Update app.py

app.py

@@ -2,7 +2,10 @@ import streamlit as st
 from dotenv import load_dotenv
 from PyPDF2 import PdfReader
 from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
+from transformers import AutoModelForCausalLM, AutoTokenizer
 from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM
 from langchain.vectorstores import FAISS, Chroma
 from langchain.embeddings import HuggingFaceEmbeddings  # General embeddings from HuggingFace models.
 from langchain.chat_models import ChatOpenAI
@@ -60,22 +63,30 @@ def get_vectorstore(text_chunks):
 
     return vectorstore # 생성된 벡터 스토어를 반환합니다.
 
-
 def get_conversation_chain(vectorstore):
-    gpt_model_name = 'gpt-3.5-turbo'
-    llm = ChatOpenAI(model_name = gpt_model_name) #gpt-3.5 모델 로드
+    # Replace 'microsoft/DialoGPT-large' with the desired model name    
+    model_name = "Shaleen123/mistrallite_medical_qa"
+    
+    config = PeftConfig.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    model = PeftModel.from_pretrained(model, model_name)
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+
     
     # 대화 기록을 저장하기 위한 메모리를 생성합니다.
     memory = ConversationBufferMemory(
         memory_key='chat_history', return_messages=True)
+    
     # 대화 검색 체인을 생성합니다.
     conversation_chain = ConversationalRetrievalChain.from_llm(
-        llm=llm,
+        llm=model,
         retriever=vectorstore.as_retriever(),
         memory=memory
     )
+    
     return conversation_chain
 
+
 # 사용자 입력을 처리하는 함수입니다.
 def handle_userinput(user_question):
     # 대화 체인을 사용하여 사용자 질문에 대한 응답을 생성합니다.