Update app.py

app.py

@@ -128,8 +128,8 @@ def initialize_llmchain(temperature, max_tokens, top_k, vector_db, progress=gr.P
                                                           "load_in_8bit": True})
     
     progress(0.75, desc="Defining buffer memory...")
-    #memory = ConversationBufferMemory(memory_key="chat_history",output_key='answer',return_messages=True)
-    memory = ConversationBufferWindowMemory(memory_key = 'chat_history', k=3)
+    memory = ConversationBufferMemory(memory_key="chat_history",output_key='answer',return_messages=True)
+    #memory = ConversationBufferWindowMemory(memory_key = 'history', k=3)
     retriever=vector_db.as_retriever()
     progress(0.8, desc="Defining retrieval chain...")
     qa_chain = ConversationalRetrievalChain.from_llm(llm,retriever=retriever,chain_type="stuff", 
@@ -184,8 +184,8 @@ def format_chat_history(message, chat_history):
     return formatted_chat_history
     
 
-def conversation(qa_chain, message, chat_history):
-    formatted_chat_history = format_chat_history(message, chat_history)
+def conversation(qa_chain, message, history):
+    formatted_chat_history = format_chat_history(message, history)
     #print("formatted_chat_history",formatted_chat_history)
    
     # Generate response using QA chain