Update app.py

app.py

@@ -3,8 +3,7 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from PyPDF2 import PdfReader
 import gradio as gr
-from datasets import Dataset, load_from_disk, save_to_disk
-import faiss
+from datasets import Dataset, load_from_disk
 
 # Extract text from PDF
 def extract_text_from_pdf(pdf_path):
@@ -21,15 +20,16 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
 # Extract text from the provided PDF
-pdf_text = extract_text_from_pdf("TOPF 2564.pdf")  # Updated path
+pdf_path = "/home/user/app/TOPF 2564.pdf"  # Ensure this path is correct
+pdf_text = extract_text_from_pdf(pdf_path)
 passages = [{"title": "", "text": line} for line in pdf_text.split('\n') if line.strip()]
 
 # Create a Dataset
 dataset = Dataset.from_list(passages)
 
 # Save the dataset and create an index in the current working directory
-dataset_path = "./rag_document_dataset"
-index_path = "./rag_document_index"
+dataset_path = "/home/user/app/rag_document_dataset"
+index_path = "/home/user/app/rag_document_index"
 
 # Ensure the directory exists
 os.makedirs(dataset_path, exist_ok=True)