Error with calling a machine learning serving endpoint

[notsure]

Hi!

I have registered a spark model and generated a serving endpoint based on that.

I am calling the endpoint with the relevant dataframe, somehow I got below errors. Could anyone show me how to tackle it, please?🙏

"Exception: Request failed with status 400, {"error_code": "BAD_REQUEST", "message": "Encountered an unexpected error while evaluating the model. Verify that the serialized input Dataframe is compatible with the model for inference. Error 'requirement failed: Column features must be of type class org.apache.spark.ml.linalg.VectorUDT:struct<type:tinyint,size:int,indices:array<int>,values:array<double>> but was actually class org.apache.spark.sql.types.StringType$:string.'"}

"

[jose_gonzalez]

Hi,

Can you share the request you are sending/using? please provide a screenshot and more details, so we will be able to provide a solution.

[Kaniz]

Hi @mavis chen​, The error message suggests that the input DataFrame you are passing to the serving endpoint is incompatible with the inference model.

Specifically, it appears that the "features" column in your input DataFrame is StringType, while the model expects it to be VectorUDT.

It would be best to convert the "features" column in your input DataFrame to the correct type.

[Anonymous]

Hi @mavis chen​ 

Thank you for posting your question in our community! We are happy to assist you.

To help us provide you with the most accurate information, could you please take a moment to review the responses and select the one that best answers your question?

This will also help other community members who may have similar questions in the future. Thank you for your participation and let us know if you need any further assistance!