Update app.py

app.py

@@ -4,7 +4,7 @@ from dotenv import load_dotenv
 import streamlit as st
 from PyPDF2 import PdfReader
 from langchain.text_splitter import CharacterTextSplitter
-from langchain.embeddings import HuggingFaceInstructEmbeddings
+from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
@@ -25,7 +25,7 @@ def get_pdf_text(pdf_docs):
     for pdf in pdf_docs:
         pdf_reader = PdfReader(pdf)
         for page in pdf_reader.pages:
-            text += page.extract_text()
+            text += page.extract_text() or ""
     return text
 
 # Function to split the extracted text into chunks
@@ -41,7 +41,7 @@ def get_text_chunks(text):
 
 # Function to create a FAISS vectorstore using Hugging Face embeddings
 def get_vectorstore(text_chunks):
-    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
     return vectorstore