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

Improve error handling #723

Merged
merged 14 commits into from
Feb 6, 2025
Merged

Improve error handling #723

merged 14 commits into from
Feb 6, 2025

Conversation

danielaskdd
Copy link
Contributor

@danielaskdd danielaskdd commented Feb 6, 2025 •
edited
Loading

Improve error handling, especially when LLM service is unstable:

  • Check if LLM response with None value, and retry if necessary.
  • Add error logs for each retry.
  • Send 'done' status to client when streaming is canceled before finish in Ollama API.
  • Improve timing accuracy for Ollama API
  • Increase timeout value for unit test.
  • Refactor concurrent unit test.

@danielaskdd
Merge branch 'main' into improve-error-handling
b21d388
@danielaskdd
refactor: enhance stream error handling and optimize code structure
e26c6e5 
- Initialize timestamps at start to avoid null checks
- Add detailed error handling for streaming response
- Handle CancelledError and other exceptions separately
- Unify exception handling with trace_exception
- Clean up redundant code and simplify logic
@danielaskdd
Fix linting
65dc0a6
@danielaskdd
Add error handling and improve logging for concurrent request testing
9242f16 
• Added McpError and ErrorCode classes
• Added detailed error collection logic
• Improved error reporting & formatting
• Added request ID tracking
• Enhanced test results visibility
@danielaskdd
Fix linting
e49d366
@danielaskdd
Fix timing calculation logic in OllamaAPI stream generators
e124ad7 
• Initialize first_chunk_time as None
• Set timing only when first chunk arrives
@danielaskdd
fix: improve timing accuracy and variable scoping in OllamaAPI
9103e7f
@danielaskdd
Enhance OpenAI API error handling and logging for better reliability
506e39e 
• Add InvalidResponseError custom exception
• Improve error logging for API failures
• Add empty response content validation
• Add more detailed debug logging info
• Add retry for invalid response cases
@danielaskdd
Update timeout and max_retries for unit tests
6ca7487
@danielaskdd
Add LightRAG version to User-Agent header for better request tracking
2760433 
• Add User-Agent header with version info
• Update header creation in Ollama client
• Update header creation in OpenAI client
• Ensure consistent header format
• Include Mozilla UA string for OpenAI
@danielaskdd
Merge tag 'time-temp' into improve-ollama-api-streaming
81377da
@danielaskdd
Remove Chinese comments and added English comments for clarity
c838229
@danielaskdd
Fix linting
8fdba5d
@danielaskdd
Merge branch 'main' into improve-ollama-api-streaming
349dcf7
@danielaskdd danielaskdd marked this pull request as ready for review February 6, 2025 17:03
@LarFii LarFii merged commit 0005462 into HKUDS:main Feb 6, 2025
1 check passed
@danielaskdd danielaskdd deleted the improve-ollama-api-streaming branch February 10, 2025 10:09
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@danielaskdd @LarFii