new

main.py

@@ -1,10 +1,27 @@
 import os
 import tempfile
+import nltk
 
-# Set up cache directory for transformers
+# Set up cache directories
 cache_dir = tempfile.mkdtemp()
+nltk_data_dir = os.path.join(cache_dir, 'nltk_data')
 os.environ['HF_HOME'] = cache_dir
 
+# Create NLTK data directory
+os.makedirs(nltk_data_dir, exist_ok=True)
+
+# Add the custom directory to NLTK's search path BEFORE downloading
+nltk.data.path.insert(0, nltk_data_dir)  # Insert at beginning of search path
+
+# Download required NLTK data
+try:
+    print("Downloading required NLTK data...")
+    nltk.download('stopwords', download_dir=nltk_data_dir)
+    nltk.download('punkt', download_dir=nltk_data_dir)
+    nltk.download('wordnet', download_dir=nltk_data_dir)
+except Exception as e:
+    print(f"Error downloading NLTK data: {e}")
+
 from flask import Flask, request, jsonify, render_template
 import json 
 import torch

similarity_check/semantic_meaning_check/semantic.py

@@ -16,6 +16,7 @@ from all_models import models
 # Keep fasttext as is
 fasttext = load('fasttext-wiki-news-subwords-300')
 
+# Remove these commented lines since we're handling downloads in main.py
 # nltk.download('punkt')
 # nltk.download('stopwords')
 

similarity_check/tf_idf/tf_idf_score.py

@@ -5,14 +5,7 @@ from nltk.corpus import wordnet
 from collections import Counter
 import string
 
-# Check and download required NLTK packages
-try:
-    stopwords.words('english')
-except LookupError:
-    print("Downloading required NLTK data...")
-    nltk.download('stopwords')
-    nltk.download('punkt')
-    nltk.download('wordnet')
+
 
 def remove_stopwords(sentence):