Update app.py

app.py

@@ -146,7 +146,8 @@ def evolve_emotions():
     for i, (emotion, data) in enumerate(emotions.items()):
         data['percentage'] = emotion_values[i]
         data['intensity'] = intensities[i]
-# Normalize percentages
+
+    # Normalize percentages
     total = sum(e['percentage'] for e in emotions.values())
     for e in emotions:
         emotions[e]['percentage'] = (emotions[e]['percentage'] / total) * 100
@@ -192,16 +193,17 @@ def get_ai_emotion(input_text):
 
 def generate_emotion_visualization(ai_emotion, ai_emotion_percentage, ai_emotion_intensity):
     # Generate an emotion visualization based on the AI's emotional state
-    # This could involve creating an image or a visualization using Matplotlib/Seaborn
-    # The generated image should be saved and returned as the output
     emotion_visualization_path = 'emotional_state.png'
     try:
         # Generate and save the emotion visualization
-        plt.figure(figsize=(6, 6))
-        sns.barplot(x=['Emotion'], y=[ai_emotion_percentage], color=sns.color_palette()[emotions.index(ai_emotion)])
-        plt.title(f'Current Emotional State: {ai_emotion.capitalize()}')
+        plt.figure(figsize=(8, 6))
+        emotions_df = pd.DataFrame([(e, d['percentage'], d['intensity']) for e, d in emotions.items()],
+                                   columns=['emotion', 'percentage', 'intensity'])
+        sns.barplot(x='emotion', y='percentage', data=emotions_df)
+        plt.title(f'Current Emotional State: {ai_emotion.capitalize()} ({ai_emotion_percentage:.2f}%)')
         plt.xlabel('Emotion')
         plt.ylabel('Percentage')
+        plt.xticks(rotation=90)
         plt.savefig(emotion_visualization_path)
         plt.close()
     except Exception as e:
@@ -209,13 +211,13 @@ def generate_emotion_visualization(ai_emotion, ai_emotion_percentage, ai_emotion
         emotion_visualization_path = None
     return emotion_visualization_path
 
-def generate_response(ai_emotion, conversation_history):
-    # Prepare a prompt based on the current emotion
-    prompt = f"As an AI assistant, I am currently feeling {ai_emotion}. My response will reflect this emotional state."
+def generate_response(input_text, ai_emotion, conversation_history):
+    # Prepare a prompt based on the current emotion and input
+    prompt = f"As an AI assistant, I am currently feeling {ai_emotion}. My response will reflect this emotional state. Human: {input_text}\nAI: "
     
     # Add conversation history to the prompt
     for entry in conversation_history[-100:]:  # Use last 100 entries for context
-        prompt = f"My previous response: {entry['response']}\n" + prompt
+        prompt = f"Human: {entry['user']}\nAI: {entry['response']}\n" + prompt
     
     inputs = response_tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=8192)
     
@@ -252,10 +254,10 @@ def interactive_interface(input_text):
     text_complexity = analyze_text_complexity(input_text)
     ai_emotion, ai_emotion_percentage, ai_emotion_intensity = get_ai_emotion(input_text)
     emotion_visualization = generate_emotion_visualization(ai_emotion, ai_emotion_percentage, ai_emotion_intensity)
-    response = generate_response(ai_emotion, conversation_history)
+    response = generate_response(input_text, ai_emotion, conversation_history)
 
     # Update conversation history
-    conversation_history.append({'response': response})
+    conversation_history.append({'user': input_text, 'response': response})
     if len(conversation_history) > max_history_length:
         conversation_history.pop(0)
 
@@ -266,10 +268,10 @@ def interactive_interface(input_text):
         gr.Textbox(value=str(entities), label="Extracted Entities"),
         gr.Textbox(value=str(text_complexity), label="Text Complexity"),
         gr.Textbox(value=ai_emotion, label="AI Emotion"),
-        gr.Textbox(value=str(ai_emotion_percentage), label="AI Emotion Percentage"),
-        gr.Textbox(value=str(ai_emotion_intensity), label="AI Emotion Intensity"),
+        gr.Textbox(value=f"{ai_emotion_percentage:.2f}%", label="AI Emotion Percentage"),
+        gr.Textbox(value=f"{ai_emotion_intensity:.2f}", label="AI Emotion Intensity"),
         gr.Image(value=emotion_visualization, label="Emotion Visualization"),
-        gr.Textbox(value=response, label="AI Response")
+        gr.Textbox(value=f"As an AI assistant, I am currently feeling {ai_emotion}. My response will reflect this emotional state.\n\n{response}", label="AI Response")
     )
 
 # 443 additional features
@@ -302,7 +304,7 @@ def visualize_emotions():
     plt.xticks(rotation=90)
     plt.savefig('emotion_intensities.png')
 
-    return 'emotion_percentages.png', 'emotion_intensities.png'
+   return 'emotion_percentages.png', 'emotion_intensities.png'
 
 # Create the Gradio interface
 iface = gr.Interface(