Update app.py

app.py

@@ -60,7 +60,7 @@ emotion_prediction_model = AutoModelForSequenceClassification.from_pretrained("b
 emotion_prediction_tokenizer = AutoTokenizer.from_pretrained("bhadresh-savani/distilbert-base-uncased-emotion")
 
 # Load pre-trained LLM model and tokenizer for response generation with increased context window
-response_model_name = "microsoft/DialoGPT-medium"
+response_model_name = "microsoft/DialoGPT-large"
 response_tokenizer = AutoTokenizer.from_pretrained(response_model_name)
 response_model = AutoModelForCausalLM.from_pretrained(response_model_name)
 
@@ -82,7 +82,7 @@ total_percentage = 100
 emotion_history_file = 'emotion_history.json'
 global conversation_history
 conversation_history = []
-max_history_length = 30
+max_history_length = 100  # Increase the maximum history length
 
 def load_historical_data(file_path=emotion_history_file):
     if os.path.exists(file_path):
@@ -151,6 +151,7 @@ def evolve_emotions():
     total = sum(e['percentage'] for e in emotions.values())
     for e in emotions:
         emotions[e]['percentage'] = (emotions[e]['percentage'] / total) * 100
+
 def update_emotion_history(emotion, percentage, intensity, context):
     entry = {
         'emotion': emotion,
@@ -172,16 +173,15 @@ def feature_transformations():
     for feature in additional_features:
         additional_features[feature] += random.uniform(-1, 1)
 
-def generate_response(input_text, ai_emotion):
-    global conversation_history
+def generate_response(input_text, ai_emotion, conversation_history):
     # Prepare a prompt based on the current emotion and input
     prompt = f"You are an AI assistant currently feeling {ai_emotion}. Your response should reflect this emotion. Human: {input_text}\nAI:"
     
     # Add conversation history to the prompt
-    for entry in conversation_history[-5:]:  # Use last 5 entries for context
+    for entry in conversation_history[-20:]:  # Use last 20 entries for context
         prompt = f"Human: {entry['user']}\nAI: {entry['response']}\n" + prompt
     
-    inputs = response_tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=1024)
+    inputs = response_tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=2048)
     
     # Adjust generation parameters based on emotion
     temperature = 0.7
@@ -194,7 +194,7 @@ def generate_response(input_text, ai_emotion):
         response_ids = response_model.generate(
             inputs.input_ids,
             attention_mask=inputs.attention_mask,
-            max_length=1024,
+            max_length=2048,
             num_return_sequences=1,
             no_repeat_ngram_size=2,
             do_sample=True,
@@ -271,7 +271,7 @@ def interactive_interface(input_text):
         ai_emotion = max(emotions, key=lambda e: emotions[e]['percentage'])
         
         # Generate response based on AI's emotion
-        response = generate_response(input_text, ai_emotion)
+        response = generate_response(input_text, ai_emotion, conversation_history)
         
         # Update conversation history
         conversation_history.append({
@@ -294,39 +294,36 @@ def interactive_interface(input_text):
             'sentiment_scores': sentiment_scores,
             'entities': entities,
             'text_complexity': text_complexity,
-            'current_emotional_state': emotions,
             'response': response,
             'emotion_visualization': emotion_visualization
         }
         
         return analysis_result
     except Exception as e:
-        print(f"An error occurred: {str(e)}")
-        return "I apologize, but I encountered an error while processing your input. Please try again."
-
-def gradio_interface(input_text):
-    response = interactive_interface(input_text)
-    if isinstance(response, str):
-        return response, None
-    else:
-        return (
-            f"User Emotion: {response['predicted_user_emotion']}\n"
-            f"AI Emotion: {response['ai_emotion']}\n"
-            f"AI Response: {response['response']}\n\n"
-            f"Sentiment: {response['sentiment_scores']}\n"
-            f"Entities: {response['entities']}\n"
-            f"Text Complexity: {response['text_complexity']}\n",
-            response['emotion_visualization']
-        )
+        print(f"Error: {e}")
+        return {
+            'predicted_user_emotion': 'unknown',
+            'ai_emotion': 'neutral',
+            'sentiment_scores': {'compound': 0, 'neg': 0, 'neu': 1, 'pos': 0},
+            'entities': [],
+            'text_complexity': {'word_count': 0, 'sentence_count': 0, 'average_sentence_length': 0, 'polarity': 0, 'subjectivity': 0},
+            'response': "I'm sorry, but I encountered an error and was unable to generate a response.",
+            'emotion_visualization': 'emotional_state.png'
+        }
 
-# Create Gradio interface
-iface = gr.Interface(
-    fn=gradio_interface,
-    inputs="text",
-    outputs=["text", gr.Image(type="filepath")],
-    title="Enhanced Emotional AI Interface",
-    description="Enter text to interact with the AI and analyze emotions."
-)
-
-if __name__ == "__main__":
-    iface.launch(share=True)
+# Create a Gradio interface
+gr.Interface(
+    fn=interactive_interface,
+    inputs=gr.Textbox(label="Your Message"),
+    outputs=[
+        gr.Textbox(label="Predicted User Emotion"),
+        gr.Textbox(label="AI Emotion"),
+        gr.Textbox(label="Sentiment Scores"),
+        gr.Textbox(label="Extracted Entities"),
+        gr.Textbox(label="Text Complexity"),
+        gr.Textbox(label="AI Response"),
+        gr.Image(label="Emotional State Visualization")
+    ],
+    title="Emotion-Aware AI Assistant",
+    description="Interact with an AI assistant that responds based on its emotional state."
+).launch()