Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Enhance Error Messaging by Specifying Failure in STT, TTS, or LLM Components #430

Closed
Ashesh3 opened this issue Jan 5, 2024 · 6 comments · Fixed by #491
Closed

Enhance Error Messaging by Specifying Failure in STT, TTS, or LLM Components #430

Ashesh3 opened this issue Jan 5, 2024 · 6 comments · Fixed by #491
Assignees

Comments

@Ashesh3
Copy link
Member

Ashesh3 commented Jan 5, 2024

Our current error messages are verbose and lack clarity in pinpointing the exact component failure, whether it's Speech-to-Text (STT), Text-to-Speech (TTS), or Language Learning Models (LLM). We need to improve our error handling to provide more user-friendly and specific error messages.

Problem Statement:

  • Current Behavior: Error messages are too verbose and do not specify which part of the process (STT, TTS, or LLM) failed.
  • Impact: This lack of clarity can be confusing for users and makes troubleshooting more difficult for our support and development teams.

Proposed Solution:

  1. Implement Component-Specific Error Messages: Revise our error handling mechanism to include component-specific tags or identifiers (STT, TTS, LLM) in the error messages.
  2. Simplify Error Language: Make the error messages less technical and more understandable to a general audience.

Goals:

  • Clearly identify which component (STT, TTS, or LLM) the error originated from.
  • Make error messages concise and easy to understand for users without technical backgrounds.
  • Assist in faster diagnosis and resolution of issues by our support and development teams.

Additional Notes:

  • This improvement is part of our ongoing efforts to enhance user experience and streamline support processes.
  • We should ensure that these changes do not affect the underlying error handling and logging capabilities.
@Ashesh3 Ashesh3 self-assigned this Feb 14, 2024
@MAVRICK-1
Copy link

is this issue still open can you assign me this ?

@Ashesh3
Copy link
Member Author

Ashesh3 commented Feb 21, 2024

@MAVRICK-1 Hey, yes the issue is still open. The frontend changes are done and its ready to accept the error along with the point of failure, all you have to do is return the error along with the component which failed from the backend side.

Example:
STT: Failed to transcribe voice
LLM: Failed to connect to openai

etc.

@Ashesh3 Ashesh3 assigned MAVRICK-1 and unassigned Ashesh3 Feb 21, 2024
@Ashesh3
Copy link
Member Author

Ashesh3 commented Mar 6, 2024

@MAVRICK-1 any updates on this issue?

@MAVRICK-1
Copy link

@MAVRICK-1 any updates on this issue?

Sorry, My exams are going on , I wasn't able to look at it . You can assign this to anyone else.

@Ashesh3
Copy link
Member Author

Ashesh3 commented Mar 6, 2024

No worries, I'll keep you assigned till someone else wants to take this up. Feel free to unassign yourself if you are no longer interested to work on this.

@aeswibon
Copy link
Member

@Ashesh3 I would like to work if Mavrick is not working on it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

3 participants