Update app.py

app.py

@@ -70,8 +70,10 @@ def cstr_break(s, color='black'):
 
 def print_colored(text, start_idx, end_idx, confidence):
     conf_str = 'Confidence: ' +  confidence
-    a = cstr_break(' '.join([cstr(' '.join([text[:start_idx], cstr_bold(text[start_idx:end_idx], color='red'), text[end_idx:]]), color='black'), conf_str]))
-    #a = colored(text[:start_idx]) + colored(text[start_idx:end_idx], 'red', 'on_yellow') + colored(text[end_idx:])
+    a = cstr(' '.join([text[:start_idx], \
+                        cstr_bold(text[start_idx:end_idx], color='red'), \
+                        text[end_idx:], \
+                        cstr_break(conf_str, color='yellow')]), color='black')
     return a
        
 def final_qa_pipeline(file, query):
@@ -95,7 +97,7 @@ def final_qa_pipeline(file, query):
         #    print_colored(fnl_['doc'], fnl_['start'], fnl_['end'])
         #    print(colored("Confidence score of ") + colored(str(fnl_['score'])[:4], attrs=['bold']))
     else:
-        return ("No match", "0")
+        return ("No match")
         
 examples = [
     [os.path.abspath("dbs-annual-report-2020.pdf"), "how much dividend was paid to shareholders ?"],
@@ -109,7 +111,7 @@ examples = [
 iface = gr.Interface(
    fn = final_qa_pipeline,
    inputs = [gr.inputs.File(label="input pdf file"), gr.inputs.Textbox(label="Question:")],
-   outputs = [gr.outputs.HTML(label="Predicted answer"), gr.outputs.Textbox(label="Confidence") ],
+   outputs = [gr.outputs.HTML(label="Predicted answer")],
    examples=examples,
    title = "Question Answering on company annual reports",
    description = "Navigate long annual reports by using Machine learning to answer your questions. \nSimply upload any annual report pdf you are interested in and ask model a question OR load an example from below."