IssueTracker

// Note: This will create a feature request which anybody can view and comment on.

-- Requested enhancement description (What would you like to accomplish?) --
We would like to see an out-of-the-box solution that generates a confidence score based on the answer produced by the Conversational Agent. This would help assess the reliability and accuracy of the responses in real-time.

-- Detailed functionality description (How might it work? What needs to be changed?) --
The solution would involve integrating a mechanism that assigns a confidence score to each generated answer. This score should be based on factors such as the quality of the data, relevance of the answer to the question, and consistency with existing knowledge. We propose that this feature be added to the system as an automatic process without requiring additional manual configuration.

-- If applicable, reasons why alternative solutions are not sufficient --
Currently, we do not have an out-of-the-box solution that generates confidence scores, and existing alternatives require additional manual effort or complex configurations. These solutions do not provide a seamless or automated way to evaluate answer accuracy, which could be a challenge in real-time applications.

-- Other information (workarounds you have tried, documentation consulted, etc) --
We have tried exploring existing documentation and possible workarounds; however, none have addressed this specific need in a manner that suits our use case