Update app.py

app.py

@@ -7,7 +7,6 @@ import nltk
 from transformers.models.roberta.modeling_roberta import *
 from transformers import RobertaForQuestionAnswering
 from nltk import word_tokenize
-import spacy
 import json
 import pandas as pd
 import re
@@ -21,7 +20,7 @@ phoBert_tokenizer = AutoTokenizer.from_pretrained('minhdang14902/PhoBert_Edu')
 chatbot_pipeline = pipeline("sentiment-analysis", model=phoBert_model, tokenizer=phoBert_tokenizer)
 
 # Load spaCy Vietnamese model
-nlp = spacy.load('vi_core_news_lg')
+# nlp = spacy.load('vi_core_news_lg')
 
 # Load intents from json file
 def load_json_file(filename):
@@ -57,13 +56,13 @@ num_labels = len(labels)
 id2label = {id: label for id, label in enumerate(labels)}
 label2id = {label: id for id, label in enumerate(labels)}
 
-def tokenize_with_spacy(text):
-    doc = nlp(text)
-    tokens = [token.text for token in doc]
-    tokenized_text = ' '.join(tokens)
-    tokenized_text = re.sub(r'(?<!\s)([.,?])', r' \1', tokenized_text)
-    tokenized_text = re.sub(r'([.,?])(?!\s)', r'\1 ', tokenized_text)
-    return tokenized_text
+# def tokenize_with_spacy(text):
+#     doc = nlp(text)
+#     tokens = [token.text for token in doc]
+#     tokenized_text = ' '.join(tokens)
+#     tokenized_text = re.sub(r'(?<!\s)([.,?])', r' \1', tokenized_text)
+#     tokenized_text = re.sub(r'([.,?])(?!\s)', r'\1 ', tokenized_text)
+#     return tokenized_text
 
 # Load Roberta model and tokenizer
 roberta_model_checkpoint = "minhdang14902/Roberta_edu"