Update app.py

app.py

@@ -3,7 +3,6 @@ import streamlit as st
 
 from langchain.embeddings import HuggingFaceInstructEmbeddings, HuggingFaceEmbeddings
 from langchain.vectorstores.faiss import FAISS
-from langchain.chains import ChatVectorDBChain
 from huggingface_hub import snapshot_download
 from langchain.chat_models import ChatOpenAI
 from langchain.prompts.chat import (
@@ -18,6 +17,11 @@ from langchain.schema import (
     SystemMessage
 )
 
+from langchain.chains.llm import LLMChain
+from langchain.callbacks.base import CallbackManager
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_PROMPT
+from langchain.chains.question_answering import load_qa_chain
 
 st.set_page_config(page_title="CFA Level 1", page_icon="📖")
 
@@ -114,14 +118,23 @@ def load_prompt():
     
 @st.experimental_singleton(show_spinner=False)
 def load_chain():
-    llm = ChatOpenAI(temperature=0)
+    '''Load langchain Conversational Retrieval Chain'''
+    
     cfa_db = load_vectorstore(embeddings)
-
-    qa = ChatVectorDBChain.from_llm(llm, 
-                                    cfa_db,
-                                    qa_prompt=load_prompt(),
-                                    return_source_documents=True,
-                                   )
+    llm = ChatOpenAI(temperature=0)
+    streaming_llm = ChatOpenAI(streaming=True, 
+                               callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), 
+                               verbose=True, 
+                               temperature=0)
+
+    question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)
+    doc_chain = load_qa_chain(streaming_llm, chain_type="stuff", prompt=load_prompt())
+
+    qa = ConversationalRetrievalChain(
+        retriever=vectorstore.as_retriever(), 
+        combine_docs_chain=doc_chain, 
+        question_generator=question_generator,
+        return_source_documents=True)
     
     return qa