Update app.py

app.py

@@ -14,6 +14,8 @@ from langchain.chains import ConversationChain
 from langchain.memory import ConversationBufferMemory
 from langchain_community.llms import HuggingFaceEndpoint
 import torch
+import spaces
+
 
 list_llm = ["meta-llama/Meta-Llama-3-8B-Instruct", "mistralai/Mistral-7B-Instruct-v0.2"]  
 list_llm_simple = [os.path.basename(llm) for llm in list_llm]
@@ -42,6 +44,7 @@ def create_db(splits):
 
 
 # Initialize langchain LLM chain
+@spaces.GPU(duration=60)
 def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, progress=gr.Progress()):
     if llm_model == "meta-llama/Meta-Llama-3-8B-Instruct":
         llm = HuggingFaceEndpoint(
@@ -88,6 +91,7 @@ def initialize_database(list_file_obj, progress=gr.Progress()):
     return vector_db, "Database created!"
 
 # Initialize LLM
+@spaces.GPU(duration=60)
 def initialize_LLM(llm_option, llm_temperature, max_tokens, top_k, vector_db, progress=gr.Progress()):
     # print("llm_option",llm_option)
     llm_name = list_llm[llm_option]
@@ -103,7 +107,7 @@ def format_chat_history(message, chat_history):
         formatted_chat_history.append(f"Assistant: {bot_message}")
     return formatted_chat_history
     
-
+@spaces.GPU(duration=60)
 def conversation(qa_chain, message, history):
     formatted_chat_history = format_chat_history(message, history)
     # Generate response using QA chain