Update app.py

app.py

@@ -3,30 +3,31 @@ from huggingface_hub import InferenceClient
 
 client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
 
-# Store conversation history
-def format_alpaca_prompt(history, user_input, system_prompt):
-    """Formats input in Alpaca/LLaMA style with conversation history"""
-    formatted_history = "\n".join([f"User: {h[0]}\nAssistant: {h[1]}" for h in history])
-    prompt = f"""{system_prompt}\n{formatted_history}\nUser: {user_input}\nAssistant:"""
+def format_alpaca_prompt(user_input, system_prompt):
+    """Formats input in Alpaca/LLaMA style"""
+    prompt = f"""{system_prompt}
+
+### Instruction:
+{user_input}
+
+### Response:
+"""
     return prompt
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
-    formatted_prompt = format_alpaca_prompt(history, message, system_message)
-    
+    formatted_prompt = format_alpaca_prompt(message, system_message)
+
     response = client.text_generation(
         formatted_prompt,
         max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
     )
+
+    # ✅ Extract only the response
+    cleaned_response = response.split("### Response:")[-1].strip()
     
-    # Extract only the response
-    cleaned_response = response.strip().split("Assistant:")[-1].strip()
-    
-    # Update history
-    history.append((message, cleaned_response))
-    
-    return cleaned_response  # Output only the answer
+    yield cleaned_response  # ✅ Output only the answer
 
 demo = gr.ChatInterface(
     respond,
@@ -38,5 +39,6 @@ demo = gr.ChatInterface(
     ],
 )
 
-if __name__ == "__main__":
-    demo.launch()
+if 
+__name__ == "__main__":
+    demo.launch()