Update app.py

app.py

@@ -265,6 +265,7 @@ import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import os
+import spaces
 from threading import Thread
 
 import langchain
@@ -345,6 +346,7 @@ retriever = vectordb.as_retriever(search_type="similarity", search_kwargs={"k":
 def process_llm_response(llm_response):
     ans = textwrap.fill(llm_response['result'], width=1500)
     sources_used = ' \n'.join([f"{source.metadata['source'].split('/')[-1][:-4]} - page: {str(source.metadata['page'])}" for source in llm_response['source_documents']])
+    
     return f"{ans}\n\nSources:\n{sources_used}"
 
 
@@ -352,7 +354,8 @@ def process_llm_response(llm_response):
 
 
 
-@spaces.GPU
+
+@spaces.GPU(duration=60)
 def llm_ans(message, history):
     tok, model = build_model()
     terminators = [tok.eos_token_id, 32007, 32011, 32001, 32000]