Update app.py

app.py

@@ -1,12 +1,9 @@
 # app.py
 import streamlit as st
 import os
-import shutil
 import tempfile
 from io import BytesIO
 from PyPDF2 import PdfReader
-import pandas as pd
-from docx import Document
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
@@ -54,7 +51,7 @@ with st.sidebar:
     
     # File uploader
     if st.session_state.authenticated:
-        input_data = st.file_uploader("Upload a PDF, TXT, XLS/XLSX, or DOC/DOCX file", type=["pdf", "txt", "xls", "xlsx", "doc", "docx"])
+        input_data = st.file_uploader("Upload a PDF file", type=["pdf"])
         
         if st.button("Process File") and input_data is not None:
             try:
@@ -118,14 +115,14 @@ def main():
     """, unsafe_allow_html=True)
     
     st.title("RAG Q&A App with Mistral AI")
-    st.markdown("Welcome to the BSNL RAG App! Upload your PDFs, TXTs, XLS/XLSX, or DOC/DOCX files and ask questions with ease.", unsafe_allow_html=True)
+    st.markdown("Welcome to the BSNL RAG App! Upload your PDF files and ask questions with ease.", unsafe_allow_html=True)
     
     if not st.session_state.authenticated:
         st.warning("Please authenticate with your API key in the sidebar.")
         return
     
     if st.session_state.vectorstore is None:
-        st.info("Please upload and process a PDF, TXT, XLS/XLSX, or DOC/DOCX file in the sidebar.")
+        st.info("Please upload and process a PDF file in the sidebar.")
         return
     
     query = st.text_input("Enter your question:")
@@ -146,38 +143,25 @@ def process_input(input_data):
     
     # Initialize progress bar and status
     progress_bar = st.progress(0)
-    status = st.status("Processing file...", expanded=True)
-    
-    documents = ""
-    file_name = input_data.name.lower()
+    status = st.status("Processing PDF file...", expanded=True)
     
     # Step 1: Save file temporarily
-    status.update(label="Saving file...")
+    status.update(label="Saving PDF file...")
     progress_bar.progress(0.20)
     
-    with tempfile.NamedTemporaryFile(delete=False, dir="uploads", suffix=file_name) as tmp_file:
+    with tempfile.NamedTemporaryFile(delete=False, dir="uploads", suffix=".pdf") as tmp_file:
         tmp_file.write(input_data.read())
         tmp_file_path = tmp_file.name
     
-    # Step 2: Read file
-    status.update(label="Reading file...")
+    # Step 2: Read PDF file
+    status.update(label="Reading PDF file...")
     progress_bar.progress(0.40)
     
     try:
-        if file_name.endswith(".pdf"):
-            pdf_reader = PdfReader(tmp_file_path)
-            for page in pdf_reader.pages:
-                documents += page.extract_text() or ""
-        elif file_name.endswith(".txt"):
-            with open(tmp_file_path, "r", encoding="utf-8") as f:
-                documents = f.read()
-        elif file_name.endswith((".xls", ".xlsx")):
-            df = pd.read_excel(tmp_file_path)
-            documents = " ".join(df.astype(str).values.flatten())
-        elif file_name.endswith((".doc", ".docx")):
-            doc = Document(tmp_file_path)
-            for para in doc.paragraphs:
-                documents += para.text + "\n"
+        pdf_reader = PdfReader(tmp_file_path)
+        documents = ""
+        for page in pdf_reader.pages:
+            documents += page.extract_text() or ""
     finally:
         os.remove(tmp_file_path)  # Clean up temporary file