Update app.py

app.py

@@ -16,7 +16,7 @@ tokenizer = GPT2Tokenizer.from_pretrained('gpt2-medium')
 model = openai.api_key = os.environ["OAPI_KEY"]
 
 # Define the initial message and messages list
-initialt = 'If user asked COLORIZE, don't need to do anything but present the input as it is with organized tabs (layers). You are a USMLE Tutor. Respond with ALWAYS layered "bullet points" (listing rather than sentences) \
+initialt = 'If user asked COLORIZE, dont need to do anything but present the input as it is with organized tabs (layers). You are a USMLE Tutor. Respond with ALWAYS layered "bullet points" (listing rather than sentences) \
                    to all input with a fun mneumonics to memorize that list. But you can answer up to 1200 words if the user requests longer response. \
                     You are going to keep answer and also challenge the student to learn USMLE anatomy, phsysiology, and pathology.'
 initial_message = {"role": "system", "content": initialt}
@@ -29,6 +29,48 @@ answer_count = 0
 # Define the Notion API key
 API_KEY = os.environ["NAPI_KEY"]
 
+nlp = spacy.load("en_core_web_sm")
+def process_nlp(system_message):
+    # Colorize the system message text
+    colorized_text = colorize_text(system_message['content'])
+    return colorized_text
+
+def colorize_text(text):
+    colorized_text = ""
+    lines = text.split("\n")
+
+    for line in lines:
+        doc = nlp(line)
+        for token in doc:
+            if token.ent_type_:
+                colorized_text += f'**{token.text_with_ws}**'
+            elif token.pos_ == 'NOUN':
+                colorized_text += f'<span style="color: #FF3300; background-color: transparent;">{token.text_with_ws}</span>'
+            elif token.pos_ == 'VERB':
+                colorized_text += f'<span style="color: #FFFF00; background-color: transparent;">{token.text_with_ws}</span>'
+            elif token.pos_ == 'ADJ':
+                colorized_text += f'<span style="color: #00CC00; background-color: transparent;">{token.text_with_ws}</span>'
+            elif token.pos_ == 'ADV':
+                colorized_text += f'<span style="color: #FF6600; background-color: transparent;">{token.text_with_ws}</span>'
+            elif token.is_digit:
+                colorized_text += f'<span style="color: #9900CC; background-color: transparent;">{token.text_with_ws}</span>'
+            elif token.is_punct:
+                colorized_text += f'<span style="color: #8B4513; background-color: transparent;">{token.text_with_ws}</span>'
+            elif token.is_quote:
+                colorized_text += f'<span style="color: #008080; background-color: transparent;">{token.text_with_ws}</span>'
+            else:
+                colorized_text += token.text_with_ws
+        colorized_text += "<br>"
+
+    return colorized_text
+
+def colorize_and_update(system_message, submit_update):
+    colorized_system_message = colorize_text(system_message['content'])
+    submit_update(None, colorized_system_message)  # Pass the colorized_system_message as the second output
+
+def update_text_output(system_message, submit_update):
+    submit_update(system_message['content'], None)
+
 def transcribe(audio, text):
     global messages
     global answer_count
@@ -104,42 +146,53 @@ def transcribe(audio, text):
             max_tokens=2000
         )["choices"][0]["message"]
     # Wait for the completion of the OpenAI API call
-        
+
+    if submit_update:  # Check if submit_update is not None
+        update_text_output(system_message, submit_update)
+
     # Add the system message to the messages list
     messages.append(system_message)
-        
+
     # Add the system message to the beginning of the messages list
     messages_rev.insert(0, system_message)
     # Add the input text to the messages list
     messages_rev.insert(0, {"role": "user", "content": input_text + transcript["text"]})
 
-    # Concatenate the chat history
+    # Start a separate thread to process the colorization and update the Gradio interface
+    if submit_update:  # Check if submit_update is not None
+        colorize_thread = threading.Thread(target=colorize_and_update, args=(system_message, submit_update))
+        colorize_thread.start()
+
+    # Return the system message immediately
+    chat_transcript = system_message['content']
+
+    # Concatenate the chat
     chat_transcript = "\n\n".join([f"[ANSWER {answer_count}]{message['role']}: {message['content']}" for message in messages_rev if message['role'] != 'system'])
 
     # chat_transcript_copy = chat_transcript
     # Append the number of tokens used to the end of the chat transcript
     chat_transcript += f"\n\nNumber of tokens used: {num_tokens}\n\n"
-    
-    # Upload the chat transcript to Notion
+
     now_et = datetime.now(timezone(timedelta(hours=-4)))
     published_date = now_et.strftime('%m-%d-%y %H:%M')
     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']
-    
+    # Return the chat transcript    
+    return system_message['content'], colorize_text(system_message['content'])
+
+
 # Define the input and output components for Gradio
 audio_input = Audio(source="microphone", type="filepath", label="Record your message")
 text_input = Textbox(label="Type your message", max_length=4096)
-output_text = gr.outputs.Textbox(label="Response")
-output_audio = Audio()
+output_text = Textbox(label="Text Output")
+output_html = Markdown()
 
 # Define the Gradio interface
 iface = gr.Interface(
     fn=transcribe,
     inputs=[audio_input, text_input],
-    outputs=[output_text],
+    outputs=[output_text, output_html],
     title="Hold On, Pain Ends (HOPE)",
     description="Talk to Your USMLE Tutor HOPE",
     theme="compact",