Update app.py

app.py

@@ -77,6 +77,7 @@ emotions = {
 
 total_percentage = 100
 emotion_history_file = 'emotion_history.json'
+global conversation_history
 conversation_history = []
 max_history_length = 30
 
@@ -170,6 +171,7 @@ def feature_transformations():
         additional_features[feature] += random.uniform(-1, 1)
 
 def generate_response(input_text, ai_emotion):
+    global 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:"
     
@@ -177,7 +179,7 @@ def generate_response(input_text, ai_emotion):
     for entry in conversation_history[-5:]:  # Use last 5 entries for context
         prompt = f"Human: {entry['user']}\nAI: {entry['response']}\n" + prompt
     
-    inputs = response_tokenizer(prompt, return_tensors="pt", truncation=True, max_length=1024)
+    inputs = response_tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=1024)
     
     # Adjust generation parameters based on emotion
     temperature = 0.7
@@ -189,9 +191,11 @@ def generate_response(input_text, ai_emotion):
     with torch.no_grad():
         response_ids = response_model.generate(
             inputs.input_ids,
+            attention_mask=inputs.attention_mask,
             max_length=1024,
             num_return_sequences=1,
             no_repeat_ngram_size=2,
+            do_sample=True,
             top_k=50,
             top_p=0.95,
             temperature=temperature
@@ -249,6 +253,7 @@ def visualize_emotions():
     return 'emotional_state.png'
 
 def interactive_interface(input_text):
+    global conversation_history
     try:
         evolve_emotions()
         predicted_emotion = predict_emotion(input_text)
@@ -321,4 +326,4 @@ iface = gr.Interface(
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    iface.launch(share=True)