Update app.py

app.py

@@ -67,16 +67,7 @@ def load_db():
         embedding_function=embedding)
     return vectordb
 
-# Initialize langchain LLM chain
-llm = HuggingFaceHub(repo_id = llm_model,
-                    model_kwargs={"temperature": temperature, 
-                                  "max_new_tokens": max_tokens, 
-                                  "top_k": top_k, 
-                                  "load_in_8bit": True})
-retriever=vector_db.as_retriever()
-memory = ConversationBufferMemory(memory_key="chat_history", output_key='answer', return_messages=True)
-qa_chain = ConversationalRetrievalChain.from_llm(llm_model,retriever=retriever,chain_type="stuff", 
-                                                 memory=memory,return_source_documents=True,verbose=False,)
+
 
 
 
@@ -154,6 +145,17 @@ def conversation(qa_chain, message, history):
 vector_db, collection_name = initialize_database(list_file_obj)
 #qa_chain = 
 
+# Initialize langchain LLM chain
+llm = HuggingFaceHub(repo_id = llm_model,
+                    model_kwargs={"temperature": temperature, 
+                                  "max_new_tokens": max_tokens, 
+                                  "top_k": top_k, 
+                                  "load_in_8bit": True})
+retriever=vector_db.as_retriever()
+memory = ConversationBufferMemory(memory_key="chat_history", output_key='answer', return_messages=True)
+qa_chain = ConversationalRetrievalChain.from_llm(llm_model,retriever=retriever,chain_type="stuff", 
+                                                 memory=memory,return_source_documents=True,verbose=False,)
+
 print('qa chain and vector_db done')
 
 def demo():