Update app.py

app.py

@@ -8,7 +8,7 @@ menu = st.sidebar.radio("", options=["Introduction", "Parsing NLU data into SQuA
                                      "Evaluation"], index=0)
 
 
-if menu == "Introduction":
+if menu == "Demo":
 
     st.markdown('''
 
@@ -41,7 +41,35 @@ if menu == "Introduction":
         NLU dataset (e.g. utterances and intent / slot annotations) into [SQuAD 2.0 format](https://rajpurkar.github.io/SQuAD-explorer/explore/v2.0/dev/)
         question-answering data that can be used by QANLU.
 
+        Feel free to query the pre-trained QA-NLU model using the buttons below. 
+        
+        *Please note that this model has been trained on ATIS and may be need to be further fine-tuned to support intents and slots that are not covered in ATIS*.
     ''')
+    
+    tokenizer = AutoTokenizer.from_pretrained("AmazonScience/qanlu")
+
+    model = AutoModelForQuestionAnswering.from_pretrained("AmazonScience/qanlu")
+
+    qa_pipeline = pipeline('question-answering', model=model, tokenizer=tokenizer)
+    
+    context = st.text_input(
+        'Please enter the context (remember to include "Yes. No. " in the beginning):',
+        value="Yes. No. I want a cheap flight to Boston."
+    )
+    question = st.text_input(
+        'Please enter the intent question:',
+        value="Are they looking for a flight?"
+    )
+
+
+    qa_input = {
+      'context': context,
+      'question': question
+    }
+
+    if st.button('Ask QANLU'):
+        answer = qa_pipeline(qa_input)
+        st.write(answer)
 
 elif menu == "Parsing NLU data into SQuAD 2.0":
     st.header('QA-NLU Data Parsing')
@@ -167,32 +195,6 @@ elif menu == "Evaluation":
     st.markdown('''
         To assess the performance of the trained model, we can use the `calculate_pr.py` script from the [QA-NLU Amazon Research repository](https://github.com/amazon-research/question-answering-nlu).
         
-        Feel free to query the pre-trained QA-NLU model using the buttons below. 
-        
-        *Please note that this model has been trained on ATIS and may be need to be further fine-tuned to support intents and slots that are not covered in ATIS*.
+        Feel free to query the pre-trained QA-NLU model in the Demo section.
     ''')
-    
-    tokenizer = AutoTokenizer.from_pretrained("AmazonScience/qanlu")
-
-    model = AutoModelForQuestionAnswering.from_pretrained("AmazonScience/qanlu")
-
-    qa_pipeline = pipeline('question-answering', model=model, tokenizer=tokenizer)
-    
-    context = st.text_input(
-        'Please enter the context (remember to include "Yes. No. " in the beginning):',
-        value="Yes. No. I want a cheap flight to Boston."
-    )
-    question = st.text_input(
-        'Please enter the intent question:',
-        value="Are they looking for a flight?"
-    )
-
-
-    qa_input = {
-      'context': context,
-      'question': question
-    }
-
-    if st.button('Ask QANLU'):
-        answer = qa_pipeline(qa_input)
-        st.write(answer)
+