Reverting back to version without memory

app.py

@@ -28,28 +28,17 @@ qa_chain = RetrievalQA.from_chain_type(
     retriever=vectordb.as_retriever()
 )
 
-# Conversation memory
-from langchain.memory import ConversationBufferMemory
-memory = ConversationBufferMemory(
-    memory_key="chat_history",
-    return_messages=True
-)
+question = "production is broken how do I fix it?"
 
-from langchain.chains import ConversationalRetrievalChain
-retriever=vectordb.as_retriever()
-qa_memory = ConversationalRetrievalChain.from_llm(
-    llm,
-    retriever=vectordb.as_retriever(),
-    memory=memory
-)
+result = qa_chain({"query": question})
+
+print(result['result'])
 
 
 # Streamed response emulator
 def response_generator(prompt):
-
-    response = qa_memory({"question": prompt})['result']   
-
-    # Fake streaming
+    response = qa_chain({"query": prompt})['result']   
+    
     for word in response.split():
         yield word + " "
         time.sleep(0.05)
@@ -76,7 +65,7 @@ if prompt := st.chat_input("What is up?"):
 
     # Display assistant response in chat message container
     with st.chat_message("assistant"):
-        response = qa_memory({"question": prompt})
-        st.write(response)
+        response = st.write_stream(response_generator(prompt))
     # Add assistant response to chat history
     st.session_state.messages.append({"role": "assistant", "content": response})
+