Update app.py

app.py

@@ -1,14 +1,9 @@
 import torch
 import streamlit as st
 from transformers import RobertaTokenizer, RobertaForSequenceClassification
-import nltk
-from nltk.corpus import stopwords
 import re
 import string
-
-nltk.download('stopwords')
-nltk.download('punkt')
-stop_words = set(stopwords.words('english'))
+ 
 
 
 def tokenize_sentences(sentence):
@@ -23,18 +18,11 @@ def tokenize_sentences(sentence):
     )
     return torch.cat([encoded_dict['input_ids']], dim=0), torch.cat([encoded_dict['attention_mask']], dim=0)
 
-def remove_stop_words(sentence):
-    words = nltk.word_tokenize(sentence)
-    custom_words = ['recommend', 'having', 'Hello', 'best', 'restaurant', 'top', 'want', 'need', 'well', 'most', 'should', 'be', 'good', 'also']
-    stop_words.update(custom_words)
-    words_without_stopwords = [word for word in words if word.lower() not in stop_words]
-    sentence_without_stopwords = ' '.join(words_without_stopwords)
-    return sentence_without_stopwords
+ 
 
 def preprocess_query(query):
     query = str(query).lower()
     query = query.strip()
-    query = remove_stop_words(query)
     query=query.translate(str.maketrans("", "", string.punctuation))
     return query