Update app.py

app.py

@@ -4,22 +4,22 @@ from transformers import RagTokenizer, RagRetriever, RagSequenceForGeneration
 import pandas as pd
 import pdfplumber
 
-# Initialize RAG components
+# Load the RAG model and tokenizer
 tokenizer = RagTokenizer.from_pretrained("facebook/rag-sequence-nq")
-retriever = RagRetriever.from_pretrained("facebook/wiki_dpr", use_dummy_dataset=True)  # Correct usage of dataset
+retriever = RagRetriever.from_pretrained("facebook/wiki_dpr", use_dummy_dataset=True)
 model = RagSequenceForGeneration.from_pretrained("facebook/rag-sequence-nq", retriever=retriever)
 
-# Extract text from PDF
+# Function to extract text from a PDF file
 def extract_text_from_pdf(pdf_file):
+    text = ""
     with pdfplumber.open(pdf_file) as pdf:
-        text = ""
         for page in pdf.pages:
             page_text = page.extract_text()
             if page_text:
                 text += page_text + "\n"
     return text.strip()
 
-# Streamlit UI
+# Streamlit app
 st.title("RAG-Powered PDF & CSV Chatbot")
 
 # CSV file upload