Update app.py

app.py

@@ -11,16 +11,21 @@ HISTORY_WEIGHT = 100 # set history weight (if found any keyword from history, it
 def get_model(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 from model...')
+@st.cache(allow_output_mutation=True)
+def loading_models(model='roberta-base'):
+     return get_model(model), SentenceTransformer('all-MiniLM-L6-v2')
+
+def main(nlp, semantic_model, data_load_state):
+    data_load_state.text('Inference from model...')
     result = nlp(text+' '+nlp.tokenizer.mask_token)
-    data_load_state.text('')
     sem_list=[semantic_text.strip()]
+    data_load_state.text('Checking similarity...')
     if len(semantic_text):
         predicted_seq=[rec['sequence'] for rec in result]
         predicted_embeddings = semantic_model.encode(predicted_seq, convert_to_tensor=True)
         semantic_history_embeddings = semantic_model.encode(sem_list, convert_to_tensor=True)
         cosine_scores = util.cos_sim(predicted_embeddings, semantic_history_embeddings)
+    data_load_state.text('similarity check completed...')
     
     for index, r in enumerate(result):
         if len(semantic_text):
@@ -29,6 +34,7 @@ def main(nlp, semantic_model):
         if r['token_str'].lower().strip() in history_keyword_text.lower().strip() and len(r['token_str'].lower().strip())>1:
             #found from history, then increase the score of tokens
             result[index]['score']*=HISTORY_WEIGHT
+    data_load_state.text('Score updated...')
             
     #sort the results        
     df=pd.DataFrame(result).sort_values(by='score', ascending=False)
@@ -36,6 +42,7 @@ def main(nlp, semantic_model):
 #    show the results as a table
     st.table(df)
 #    print(df)
+    data_load_state.text('')
     
     
 if __name__ == '__main__':
@@ -44,7 +51,6 @@ if __name__ == '__main__':
 # 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="")
         semantic_text = st.text_input("Enter users's history <Semantic> (optional, i.e., 'Microsoft' or 'President')", value="Microsoft")
@@ -55,12 +61,13 @@ The next token is predicted per probability and a weight if it is appeared in ke
         
         model = st.selectbox("Choose a model", ["roberta-base", "bert-base-uncased"])
         
-        data_load_state = st.text('Loading model...')
+        data_load_state = st.text('1.Loading model ...')
 
-        semantic_model = SentenceTransformer('all-MiniLM-L6-v2')
-        nlp = get_model(model)
+#        semantic_model = SentenceTransformer('all-MiniLM-L6-v2')
+#        nlp = get_model(model)
+        nlp, semantic_model = loading_models(model)
         
-        main(nlp, semantic_model)
+        main(nlp, semantic_model, data_load_state)
     else:
         sys.argv = ['streamlit', 'run', sys.argv[0]]
         sys.exit(stcli.main())