Sign up to take part
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
Hello,
I have an end point for a prediction model that's supposed to receive the input directly from the UI. is there a way I can modify the way the API handles the request? because the data sent from the UI needs some refining before the model can process the request.
Operating system used: Windows 11
Hi @rawan_mohammed ,
You may need to use different endpoints to achieve what you are looking for here if the data preparation steps (in the โScriptโ tab) included in the endpoint are not sufficient.
https://doc.dataiku.com/dss/latest/apinode/enrich-prediction-queries.html
https://knowledge.dataiku.com/latest/courses/mlops/real-time-apis/endpoints-and-enrichments.html
You can also use a custom python endpoint to sanitize the input for the prediction endpoint and call the prediction endpoint from this endpoint.
https://doc.dataiku.com/dss/latest/apinode/api/endpoints-api.html#calling-another-endpoint
Thanks
Hi @rawan_mohammed ,
You may need to use different endpoints to achieve what you are looking for here if the data preparation steps (in the โScriptโ tab) included in the endpoint are not sufficient.
https://doc.dataiku.com/dss/latest/apinode/enrich-prediction-queries.html
https://knowledge.dataiku.com/latest/courses/mlops/real-time-apis/endpoints-and-enrichments.html
You can also use a custom python endpoint to sanitize the input for the prediction endpoint and call the prediction endpoint from this endpoint.
https://doc.dataiku.com/dss/latest/apinode/api/endpoints-api.html#calling-another-endpoint
Thanks