Using Dataiku

Hello all,

i am still looking for a solution to my problem. I have the following Jupyter Notebook:

import dataiku

import pickle

import pandas as pd

from sklearn.feature_extraction.text import TfidfVectorizer

from sklearn.metrics.pairwise import cosine_similarity

import dataikuapi



def load_data(folder_name="Recommender"):

    managed_folder = dataiku.Folder(folder_name)



    with managed_folder.get_download_stream("cosine_similarity.pkl") as stream:

        cosine_sim = pickle.load(stream)



    with managed_folder.get_download_stream("tfidf_vectorizer.pkl") as stream:

        vectorizer = pickle.load(stream)


    with managed_folder.get_download_stream("tfidf_matrix.pkl") as stream:

        X_tfidf = pickle.load(stream)  



    sachnummer = dataiku.Dataset("LTM_prep")

    df = sachnummer.get_dataframe()

    df.drop(['lieferant_name', 'lieferant_ort', 'LIEFERANT_NAME_ORT', 'LT_GEBINDE_NUMMER', 'MDI'], axis=1, inplace=True)


    return cosine_sim, vectorizer, X_tfidf, df



def recommend_filtered1(input_bennenung, vectorizer, X_tfidf, df, top_n=10):

    try:

        if not input_bennenung:

            return {"error": "Die Eingabe-Benennung darf nicht leer sein."}


        input_bennenung = input_bennenung.upper()

        input_vector = vectorizer.transform([input_bennenung])  

        similarities = cosine_similarity(input_vector, X_tfidf).flatten()  


        top_indices = similarities.argsort()[-top_n:][::-1]

        recommendations = [

            {"test": df.iloc[idx]['test'],

             "test2": df.iloc[idx]['test2'],

             "SIMILARITY_SCORE": round(similarities[idx], 2)}

            for idx in top_indices if similarities[idx] > 0

        ]


        return recommendations if recommendations else {"message": "Keine ähnlichen Benennungen gefunden."}

    except Exception as e:

        return {"error": f"Fehler: {str(e)}"}



def recommend_from_input(input_bennenung):


    folder_name = "Recommender"  


    if not input_bennenung:

        return {"error": "Fehlender Parameter 'input_bennenung'"}


    try:

        # Lade alle benötigten Objekte

        cosine_sim, vectorizer, X_tfidf, df = load_data(folder_name)  


        # Empfehlung berechnen

        return recommend_filtered1(input_bennenung, vectorizer, X_tfidf, df)

    except Exception as e:

        return {"error": f"Fehler beim Laden der Daten oder der Empfehlung: {str(e)}"}

and want to call the method recommend_from_input from it. I am in the API Designer. I have a managed folder called "Recommender," which I can also see in the Flow. The structure im Folder is

Unter Folder Settings i see type is Amazon S3 and i have a setted connection and see also the path in bucket. So when i call def recommend_from_input(input_bennenung): return input_bennenung in the api designer code section with the test query

{

"input_bennenung": "Stern"

}

there are no errors and i get "Stern back". So now i just pasted my notebook code in the api designer code Section and when i run it there is a error:

Result: 

{"error":"Fehler beim Laden der Daten oder der Empfehlung: Default project key is not specified (no DKU_CURRENT_PROJECT_KEY in env)"}

In the logs are no errors only info and debug.

I would appreciate any help. I have already read the documentation on Exposing Python Functions, but I still don't know where my mistake is.