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.

Sign up for GitHub

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

Jump to bottom

[FEATURE] wait 60 seconds on HTTP 429 response #524

Open
Polygons1 opened this issue May 2, 2024 · 0 comments · May be fixed by #668
Open

[FEATURE] wait 60 seconds on HTTP 429 response #524

Polygons1 opened this issue May 2, 2024 · 0 comments · May be fixed by #668

Comments

@Polygons1
Copy link

Is your feature request related to a problem? Please describe.

Devika will stop after an HTTP 429 response

Describe the solution you'd like

sleep for 60 seconds on an HTTP 429 response and then retry again

Describe alternatives you've considered

redo the entire project

Additional context

24.05.02 19:16:04: root: ERROR : Error code: 429 - {'error': {'message': 'Rate limit reached for model mixtral-8x7b-32768in organizationPLACEHOLDER on tokens per minute (TPM): Limit 5000, Used 0, Requested ~5597. Please try again in 7.164s. Visit https://console.groq.com/docs/rate-limits for more information.', 'type': 'tokens', 'code': 'rate_limit_exceeded'}}
erkinalp added a commit to erkinalp/devika that referenced this issue Dec 18, 2024
@devin-ai-integration @erkinalp
fix: Implement rate limit handling with 60s wait
73c14f2 
- Add 60-second wait on HTTP 429 responses
- Properly handle Groq API rate limit errors
- Add comprehensive test coverage
- Improve error messaging and logging

Fixes stitionai#524

Co-Authored-By: Erkin Alp Güney <[email protected]>
@erkinalp erkinalp linked a pull request Dec 18, 2024 that will close this issue
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

fix: Implement rate limit handling with 60s wait erkinalp/devika
1 participant
@Polygons1