Model monitoring issues for Databricks Trainied Model and deployed in Sagemaker

[Gopi0403]

We have trined the model in Databricks and Deployed in SageMaker. After deployment, We set the baseline for the model and enable model monitoring. 

After enabling the data capture for the SageMaker endpoint, we receive the following error when we do the invocation request.

Latest execution status: Failed

Latest execution result: Error: Encoding mismatch: Encoding is CSV for endpointInput, but Encoding is JSON for endpointOutput. We currently only support the same type of input and output encoding at the moment.

Please Note: We are receiving this error for any model trained in Databricks. Any help / pointers on this issue would be really great.  

Thanks in Advance. 

[Kaniz_Fatma]

Hi @ Gopi0403 ! My name is Kaniz, and I'm the technical moderator here. Great to meet you, and thanks for your question! Let's see if your peers in the community have an answer to your question first. Or else I will get back to you soon. Thanks.

[Kaniz_Fatma · Accepted solution]

Hi @Gopichandran N​ , This link might help you:-https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpointConfig.html