Update app.py

app.py

@@ -11,7 +11,6 @@ import torch
 from transformers import pipeline, TextIteratorStreamer, StoppingCriteria
 from transformers import AutoTokenizer
 from ddgs import DDGS
-import spaces  # Import spaces early to enable ZeroGPU support
 from torch.utils._pytree import tree_map
 from config import *
 # Global event to signal cancellation from the UI thread to the generation thread
@@ -19,9 +18,6 @@ cancel_event = threading.Event()
 
 access_token=os.environ['HF_TOKEN']
 
-# Optional: Disable GPU visibility if you wish to force CPU usage
-# os.environ["CUDA_VISIBLE_DEVICES"] = ""
-
 
 
 # Global cache for pipelines to avoid re-loading.
@@ -109,7 +105,7 @@ def get_duration(user_msg, chat_history, system_prompt, enable_search, max_resul
     
     return base_duration + token_duration + search_duration + aot_compilation_buffer
 
-@spaces.GPU(duration=get_duration)
+
 def chat_response(user_msg, chat_history, system_prompt,
                   enable_search, max_results, max_chars,
                   model_name, max_tokens, temperature,