If you need help troubleshooting Domino Models:
You might see this error with Python endpoints if you return values that are NumPy objects, rather than native Python primitives.
To fix this, convert your NumPy values to Python primitives.
Domino recommends that you call numpy.asscalar
to do this.
The result of your endpoint function gets serialized to JSON before being sent in the response.
However some object types, such as Decimal or certain NumPy data types, are not JSON serializable by default.
For Decimal data types, cast the Decimal type to a Float type.
For NumPy data types, convert the values to Python primitives.
An easy way to do this is to call numpy.asscalar
as described above.
You might encounter this and other storage related errors in the build log when your model is too large. Models are limited to 500MB. If your project includes a large trained model dataset then Domino recommends that you exclude this upon publishing a new version of your model.