Update app.py

app.py

@@ -2,7 +2,7 @@ import os
 import streamlit as st
 from dotenv import load_dotenv
 from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.llms import llamacpp
+from langchain_community.llms import llamacpp, LlamaCpp
 from langchain_core.runnables.history import RunnableWithMessageHistory
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler
@@ -16,7 +16,7 @@ from langchain.text_splitter import TokenTextSplitter, RecursiveCharacterTextSpl
 from langchain_community.document_loaders.directory import DirectoryLoader
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.runnables import RunnablePassthrough
-
+from langchain_experimental.chat_models import Llama2Chat
 
 lang_api_key = os.getenv("lang_api_key")
 
@@ -173,6 +173,8 @@ def create_conversational_rag_chain(retriever):
         verbose=False,
     )
 
+    model = Llama2Chat(llm=llm)
+    
     template = """Answer the question, based only on the following context:
     {context}.Be consise.
     Question: {question}