Fixed directory permissions and fasttext loading

main.py

@@ -2,10 +2,11 @@ import os
 import tempfile
 import nltk
 
-# Set up cache directories
+# Set up all cache and data directories in /tmp
 cache_dir = tempfile.mkdtemp()
 nltk_data_dir = os.path.join(cache_dir, 'nltk_data')
 gensim_data_dir = os.path.join(cache_dir, 'gensim-data')
+upload_dir = os.path.join(cache_dir, 'uploads')  # New upload directory in /tmp
 
 # Set environment variables
 os.environ['HF_HOME'] = cache_dir
@@ -14,9 +15,10 @@ os.environ['GENSIM_DATA_DIR'] = gensim_data_dir
 # Create directories with correct permissions
 os.makedirs(nltk_data_dir, exist_ok=True)
 os.makedirs(gensim_data_dir, exist_ok=True)
+os.makedirs(upload_dir, exist_ok=True)  # Create uploads directory
 
-# 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
+# Add the custom directory to NLTK's search path
+nltk.data.path.insert(0, nltk_data_dir)
 
 # Download required NLTK data
 try:
@@ -43,8 +45,8 @@ from similarity_check.llm_based_scoring.llm import llm_score
 
 app = Flask(__name__)
 
-UPLOAD_FOLDER = 'uploads'
-os.makedirs(UPLOAD_FOLDER, exist_ok=True)
+# Use the new upload directory
+UPLOAD_FOLDER = upload_dir  # Changed from 'uploads' to upload_dir
 
 @app.route('/')
 def index():

similarity_check/semantic_meaning_check/semantic.py

@@ -17,12 +17,20 @@ from all_models import models
 # Use custom directory for gensim data
 gensim_data_dir = os.getenv('GENSIM_DATA_DIR', tempfile.gettempdir())
 
-# Load fasttext with custom data directory
+# Load fasttext with error handling
 try:
-    fasttext = load('fasttext-wiki-news-subwords-300', data_dir=gensim_data_dir)
+    print("Loading fasttext model...")
+    fasttext = load('fasttext-wiki-news-subwords-300')
 except Exception as e:
     print(f"Error loading fasttext model: {e}")
-    # Fallback similarity function if model fails to load
+    # Provide a fallback for similarity calculations
+    class DummyFasttext:
+        def __getitem__(self, word):
+            return np.zeros(300)  # Return zero vector of size 300
+        def __contains__(self, word):
+            return True
+    fasttext = DummyFasttext()
+    
     def compute_scm(tokens1, tokens2, model):
         return 0.5  # Return default similarity score