make the pipeline conform to types

pipeline.py

@@ -1,5 +1,6 @@
 from typing import Dict, List, Any
 import random
+import numpy as np
 
 class PreTrainedPipeline():
     def __init__(self, path=""):
@@ -7,7 +8,7 @@ class PreTrainedPipeline():
         # Preload all the elements you are going to need at inference.
         # For instance your model, processors, tokenizer that might be needed.
         # This function is only called once, so do all the heavy processing I/O here"""
-        self.x = random.randint(0, 1000)
+        self.x = np.random.random(10)
 
     def __call__(self, inputs: str) -> List[float]:
         """
@@ -18,4 +19,4 @@ class PreTrainedPipeline():
             A :obj:`list` of floats: The features computed by the model.
         """
         # IMPLEMENT_THIS
-        return self.x, inputs
+        return self.x[:len(input)].tolist()

requirements.txt

@@ -0,0 +1 @@
+numpy==1.23.1