Update app.py

app.py

@@ -10,6 +10,7 @@ import pandas as pd
 from datetime import datetime, timezone, timedelta
 import notion_df
 import concurrent.futures
+from IPython.core.display import HTML
 
 # Define the tokenizer and model
 tokenizer = GPT2Tokenizer.from_pretrained('gpt2-medium')
@@ -126,8 +127,12 @@ def transcribe(audio, text):
     df = pd.DataFrame([chat_transcript])
     notion_df.upload(df, 'https://www.notion.so/YENA-be569d0a40c940e7b6e0679318215790?pvs=4', title=str(published_date), api_key=API_KEY)
 
-    # Return the chat transcript
-    return system_message['content']
+    # Colorize the system message text
+    colorized_system_message = colorize_text(system_message['content'])
+
+    # Return the colorized chat transcript
+    return colorized_system_message
+
     
 # Define the input and output components for Gradio
 audio_input = Audio(source="microphone", type="filepath", label="Record your message")
@@ -135,11 +140,29 @@ text_input = Textbox(label="Type your message", max_length=4096)
 output_text = gr.outputs.Textbox(label="Response")
 output_audio = Audio()
 
+
+def colorize_text(text):
+    doc = nlp(text)
+    colorized_text = ""
+
+    for token in doc:
+        if token.ent_type_:
+            colorized_text += f'<span style="background-color: yellow;">{token.text_with_ws}</span>'
+        elif token.pos_ in {'NOUN'}:
+            colorized_text += f'<span style="color: blue;">{token.text_with_ws}</span>'
+        else:
+            colorized_text += token.text_with_ws
+
+    return colorized_text
+
+
+
 # Define the Gradio interface
 iface = gr.Interface(
     fn=transcribe,
     inputs=[audio_input, text_input],
     outputs=[output_text],
+    output_text = gr.outputs.HTML(label="Response"),
     title="Hold On, Pain Ends (HOPE)",
     description="Talk to Your USMLE Tutor HOPE",
     theme="compact",