Update app.py

app.py

@@ -32,10 +32,36 @@ from sklearn.feature_extraction.text import TfidfVectorizer
 # Load environment variables
 load_dotenv()
 
-# Download NLTK resources (Ensure this runs once or handle caching)
-# nltk.download(['stopwords', 'wordnet', 'words'])
-# nltk.download('punkt')
-# nltk.download('punkt_tab')
+# Inside your main script (e.g., near the top after imports)
+import nltk
+import ssl # Sometimes needed for NLTK downloads
+
+def ensure_nltk_resources():
+    try:
+        # Try to find a resource to see if download is needed
+        # Using punkt as an example; you might check others too
+        nltk.data.find('tokenizers/punkt')
+        nltk.data.find('corpora/stopwords')
+        # Add checks for wordnet, words, punkt_tab as needed
+    except LookupError:
+        print("NLTK resources not found. Downloading...")
+        try:
+            # Handle potential SSL issues (common on some systems)
+            _create_unverified_https_context = ssl._create_unverified_context
+        except AttributeError:
+            pass
+        else:
+            ssl._create_default_https_context = _create_unverified_https_context
+
+        nltk.download(['stopwords', 'wordnet', 'words'])
+        nltk.download('punkt')
+        nltk.download('punkt_tab')
+        print("NLTK resources downloaded successfully.")
+
+# Call the function at the start of your script
+ensure_nltk_resources()
+
+
 
 # Initialize Groq client
 groq_api_key = os.getenv("GROQ_API_KEY")