Create app.py

app.py

@@ -0,0 +1,37 @@
+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)
+@st.cache_resource # Cache the model for faster subsequent runs
+def load_bert():
+    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+    model = BertModel.from_pretrained('bert-base-uncased')
+    return tokenizer, model
+
+tokenizer, model = load_bert()
+
+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")
+
+word1 = st.text_input("Enter the first word:")
+word2 = st.text_input("Enter the second word:")
+
+if st.button("Check Similarity"):
+    if word1 and word2:
+        similarity = calculate_similarity(word1, word2)
+        st.write(f"Similarity between '{word1}' and '{word2}': {similarity:.4f}")
+    else:
+        st.warning("Please enter both words.")