cancel
Showing results for 
Search instead for 
Did you mean: 
Machine Learning
cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

Charley
by New Contributor II
  • 3900 Views
  • 1 replies
  • 1 kudos

error status 400 calling serving model endpoint invocation using personal access token on Azure Databricks

Hi all, I've deployed a model, moved it to production and served it (mlflow), but when testing it in the python notebook I get a 400 error. code/details below:import osimport requestsimport jsonimport pandas as pdimport numpy as np# Create two record...

  • 3900 Views
  • 1 replies
  • 1 kudos
Latest Reply
nakany
New Contributor II
  • 1 kudos

data_json in the score_model function should be defined as followsds_dict = {"dataframe_split": dataset.to_dict(orient='split')} if isinstance(dataset, pd.DataFrame) else create_tf_serving_json(dataset)

  • 1 kudos
User16753724663
by Valued Contributor
  • 5040 Views
  • 1 replies
  • 0 kudos

Error importing pip package s3fs

A job recently began failing with the following error when a python notebook imports the pip package s3fs.ImportError: cannot import name 'maybe_sync' from 'fsspec.asyn' (/databricks/python/lib/python3.8/site-packages/fsspec/asyn.py)   ImportError Tr...

  • 5040 Views
  • 1 replies
  • 0 kudos
Latest Reply
User16753724663
Valued Contributor
  • 0 kudos

While checking the init script is installing the s3fs version 0.5.2.This version has issues at the moment from the pypi. I have tested version 0.6.0 that works fine. please change your requirement.txt file with a newer version of s3fs. Below is the p...

  • 0 kudos
Labels