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

1.5.x Release Notes

This document provides information about feature updates and enhancements introduced in various releases in SearchAssist, version 1.5.x.

Version 1.5.3 March 9, 2024

Patch Release

This latest release, SearchAssist v1.5.3, introduces features like customizable web crawling, Insights into Answers, and dynamic recency ranking of documents, designed to improve overall performance and provide greater flexibility to customize the application as required. Below is a description of the changes in this release.

Answer Insights

Harness the power of Answer Insights to gain invaluable insights and refine your application, ultimately striving for improved answers and enhanced user experiences. Dig into the queries directed at your application and the corresponding responses generated to understand and fulfil the gaps. 

Incremental web crawl

Effortlessly update your web sources with the Incremental Web Crawl feature powered by the Ingest Public API. Seamlessly add a new web page without the need to recrawl existing ones. If the page is already present within the source, it undergoes recrawling; otherwise, it’s crawled and added to the source as a new page in addition to the existing pages.

Public API for App details

SearchAssist now enables you to access extensive information about an application via its public APIs. This includes details such as the owner, codevelopers, configured source lists, and other information about the application.

Weighted Recency and Relevancy for Search Results

Ensure that the latest content takes precedence in your search results with the Recency Search feature, available through custom configuration. By incorporating a decay function, this feature reduces the similarity score of documents as they age past a specified benchmark. As a result, the results from older documents are automatically lowered, prioritizing the freshest content and enhancing search relevance. 

Custom Config Crawler

Enhance your efficiency and relevance by using a custom crawler that can exclude specific CSS selectors or XPath expressions. Refine your content by removing unwanted content from your page, like the sidebar, navbar, etc., from the crawl and focus on relevant sections of the page. 

Version 1.5.2 February 3, 2024

Patch Release

SearchAssist, v 1.5.2 brings forth additional features and enhancements aimed to improve overall performance, provide useful insights, and offer greater flexibility. In addition, this update also addresses some critical security issues. Following is the list of some important changes. 

Enhanced Answer Index Efficiency

Answer Index now uses the workbench-processed data to create chunks. This gives you greater flexibility to enhance and enrich the input data before chunks are created from it and used for generating answers. 

JSON view in Chunk Browser

SearchAssist now introduces JSON View in Chunk Browser offering you more visibility into the actual chunks. JSON data provides additional information about the chunks. This can be particularly valuable in understanding specific aspects or content of the chunk metadata.

Auto training for Answer Index with data from connectors

This feature enables auto-training of the Answer Index in the application when the answer snippets are enabled at the time of syncing data with the connector. If Answer snippets are enabled after syncing the data, the application must be trained manually once, autosync will work as expected post that. 

Additional fields to apply Business Rules to Answers

This enhancement allows you to add any metadata from your sources into the chunks. Use the workbench to include the desired data into the chunk field ‘chunkMeta’. Subsequently, you can use this data to apply business rules to your answers and personalize them as required. 

Public API Support for Ingesting File Data

This enhancement offers a new public API to upload files to a SearchAssist application. Invoking the Ingest API after this API can automate the training of the SearchAssist application as well. 

Version 1.5.1 January 21, 2024

Patch Release

SearchAssist v1.5.1 primarily focuses on addressing minor bugs and code enhancements to improve performance.

Version 1.5 December 03, 2023

Minor release

SearchAssist v1.5 introduces several new features to enhance user experience and provide greater flexibility. This update includes support for new connectors and languages and a powerful way to manage the prompts for interacting with LLMs.

To know more about the features and enhancements included in this release, see What’s new in SearchAssist v1.5 .

1.5.x Release Notes

This document provides information about feature updates and enhancements introduced in various releases in SearchAssist, version 1.5.x.

Version 1.5.3 March 9, 2024

Patch Release

This latest release, SearchAssist v1.5.3, introduces features like customizable web crawling, Insights into Answers, and dynamic recency ranking of documents, designed to improve overall performance and provide greater flexibility to customize the application as required. Below is a description of the changes in this release.

Answer Insights

Harness the power of Answer Insights to gain invaluable insights and refine your application, ultimately striving for improved answers and enhanced user experiences. Dig into the queries directed at your application and the corresponding responses generated to understand and fulfil the gaps. 

Incremental web crawl

Effortlessly update your web sources with the Incremental Web Crawl feature powered by the Ingest Public API. Seamlessly add a new web page without the need to recrawl existing ones. If the page is already present within the source, it undergoes recrawling; otherwise, it’s crawled and added to the source as a new page in addition to the existing pages.

Public API for App details

SearchAssist now enables you to access extensive information about an application via its public APIs. This includes details such as the owner, codevelopers, configured source lists, and other information about the application.

Weighted Recency and Relevancy for Search Results

Ensure that the latest content takes precedence in your search results with the Recency Search feature, available through custom configuration. By incorporating a decay function, this feature reduces the similarity score of documents as they age past a specified benchmark. As a result, the results from older documents are automatically lowered, prioritizing the freshest content and enhancing search relevance. 

Custom Config Crawler

Enhance your efficiency and relevance by using a custom crawler that can exclude specific CSS selectors or XPath expressions. Refine your content by removing unwanted content from your page, like the sidebar, navbar, etc., from the crawl and focus on relevant sections of the page. 

Version 1.5.2 February 3, 2024

Patch Release

SearchAssist, v 1.5.2 brings forth additional features and enhancements aimed to improve overall performance, provide useful insights, and offer greater flexibility. In addition, this update also addresses some critical security issues. Following is the list of some important changes. 

Enhanced Answer Index Efficiency

Answer Index now uses the workbench-processed data to create chunks. This gives you greater flexibility to enhance and enrich the input data before chunks are created from it and used for generating answers. 

JSON view in Chunk Browser

SearchAssist now introduces JSON View in Chunk Browser offering you more visibility into the actual chunks. JSON data provides additional information about the chunks. This can be particularly valuable in understanding specific aspects or content of the chunk metadata.

Auto training for Answer Index with data from connectors

This feature enables auto-training of the Answer Index in the application when the answer snippets are enabled at the time of syncing data with the connector. If Answer snippets are enabled after syncing the data, the application must be trained manually once, autosync will work as expected post that. 

Additional fields to apply Business Rules to Answers

This enhancement allows you to add any metadata from your sources into the chunks. Use the workbench to include the desired data into the chunk field ‘chunkMeta’. Subsequently, you can use this data to apply business rules to your answers and personalize them as required. 

Public API Support for Ingesting File Data

This enhancement offers a new public API to upload files to a SearchAssist application. Invoking the Ingest API after this API can automate the training of the SearchAssist application as well. 

Version 1.5.1 January 21, 2024

Patch Release

SearchAssist v1.5.1 primarily focuses on addressing minor bugs and code enhancements to improve performance.

Version 1.5 December 03, 2023

Minor release

SearchAssist v1.5 introduces several new features to enhance user experience and provide greater flexibility. This update includes support for new connectors and languages and a powerful way to manage the prompts for interacting with LLMs.

To know more about the features and enhancements included in this release, see What’s new in SearchAssist v1.5 .