Update app.py

app.py

@@ -95,14 +95,14 @@ with gr.Blocks() as demo:
         # T4.5 Relevance Classifier Demo 
         This is a demo created to explore floods and wildfire classification in social media posts.\n
         Usage:\n
-        (1.) Upload .tsv data file (must contain a text column with social media posts).\n
-        (2.) Next, type the name of the text column.\n
-        (3.) Then, choose a BERT classifier model from the drop down.\n
-        (4.) Finally, click the 'start prediction' buttton.\n
+            - Upload .tsv data file (must contain a text column with social media posts).\n
+            - Next, type the name of the text column.\n
+            - Then, choose a BERT classifier model from the drop down.\n
+            - Finally, click the 'start prediction' buttton.\n
         Evaluation:\n
-        (1.) To evaluate the model's accuracy select the INCORRECT classifications using the checkboxes in front of each post.\n
-        (2.) Then, click on the 'Calculate Accuracy' button.\n
-        (3.) Then, click on the 'Download data as CSV' to get the classifications and evaluation data as a .csv file.
+            - To evaluate the model's accuracy select the INCORRECT classifications using the checkboxes in front of each post.\n
+            - Then, click on the 'Calculate Accuracy' button.\n
+            - Then, click on the 'Download data as CSV' to get the classifications and evaluation data as a .csv file.
         """)
         with gr.Row(equal_height=True):
             with gr.Column(scale=4):
@@ -167,7 +167,15 @@ with gr.Blocks() as demo:
     
     with qa_tab:
         # XXX Add some button disabling here, if the classification process is not completed first XXX
-
+        
+        gr.Markdown(
+        """
+        # Question Answering Demo
+        This section uses RAG to answer questions about the relevant social media posts identified by the relevance classifier\n 
+        Usage:\n
+            - Select queries from predefined\n
+            - Parameters for QA can be editted in sidebar\n
+        """)
         selected_queries = gr.CheckboxGroup(label="Select at least one query using the checkboxes", interactive=True)
         qa_tab.select(get_queries, None, selected_queries)
         qa_button = gr.Button("Start QA")