Update app.py

app.py

@@ -15,12 +15,13 @@ tokenizer = GPT2Tokenizer.from_pretrained(model_name)
 model = GPT2LMHeadModel.from_pretrained(model_name)
 model.eval()
 
+# Ensure tokenizer pad token is set
 if tokenizer.pad_token is None:
     tokenizer.pad_token = tokenizer.eos_token
 
 tokenizer.clean_up_tokenization_spaces = True
 
-# Ensure model and tensors are moved to the GPU if available
+# Set device for model and tensors
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 model.to(device)
 
@@ -53,7 +54,6 @@ def adjust_for_emotion(response, sentiment):
     return response
 
 # ---- Neural Network Models ----
-
 # 1. RNN Model for Sentiment Classification
 class RNN(nn.Module):
     def __init__(self, vocab_size, embedding_dim, hidden_dim, output_dim):
@@ -128,39 +128,30 @@ def generate_response(prompt, max_length=512):
 
     response = tokenizer.decode(output[0], skip_special_tokens=True)
 
-    # Look for the first indentation or newline (i.e., the first significant break in the response)
+    # Split response into two parts
     parts = response.split("\n", 1)
-
     if len(parts) > 1:
-        # Text before the first indentation is orange
         before_indent = f'<span style="color: orange;">{parts[0].strip()}</span>'
-
-        # Text after the first newline or indentation gets labeled as "Inner Thoughts:" in blue
         after_indent = f'<span style="color: blue;">Inner Thoughts: {parts[1].strip()}</span>'
-        
-        # Combine the two parts
         colored_response = before_indent + '\n' + after_indent
     else:
-        # If there's no newline, color the entire response orange
         colored_response = f'<span style="color: orange;">{response.strip()}</span>'
 
     return colored_response
 
-
 # ---- Interactive Chat Function ----
 def advanced_agi_chat(user_input):
-    # Add user input to session memory
     session_memory.append({"input": user_input})
     save_memory(session_memory)
 
-    # Sentiment analysis
+    # Sentiment analysis of user input
     user_sentiment = analyze_sentiment(user_input)
 
-    # Generate the response
+    # Generate the response based on the prompt
     prompt = f"User: {user_input}\nAutistic-Gertrude:"
     response = generate_response(prompt)
 
-    # Adjust response for emotional alignment
+    # Adjust the response based on sentiment
     adjusted_response = adjust_for_emotion(response, user_sentiment)
 
     return adjusted_response
@@ -168,21 +159,32 @@ def advanced_agi_chat(user_input):
 # ---- Gradio Interface ----
 def chat_interface(user_input):
     response = advanced_agi_chat(user_input)
-    # Return the response with HTML formatting
     return response
 
+# ---- Gradio App Setup ----
 with gr.Blocks() as app:
     gr.Markdown("# **Autistic Assistant vß Edition 2024 Ultra: Gertrude's Autistic Experience**")
+    
     with gr.Row():
         with gr.Column():
             user_input = gr.Textbox(label="What will you say to Gertrude?", placeholder="Type something here... Expect 1-2 Minute Response Times...")
             submit_button = gr.Button("Send")
         with gr.Column():
-            chatbot = gr.HTML(label="Gertrude's Response", interactive=False)
-    
-    # Theme the UI with colors and a pattern
-    gr.HTML("<style>.gradio-container { background-color: #F4F8FF; padding: 20px; border-radius: 15px; font-family: 'Comic Sans MS'; }</style>")
-
+            chatbot = gr.HTML(label="Gertrude's Response")  # No 'interactive' argument
+
+    # Adding custom styling for the UI
+    gr.HTML("""
+        <style>
+            .gradio-container { 
+                background-color: #F4F8FF; 
+                padding: 20px; 
+                border-radius: 15px; 
+                font-family: 'Comic Sans MS'; 
+            }
+        </style>
+    """)
+
+    # Setting the button click event
     submit_button.click(chat_interface, inputs=user_input, outputs=chatbot)
 
 # Launch the Gradio app