-
Notifications
You must be signed in to change notification settings - Fork 2
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
predict-drug-target API results in internal server error #3
Comments
This is the API deployed from the GPU server workspace container, it was more for faster training and testing, the idea was to import the prediction endpoint in translator-openpredict, so we don't need to maintain 5 different APIs, and the underlying trained model was not stable (once boost, once random forest), so there might be change to do in the predict function: https://github.com/MaastrichtU-IDS/predict-drug-target/blob/main/src/predict_drug_target/predict.py Also checking if the pretrained model file loaded for prediction is were the code expects it to be Checkout the |
@vemonet thanks for the info! @ensaremirerol can you check the docker logs? |
Pydantic throws validation error when parsing the Response Object
I have no clue where this exceptions starts but I would start checking from the end of that function. Also maybe casting result to its data object might be a good idea in terms of logging result_dict = {"hits": scores_list, "count": len(scores_list)}
try:
result_model = PredictOutput(**result_dict)
except ValidationError as e:
# Logging - print the dict for debugging
except e:
# For other exceptions |
@vemonet
running /predict-drug-target at https://predict-drug-target.137.120.31.160.nip.io/docs#/
with
{
"subjects": ["PUBCHEM.COMPOUND:5329102"]
}
yields an Internal Server Error
did this service ever work? or ideas about what could be happening? thanks!
The text was updated successfully, but these errors were encountered: