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

Answer Insights

Answer insights provide valuable information about the use of the Answer feature by the users. It provides you with a comprehensive view of the user’s interaction with the application. You can see both the successful or unsuccessful answers presented to the users, along with any unanswered queries by the application. You can use this information to understand user behavior and queries, perform response analysis, identify gaps, and accordingly optimize the application response.

Accessing Answer Insights

You can view the user queries and answers generated by the application on the Answer Insights page under the Analytics tab.

Filtering Options

You can filter the analytics data based on the following parameters:

  • Index Configuration: You can choose the index configuration corresponding to which you want to view the data. 
  • Type of Answer Model: You can choose to see the analytics corresponding to Extractive or Generative Models of Answer Generation. You can also select ‘Both’ to view all the answers at once. 
  • Date Range: You can choose to view the data from the last 24 hrs, or the last 7 days or also provide a custom date range for the data to be displayed. However, note that you can only view the data for a maximum of 30 days at a time. 

Answer Analytics

Based on the filters set for the data, the application displays the following data in two different tabs:

  1. Queries with Answers: This section lists all the queries directed to the application for which the application was able to find and display answers. If the same query is posted more than once, it is displayed only once in this list but the count is increased accordingly. 
    • Query – User query posted to the application
    • Answer – The corresponding answer provided to the user by the application
    • Count – The number of times the given query was posted and the corresponding answer was provided as a response during the selected period. Note that the count is increased only when the same answer is presented to the same question. If the answer varies, the query is listed as a new one. 
    • Thumbs up – Count of the number of times the answer was acknowledged positively. 
    • Thumbs down – Count of the number of times the answer was acknowledged negatively.

      Note that the feedbacks are displayed(Thumbs up and Thumbs down) only if the Feedback option is enabled for Answers in the Search Interface.

  • 2. Queries without Answers: This section lists all the queries directed to the application for which the application was unable to find any answers. 
    • Query – User query posted to the application
    • Count – Number of times the query was posted in the selected time duration

Viewing Answer Details

Click on any of the records to see the details.

The details of an answer are presented in three different tabs:

Summary tab gives an overview of the answer generated. The following details are displayed on this tab. 

Answer The answer displayed to the user in response to the query. 
Documents Related source documents or citations
Type Type of answer generation model – Extractive or Generative
Model  LLM Model used in case of Generative Answers
Date Date of query
Feedback Feedback provided by the user for the generated answer
Reason Reason of the feedback given
Comments Comments provided by the user along with the feedback. 

Qualified Chunks tab lists the chunks used for answer generation. It shows the qualified chunks, top chunks sent to the LLM and chunks used for answering. 

LLM Request and Response tab shows the configuration used for Generative answers, the prompt sent as a request to the LLM, and the response sent back by the LLM.  


Click on the JSON view to see all the details in JSON format.

Answer Insights

Answer insights provide valuable information about the use of the Answer feature by the users. It provides you with a comprehensive view of the user’s interaction with the application. You can see both the successful or unsuccessful answers presented to the users, along with any unanswered queries by the application. You can use this information to understand user behavior and queries, perform response analysis, identify gaps, and accordingly optimize the application response.

Accessing Answer Insights

You can view the user queries and answers generated by the application on the Answer Insights page under the Analytics tab.

Filtering Options

You can filter the analytics data based on the following parameters:

  • Index Configuration: You can choose the index configuration corresponding to which you want to view the data. 
  • Type of Answer Model: You can choose to see the analytics corresponding to Extractive or Generative Models of Answer Generation. You can also select ‘Both’ to view all the answers at once. 
  • Date Range: You can choose to view the data from the last 24 hrs, or the last 7 days or also provide a custom date range for the data to be displayed. However, note that you can only view the data for a maximum of 30 days at a time. 

Answer Analytics

Based on the filters set for the data, the application displays the following data in two different tabs:

  1. Queries with Answers: This section lists all the queries directed to the application for which the application was able to find and display answers. If the same query is posted more than once, it is displayed only once in this list but the count is increased accordingly. 
    • Query – User query posted to the application
    • Answer – The corresponding answer provided to the user by the application
    • Count – The number of times the given query was posted and the corresponding answer was provided as a response during the selected period. Note that the count is increased only when the same answer is presented to the same question. If the answer varies, the query is listed as a new one. 
    • Thumbs up – Count of the number of times the answer was acknowledged positively. 
    • Thumbs down – Count of the number of times the answer was acknowledged negatively.

      Note that the feedbacks are displayed(Thumbs up and Thumbs down) only if the Feedback option is enabled for Answers in the Search Interface.

  • 2. Queries without Answers: This section lists all the queries directed to the application for which the application was unable to find any answers. 
    • Query – User query posted to the application
    • Count – Number of times the query was posted in the selected time duration

Viewing Answer Details

Click on any of the records to see the details.

The details of an answer are presented in three different tabs:

Summary tab gives an overview of the answer generated. The following details are displayed on this tab. 

Answer The answer displayed to the user in response to the query. 
Documents Related source documents or citations
Type Type of answer generation model – Extractive or Generative
Model  LLM Model used in case of Generative Answers
Date Date of query
Feedback Feedback provided by the user for the generated answer
Reason Reason of the feedback given
Comments Comments provided by the user along with the feedback. 

Qualified Chunks tab lists the chunks used for answer generation. It shows the qualified chunks, top chunks sent to the LLM and chunks used for answering. 

LLM Request and Response tab shows the configuration used for Generative answers, the prompt sent as a request to the LLM, and the response sent back by the LLM.  


Click on the JSON view to see all the details in JSON format.