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

504 gateway time-out error #23

Open
yy6linda opened this issue Feb 18, 2022 · 1 comment
Open

504 gateway time-out error #23

yy6linda opened this issue Feb 18, 2022 · 1 comment
Assignees
Labels
Bug Something isn't working

Comments

@yy6linda
Copy link
Member

Problem description

504 gateway time-out error received when sending notes to running phi-annotator-neuroner. Encountered the same error in both UI and using nlpsandbox python client for note annotation.

Reason: Gateway Time-out
HTTP response headers: HTTPHeaderDict({'Server': 'nginx/1.19.6', 'Date': 'Fri, 18 Feb 2022 05:12:20 GMT', 'Content-Type': 'text/html', 'Content-Length': '167', 'Connection': 'keep-alive'})
HTTP response body: <html>
<head><title>504 Gateway Time-out</title></head>
<body>
<center><h1>504 Gateway Time-out</h1></center>
<hr><center>nginx/1.19.6</center>
</body>
</html>
@yy6linda yy6linda added the Bug Something isn't working label Feb 18, 2022
@yy6linda yy6linda assigned yy6linda and tschaffter and unassigned yy6linda Feb 18, 2022
@yy6linda
Copy link
Member Author

The main issue is it takes a long time for neuroner to load pre-trained model and initiate itself before getting ready to process input data and generate responses, leading to "504 gateway" error. But after loading the pre-trained models, neuroner can generate responses in an expected manner. It's always the first request that led to "504 gateway" error. Neuroner needs to be initiated(including loading the pre-trained models) before receiving the first input data.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Bug Something isn't working
Projects
None yet
Development

No branches or pull requests

3 participants