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_community.embeddings import HuggingFaceEmbeddings  # Updated import
+from langchain_community.embeddings import HuggingFaceEmbeddings  # ✅ Fixed Import
 from langchain.vectorstores import FAISS
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
@@ -22,25 +22,24 @@ 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() or ""
+            text += page.extract_text() or ""  # Ensure it doesn't break if extract_text() returns None
     return text
 
 # Function to split extracted text into chunks
 def get_text_chunks(text):
     text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len)
-    chunks = text_splitter.split_text(text)
-    return chunks
+    return text_splitter.split_text(text)
 
 # Function to create a FAISS vectorstore using Hugging Face Embeddings
 def get_vectorstore(text_chunks):
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")  # ✅ Open-source model
     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
     return vectorstore
 
 # Function to set up the conversational retrieval chain
 def get_conversation_chain(vectorstore):
     try:
-        llm = ChatGroq(model="llama-3.3-70b-versatile", temperature=0.5)
+        llm = ChatGroq(model="llama-3.3-70b-versatile", temperature=0.5)  # ✅ Uses GROQ LLaMA model
         memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
         
         conversation_chain = ConversationalRetrievalChain.from_llm(