Create Serving Endpoint with JAVA Runtime

prafull — Sat, 02 Mar 2024 09:39:23 GMT

Hello,

Trying to create a custom serving endpoint, using artifacts argument while logging the run/model to save .jar files. These files are called during when calling .predict.

JAVA runtime 8 or higher is required to run the jar file, not sure how to create a serving endpoint that will have JAVA runtime.

# Model wrapper class

#this model will give prob of all classes, prediction, predictio prob

class ModelWrapper_custom_DataRobot_To_Linesense(mlflow.pyfunc.PythonModel😞

# Initialize model in the constructor

def __init__(self, model😞

self.model = model

# Prediction function

def predict(self, context, model_input😞

model = ScoringCodeModel(context.artifacts['model_jar'])

model_output = model.predict(model_input)

df_temp = pd.DataFrame()

#Extract Probability values for selected prediction

df_temp['prediction_probability'] = model_output.max(axis=1)

# Find the column with maximum probability for each row

df_temp['prediction'] = model_output.idxmax(axis=1)

#remove NAN, this is required to avoid error in max find

df_temp = df_temp.dropna()

# Extract the middle value from the 'prediction' column

df_temp['prediction'] = df_temp['prediction'].apply(lambda x: x.split('_')[1])

#return

return df_temp.to_json(orient='records')

This is a simplified version of model wrapper, when serving endpoint is deployed it cannot infer due to java runtime missing.

topic Create Serving Endpoint with JAVA Runtime in Machine Learning

Create Serving Endpoint with JAVA Runtime