-
Notifications
You must be signed in to change notification settings - Fork 43
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
Chapter10: seldon_core.wrapper:handle_invalid_usage:60 - ERROR: {'status': {'status': 1, 'info': 'Invalid request data type: #15
Comments
Hi, @aquynh1682! |
Hi, @webmakaka! |
Something wrong with sending metrics. But there also was wrong name for Prometheus Data Source in the book. Should be (I think) Configuration -> Data sources -> Prometheus
|
I has change name datasource same for you, but it not sending metrics. I think, I should try deploying grafana and prometheus to another namespace and I'll will redefine the value myself. |
If you find how to fix, please share info. |
Hi @webmakaka, I had resolved setup tool monitor seldon in chapter 10. You should try changing |
OK! Thanks! |
There is another book with errors. [Book][Trevor Grant, Holden Karau, Boris Lublinsky, Richard Liu, Ilan Filonenko] Kubeflow for Machine Learning From Lab to Production [ENG, 2020] If you are interested in, go to discuss in their issues page. (Main error was - I didn't find data from apache org website what needed for successful completion) |
Thank you sharing for me this book. Could you please send me the GitHub link or pdf file? |
Ok. Send me your email address. |
You can send it to me via email: nm.quynh1608@gmail.com. Thanks you. |
Hey @aquynh1682 and @webmakaka, let me know if this issue is resolved and can be closed. |
Hi, @rajat-packt |
Thanks @webmakaka for letting us know about this. |
Hi, @rajat-packt And if you want mention file from my repo, is OK! |
Hello everyone, it's me again :)))
I have resolved the previous errors I encountered. Currently, in this chapter 10, I have successfully executed the pipeline build and push. After a successful deployment, I tried to call the model (I used both curl and Postman), but it encountered an error. Below is the error log I encountered and the command to call the model.
call model with curl:
curl -vvvvk --header "content-type: application/json" -X POST -d @data.json https://yourdomain.com/api/v1.0/predictions; done
and response:
Seldon-core Logs:
The text was updated successfully, but these errors were encountered: