Update app.py

app.py

@@ -6,14 +6,20 @@ from sentence_transformers import SentenceTransformer, util
 model = SentenceTransformer('all-MiniLM-L6-v2')
 
 # Two lists of sentences
-sentences1 = ['The cat sits outside',
-             'A man is playing guitar',
-             'The new movie is awesome']
+sentences1 = ['A man is playing guitar',
+             'The cat sits outside',
+             'The new movie is awesome',
+             'I do not have a match']
 
 sentences2 = ['The dog plays in the garden',
               'A woman watches TV',
               'The new movie is so great']
 
+st.text("When you have two arrays of sentences, you can compare them. Inspect these two unlabeled arrays")
+
+st.text(sentences1)
+st.text(sentences2)
+
 #Compute embedding for both lists
 embeddings1 = model.encode(sentences1, convert_to_tensor=True)
 embeddings2 = model.encode(sentences2, convert_to_tensor=True)
@@ -21,10 +27,12 @@ embeddings2 = model.encode(sentences2, convert_to_tensor=True)
 #Compute cosine-similarities
 cosine_scores = util.cos_sim(embeddings1, embeddings2)
 
+st.text("Computing which pairs are most similar")
+
 (col1, col2, score_col)= st.columns(3)
-col1.header("first sentence")
-col2.header("second sentence")
-score_col.header("score")
+col1.header("Left Token")
+col2.header("Right Token")
+score_col.header("Score")
 #Output the pairs with their score
 for i in range(len(sentences1)):
     #st.text("{} \t\t {} \t\t Score: {:.4f}".format(sentences1[i], sentences2[i], cosine_scores[i][i]))