Open joaopcm1996 opened 2 years ago
AsyncPredictor
uses the predict_async
method to make an asynchronous prediction. It starts by upload data to input_path
, then calls invoke_endpoint_async
with this input_path
.
Solution: add input_path
and async_predictor.predict(data =data, input_path= input_path)
Describe the bug In the SageMaker SDK, if no name is given to an
AsyncPredictor
, and you call.predict_async(data)
withdata
and not aninput_path
, the SDK errors out.To reproduce Deploy an async endpoint, wrap the resulting predictor with sagemaker.predictor_async.AsyncPredictor, and do not give it a name. Then call
.predict_async
on thatAsyncPredictor
, passing it actualdata
instead of an S3input_path
. As the SDK tries to use the async predictor's name to create a key to upload the input data, it fails because there is no name.Error Logs
System information