAssist indexes the source data. Indexing is like organizing the data for quick and relevant search retrieval.  It stores the ingested data as field and value pairs. Index fields are like the schema of a database and define the data stored with SearchAssist. You can customize index configuration to train SearchAssist to return results as per your requirements. 

Based on the difference in the way ingested content is indexed for search results and answers, there are two sets of pre-defined index fields – one for the Search Index and one for the Answer Index (corresponding to the chunks generated). You can find the list of default index fields here. You can modify and delete existing fields or add new fields relevant to your ingested data. For your unstructured data, it is recommended to add the index fields so that content from those fields can be searched and displayed in the results. 

To view the existing index fields, go to the Index Fields in the Index Configuration page under the Indices tab. 

Add Index Fields

To add a new field, use the Add Field button on the top right corner and enter the following fields.

Field Description
Field Name Name of the field. Naming conventions: 

  • A field name must start with a letter or an underscore character (_).
  • A field name cannot start with a digit.
  • A field name can only contain alpha-numeric characters and underscores (a-z, A-Z, 0-9, and _ ).
  • Field names are case-sensitive (age, Age, and AGE are three different variables).
  • A field name length cannot be more than 30 characters.
  • A field name cannot contain spaces.
Field Type Select the type of the field. 
Searchable Select if the content of the field is to be made searchable. It is important to determine the set of fields that are to be made as searchable as too many searchable fields can reduce the efficiency of the search process as well as affect the quality of the search. For example, it may be useful to add the name and description fields for a product as searchable. At the same time, a URL pointing to the image of the product may not be relevant as a searchable field but may be required to display the image in the results. 
Auto Suggest Select if the content of the field is to be used for autosuggestions. Auto-suggest displays query suggestions to the user based on the inputs so far. It is recommended to enable the auto-suggest feature for fields like product name, brand, etc. where the value can be one from the given set or catalog. Marking fields like URLs for autosuggest may not be useful as these kinds of fields are unique and auto-suggest may result in too many results for the user.

 

Click Add to save the field. 

Edit Index Fields

To edit or delete an existing field, go to the field and use the buttons against the field name to take the action. 

Note that you cannot edit or delete the system fields (index fields with the prefix sys_).