Update app.py

app.py

@@ -10,6 +10,13 @@ import pandas as pd
 from datetime import datetime, timezone, timedelta
 import notion_df
 import concurrent.futures
+import nltk
+from nltk.tokenize import sent_tokenize
+nltk.download('punkt')
+import spacy
+from spacy import displacy
+from gradio import Markdown
+import threading
 
 # Define the tokenizer and model
 tokenizer = GPT2Tokenizer.from_pretrained('gpt2-medium')
@@ -27,6 +34,50 @@ answer_count = 0
 # Define the Notion API key
 API_KEY = os.environ["API_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
@@ -102,6 +153,9 @@ def transcribe(audio, text):
         )["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)
 
@@ -110,7 +164,11 @@ def transcribe(audio, text):
     # Add the input text to the messages list
     messages_rev.insert(0, {"role": "user", "content": input_text + transcript["text"]})
 
-    
+    # 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()
+
     # Concatenate the chat history
     chat_transcript = "\n\n".join([f"[ANSWER {answer_count}]{message['role']}: {message['content']}" for message in messages_rev if message['role'] != 'system'])
     
@@ -127,8 +185,9 @@ def transcribe(audio, text):
     df = pd.DataFrame([chat_transcript])
     notion_df.upload(df, 'https://www.notion.so/US-62e861a0b35f43da8ef9a7789512b8c2?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")