Update app.py

app.py

@@ -14,26 +14,31 @@ gpt2_model = AutoModelForCausalLM.from_pretrained("gpt2-medium")
 
 emotion_classifier = pipeline("text-classification", model="bhadresh-savani/distilbert-base-uncased-emotion", return_all_scores=True)
 
-# Function to generate a comforting story using GPT-2
 def generate_story(theme):
     # A detailed prompt for generating a comforting story about the selected theme
     story_prompt = f"Write a comforting, detailed, and heartwarming story about {theme}. The story should include a character who faces a tough challenge, finds hope, and ultimately overcomes the situation with a positive resolution."
     
-    # Generate story using GPT-2
+    # Generate story using GPT-2 with adjusted parameters
     input_ids = gpt2_tokenizer.encode(story_prompt, return_tensors='pt')
     
     story_ids = gpt2_model.generate(
         input_ids,
-        max_length=500,  # Generate longer stories
-        temperature=0.8,  # Balanced creativity
-        top_p=0.9,
-        repetition_penalty=1.2,
+        max_length=450,   # Generate slightly shorter but focused stories
+        temperature=0.7,  # Balanced creativity without too much randomness
+        top_p=0.9,        # Encourage diversity in output
+        top_k=50,         # Limit to more probable words
+        repetition_penalty=1.2,  # Prevent repetitive patterns
         num_return_sequences=1
     )
     
     # Decode the generated text
     story = gpt2_tokenizer.decode(story_ids[0], skip_special_tokens=True)
-    return story
+    
+    # Clean up the generated story by removing the initial prompt
+    cleaned_response = story.replace(story_prompt, "").strip()
+    
+    return cleaned_response
+
 
 def generate_response(user_input):
     # Limit user input length to prevent overflow issues