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

Index Languages

SearchAssist offers multilingual support that allows you to enhance your customer experience. SearchAssist not only allows you to add and index content in any of the supported languages but can also interpret user queries in the supported and enabled index languages, search through content in those languages, and even, present both search results and answer snippets in the same language as that of the user query.  

The following table lists the languages supported by SearchAssist currently for search results and answer snippets.

Languages Search Results  Answer Snippets – Generative Model Answer Snippets – Extractive Model
English Yes Yes Yes
Japanese Yes Yes Yes
Korean Yes Yes Yes
French Yes Yes Yes
Spanish Yes Yes Yes
Polish Yes Yes Yes
German Yes Yes Yes
Indonesian Yes Yes Yes
Turkish Yes Yes Yes
Italian Yes Yes Yes
Dutch Yes Yes Yes

To enable support for one or more of these languages, go to Index Settings under the Indices tab.  This page lists the languages enabled for the application. By default, English is always enabled. To add another language support to your app or remove one, click Add Language, select the languages to be supported, and click Save.

Whenever a language support is added or removed, the application is auto-trained to interpret the language. If specific language support is removed from the Index languages but the content in the language is still managed by SearchAssist, in that case, the language analyzer of the language identified as the default language is used to interpret the content. In such a scenario, the quality of the results can get affected.

Note:

  • You can only enable a maximum of four supported languages at a time in a given index configuration.
  • If a non-English language is added and the Generative snippets are enabled, the embeddings model is changed internally and new vector embeddings are generated. This will modify any previously generated answers for the English language. Hence, it is recommended to verify the answers generated for previously added content again.
  • The search functionality is most optimized for the English language, i.e. when both the query and the relevant documents are in the English language. For example:
    • Query (English): What is the capital of France?
    • Content(English): The capital of France is Paris.
  • SearchAssist supports multi-lingual searches when the query and the content containing the answer are in the same language. For example:
    • Query(French): Quelle est la capitale de la France?
    • Content(French) La capitale de la France est Paris.
  • SearchAssist does not support use cases where the search query is in a different language than the relevant content.
    • Query(English): What is the capital of France?
    • Content(French): La capitale de la France est Paris.

Index Languages

SearchAssist offers multilingual support that allows you to enhance your customer experience. SearchAssist not only allows you to add and index content in any of the supported languages but can also interpret user queries in the supported and enabled index languages, search through content in those languages, and even, present both search results and answer snippets in the same language as that of the user query.  

The following table lists the languages supported by SearchAssist currently for search results and answer snippets.

Languages Search Results  Answer Snippets – Generative Model Answer Snippets – Extractive Model
English Yes Yes Yes
Japanese Yes Yes Yes
Korean Yes Yes Yes
French Yes Yes Yes
Spanish Yes Yes Yes
Polish Yes Yes Yes
German Yes Yes Yes
Indonesian Yes Yes Yes
Turkish Yes Yes Yes
Italian Yes Yes Yes
Dutch Yes Yes Yes

To enable support for one or more of these languages, go to Index Settings under the Indices tab.  This page lists the languages enabled for the application. By default, English is always enabled. To add another language support to your app or remove one, click Add Language, select the languages to be supported, and click Save.

Whenever a language support is added or removed, the application is auto-trained to interpret the language. If specific language support is removed from the Index languages but the content in the language is still managed by SearchAssist, in that case, the language analyzer of the language identified as the default language is used to interpret the content. In such a scenario, the quality of the results can get affected.

Note:

  • You can only enable a maximum of four supported languages at a time in a given index configuration.
  • If a non-English language is added and the Generative snippets are enabled, the embeddings model is changed internally and new vector embeddings are generated. This will modify any previously generated answers for the English language. Hence, it is recommended to verify the answers generated for previously added content again.
  • The search functionality is most optimized for the English language, i.e. when both the query and the relevant documents are in the English language. For example:
    • Query (English): What is the capital of France?
    • Content(English): The capital of France is Paris.
  • SearchAssist supports multi-lingual searches when the query and the content containing the answer are in the same language. For example:
    • Query(French): Quelle est la capitale de la France?
    • Content(French) La capitale de la France est Paris.
  • SearchAssist does not support use cases where the search query is in a different language than the relevant content.
    • Query(English): What is the capital of France?
    • Content(French): La capitale de la France est Paris.