Update app.py

app.py

@@ -9,10 +9,10 @@ HISTORY_WEIGHT = 100 # set history weight (if found any keyword from history, it
 
 @st.cache(allow_output_mutation=True)
 def get_model(model):
-	return pipeline("fill-mask", model=model, top_k=20)#set the maximum of tokens to be retrieved after each inference to model
+	return pipeline("fill-mask", model=model, top_k=10)#set the maximum of tokens to be retrieved after each inference to model
 
 def main(nlp, semantic_model):
-    data_load_state = st.text('Inference to model...')
+    data_load_state = st.text('Inference from model...')
     result = nlp(text+' '+nlp.tokenizer.mask_token)
     data_load_state.text('')
     sem_list=[semantic_text.strip()]
@@ -41,16 +41,17 @@ def main(nlp, semantic_model):
 if __name__ == '__main__':
     if st._is_running_with_streamlit:
         st.markdown("""
-# Introduction
+# Auto-Complete
 This is an example of an auto-complete approach where the next token suggested based on users's history Keyword match & Semantic similarity of users's history (log).
 The next token is predicted per probability and a weight if it is appeared in keyword user's history or there is a similarity to semantic user's history
 
 """)
-        history_keyword_text = st.text_input("Enter users's history <keywords match> (optional, i.e., 'Gates')", value="")
+        history_keyword_text = st.text_input("Enter users's history **keywords match** (optional, i.e., 'Gates')", value="")
+        semantic_text = st.text_input("Enter users's history **semantic** (optional, i.e., 'Microsoft or President')", value="Microsoft")
         
         text = st.text_input("Enter a text for auto completion...", value='Where is Bill')
         
-        semantic_text = st.text_input("Enter users's history <semantic> (optional, i.e., 'Microsoft or President')", value="Microsoft")
+        
         
         model = st.selectbox("Choose a model", ["roberta-base", "bert-base-uncased"])