Add nltk resource

handler.py

@@ -1,5 +1,6 @@
 
 from typing import Dict, List, Union, Optional
+import os
 from pathlib import Path
 import json
 import joblib
@@ -10,6 +11,9 @@ import torch
 import numpy as np
 from sklearn.base import TransformerMixin
 
+LOCAL_PATH = Path(__file__).parent
+nltk.data.path.append(str(LOCAL_PATH/"nltk_data"))
+
 class SimcseGenerator(TransformerMixin):
     def __init__(
         self, batch_size: int =16, model_name: str = "princeton-nlp/unsup-simcse-bert-base-uncased"
@@ -57,7 +61,7 @@ class EndpointHandler():
     def __init__(self, path: str = ""):
 
         if len(path)==0:
-            path = Path(__file__).parent
+            path = LOCAL_PATH
         else:
             path = Path(path)
 

nltk_data/tokenizers/punkt/PY3/english.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cad3758596392364e3be9803dbd7ebeda384b68937b488a01365f5551bb942c
+size 406697

nltk_data/tokenizers/punkt/english.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda37972ae88998a6fd3e3ec002697a6bd362b32d050fda7d7ca5276873092aa
+size 433305