Hi, I have created a project on Dataiku which uses a bunch of csv files as inputs. This is a prediction model written in Python, however uses a totally different approach and not based on regression, classification etc. On the flow, its based on using Python recipes and I also have a dashboard off of the recipe outputs. I now want other users to be able to score new cases without providing access to the code. What is the best way to make a API that would allow me to score a new case, using the previously referenced csv files?
I have looked at documentation on both "managed folder" as well as "enriching prediction queries" but they don't answer if it is possible to reference csv files from the usual "Dataiku flow" within an API. Would appreciate if you can share your insight.
You would want either a fully custom "Python function" kind of API endpoint, or if your system remains close in spirit to a regular classifier, a "Custom Python prediction" enpdoint.
Both kinds of endpoints can access the data of a managed folder. You should put your CSV files into that managed folder. When you create the API Service package, the contents of the managed folder is taken with it, and your API endpoint code can reference it.
For more details, please see: https://doc.dataiku.com/dss/latest/apinode/endpoint-python-prediction.html#using-a-managed-folder https://doc.dataiku.com/dss/latest/apinode/endpoint-python-function.html#using-managed-folders