Update app.py

app.py

@@ -137,7 +137,7 @@ def evolve_emotions():
 
     population = toolbox.population(n=100)
     algorithms.eaMuPlusLambda(population, toolbox, mu=50, lambda_=100, cxpb=0.7, mutpb=0.2, ngen=50,
-                              stats=None, halloffame=None, verbose=False)
+                               stats=None, halloffame=None, verbose=False)
 
     best_individual = tools.selBest(population, k=1)[0]
     emotion_values = best_individual[:len(emotions)]
@@ -146,8 +146,7 @@ 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
@@ -196,16 +195,27 @@ def generate_emotion_visualization(ai_emotion, ai_emotion_percentage, ai_emotion
     # 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'
-    # Generate and save the emotion visualization
+    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.xlabel('Emotion')
+        plt.ylabel('Percentage')
+        plt.savefig(emotion_visualization_path)
+        plt.close()
+    except Exception as e:
+        print(f"Error generating emotion visualization: {e}")
+        emotion_visualization_path = None
     return emotion_visualization_path
 
-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:"
+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."
     
     # Add conversation history to the prompt
     for entry in conversation_history[-100:]:  # Use last 100 entries for context
-        prompt = f"Human: {entry['user']}\nAI: {entry['response']}\n" + prompt
+        prompt = f"My previous response: {entry['response']}\n" + prompt
     
     inputs = response_tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=8192)
     
@@ -232,8 +242,7 @@ def generate_response(input_text, ai_emotion, conversation_history):
     response = response_tokenizer.decode(response_ids[0], skip_special_tokens=True)
     
     # Extract only the AI's response
-    response = response.split("AI:")[-1].strip()
-    return response
+    return response.strip()
 
 def interactive_interface(input_text):
     # Perform your processing logic here
@@ -243,24 +252,24 @@ 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(input_text, ai_emotion, conversation_history)
+    response = generate_response(ai_emotion, conversation_history)
 
     # Update conversation history
-    conversation_history.append({'user': input_text, 'response': response})
+    conversation_history.append({'response': response})
     if len(conversation_history) > max_history_length:
         conversation_history.pop(0)
 
     # Return the expected outputs in the correct order
     return (
-        gr.Textbox(predicted_emotion),
-        gr.Textbox(str(sentiment_scores)),
-        gr.Textbox(str(entities)),
-        gr.Textbox(str(text_complexity)),
-        gr.Textbox(ai_emotion),
-        gr.Textbox(str(ai_emotion_percentage)),
-        gr.Textbox(str(ai_emotion_intensity)),
-        gr.Image(emotion_visualization),
-        gr.Textbox(response)
+        gr.Textbox(value=predicted_emotion, label="Predicted Emotion"),
+        gr.Textbox(value=str(sentiment_scores), label="Sentiment Scores"),
+        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.Image(value=emotion_visualization, label="Emotion Visualization"),
+        gr.Textbox(value=response, label="AI Response")
     )
 
 # 443 additional features
@@ -314,4 +323,4 @@ iface = gr.Interface(
     description="An AI assistant that can analyze the emotional content of text and generate responses based on its emotional state.",
 )
 
-iface.launch()
+iface.launch()