Update question_handler.py

question_handler.py

@@ -1,5 +1,11 @@
 import re
 from sklearn.metrics.pairwise import cosine_similarity
+from embeddings_utils import load_model
+import torch
+
+# Load the SentenceTransformer model directly in this file
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = load_model(device)
 
 def find_top_question(query, metadata, embeddings):
     query_embedding = model.encode(query, convert_to_tensor=True).cpu().numpy().reshape(1, -1)