Update app.py

app.py

@@ -3,7 +3,8 @@ import torch
 from transformers import BertModel, BertTokenizer
 
 # Load pre-trained BERT model and tokenizer (do this outside the main loop for efficiency)
-@st.cache_resource # Cache the model for faster subsequent runs
+# Load pre-trained BERT model and tokenizer 
+@st.cache_resource
 def load_bert():
     tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
     model = BertModel.from_pretrained('bert-base-uncased')
@@ -11,6 +12,7 @@ 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)])
@@ -26,12 +28,14 @@ def calculate_similarity(word1, word2):
 # Streamlit interface
 st.title("Word Similarity Checker")
 
-word1 = st.text_input("Enter the first word:")
-word2 = st.text_input("Enter the second word:")
+reference_word = st.text_input("Enter the reference word:")
+word_list = st.text_area("Enter a list of words (one word per line):")
 
-if st.button("Check Similarity"):
-    if word1 and word2:
-        similarity = calculate_similarity(word1, word2)
-        st.write(f"Similarity between '{word1}' and '{word2}': {similarity:.4f}")
+if st.button("Analyze"):
+    if reference_word and word_list:
+        words = word_list.splitlines()
+        for word in words:
+            similarity = calculate_similarity(reference_word, word)
+            st.write(f"Similarity between '{reference_word}' and '{word}': {similarity:.4f}")
     else:
-        st.warning("Please enter both words.")
+        st.warning("Please enter a reference word and a list of words.")