df.show()
label   prediction                 probability
  0           0           [1,2,[],[0.7558548984793847,0.2441451015206153]]
  0           0           [1,2,[],[0.5190322149055472,0.4809677850944528]]
  0           1           [1,2,[],[0.4884140358521083,0.5115859641478916]]
  0           1           [1,2,[],[0.4884140358521083,0.5115859641478916]]
  1           1           [1,2,[],[0.40305518381637956,0.5969448161836204]]
  1           1           [1,2,[],[0.40570407426458577,0.5942959257354141]]

# The probability column is VectorUDT and looks like an array of dim 4 that contains probabilities of predicted variables I want to retrieve
df.schema
StructType(List(StructField(label,DoubleType,true),StructField(prediction,DoubleType,false),StructField(probability,VectorUDT,true)))

# I tried this:
import pyspark.sql.functions as f

df.withColumn("prob_flag", f.array([f.col("probability")[3][1])).show()

"Can't extract value from probability#6225: need struct type but got struct<type:tinyint,size:int,indices:array<int>,values:array<double>>;"