Update app.py

app.py

@@ -14,7 +14,7 @@ from langchain.chains import ConversationChain
 from langchain.memory import ConversationBufferMemory
 from langchain_community.llms import HuggingFaceEndpoint
 import torch
-import spaces
+# import spaces
 
 
 list_llm = ["meta-llama/Meta-Llama-3-8B-Instruct", "mistralai/Mistral-7B-Instruct-v0.2"]  
@@ -44,7 +44,7 @@ def create_db(splits):
 
 
 # Initialize langchain LLM chain
-@spaces.GPU(duration=60)
+# @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(
@@ -81,7 +81,7 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, pr
     return qa_chain
 
 # Initialize database
-@spaces.GPU(duration=60)
+# @spaces.GPU(duration=60)
 def initialize_database(list_file_obj, progress=gr.Progress()):
     # Create a list of documents (when valid)
     list_file_path = [x.name for x in list_file_obj if x is not None]
@@ -92,7 +92,7 @@ def initialize_database(list_file_obj, progress=gr.Progress()):
     return vector_db, "Database created!"
 
 # Initialize LLM
-@spaces.GPU(duration=60)
+# @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]
@@ -108,7 +108,7 @@ def format_chat_history(message, chat_history):
         formatted_chat_history.append(f"Assistant: {bot_message}")
     return formatted_chat_history
     
-@spaces.GPU(duration=60)
+# @spaces.GPU(duration=60)
 def conversation(qa_chain, message, history):
     formatted_chat_history = format_chat_history(message, history)
     # Generate response using QA chain