Skip to content

Conversation

@nishika26
Copy link

This PR introduces a maximum latency limit (MAX_LATENCY = 90 seconds) to the response generation process using a ThreadPoolExecutor. If a response takes longer than the defined threshold, it is automatically timed out and excluded from the final output.

This ensures that no outlier responses with high latency are included in the final response.json

@nishika26 nishika26 self-assigned this Jun 12, 2025
@nishika26
Copy link
Author

@EdmundKorley can you review this pr

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 this pull request may close these issues.

2 participants