Update app.py

app.py

@@ -1,12 +1,12 @@
 import streamlit as st
+import os
 import speech_recognition as sr
 import fitz  # PyMuPDF
-from transformers import pipeline, AutoTokenizer, AutoModel
+from transformers import AutoTokenizer, AutoModel
 import torch
 import faiss
 import numpy as np
 from gtts import gTTS
-import os
 
 # Function to convert audio file to text
 def audio_to_text(audio_file):
@@ -51,8 +51,12 @@ model = AutoModel.from_pretrained("bert-base-uncased")
 dimension = 768  # Size of BERT embeddings
 index = faiss.IndexFlatL2(dimension)
 
-# Load and process PDFs (assume PDFs are stored at a specific path)
-pdf_paths = ["path/to/your/advice1.pdf", "path/to/your/advice2.pdf"]
+# Folder path containing PDFs
+pdf_folder_path = "path/to/your/pdf_folder"
+
+# Read all PDF files from the specified folder
+pdf_paths = [os.path.join(pdf_folder_path, f) for f in os.listdir(pdf_folder_path) if f.endswith('.pdf')]
+
 texts = []
 for path in pdf_paths:
     pdf_text = extract_text_from_pdf(path)