Update app.py

app.py

@@ -2,7 +2,6 @@ import streamlit as st
 import torch
 from transformers import BertModel, BertTokenizer
 
-# Load pre-trained BERT model and tokenizer (do this outside the main loop for efficiency)
 # Load pre-trained BERT model and tokenizer 
 @st.cache_resource
 def load_bert():
@@ -12,18 +11,17 @@ def load_bert():
 
 tokenizer, model = load_bert()
 
-    def calculate_similarity(word1, word2):
-    def calculate_similarity(word1, word2):
-        # Tokenize and get embeddings
-        input_ids1 = torch.tensor([tokenizer.encode(word1, add_special_tokens=True)])
-        input_ids2 = torch.tensor([tokenizer.encode(word2, add_special_tokens=True)])
-    
-        with torch.no_grad():
-            embeddings1 = model(input_ids1)[0][0, 0, :] 
-            embeddings2 = model(input_ids2)[0][0, 0, :]
-    
-        cos_sim = torch.nn.functional.cosine_similarity(embeddings1, embeddings2, dim=0)
-        return cos_sim.item()  # Convert tensor to a float
+def calculate_similarity(word1, word2):
+    # Tokenize and get embeddings
+    input_ids1 = torch.tensor([tokenizer.encode(word1, add_special_tokens=True)])
+    input_ids2 = torch.tensor([tokenizer.encode(word2, add_special_tokens=True)])
+
+    with torch.no_grad():
+        embeddings1 = model(input_ids1)[0][0, 0, :] 
+        embeddings2 = model(input_ids2)[0][0, 0, :]
+
+    cos_sim = torch.nn.functional.cosine_similarity(embeddings1, embeddings2, dim=0)
+    return cos_sim.item()  # Convert tensor to a float
 
 # Streamlit interface
 st.title("Word Similarity Checker")