push

app.py

@@ -1,15 +1,15 @@
 import gradio as gr
-import fitz  # PyMuPDF
+from langchain.document_loaders import PyPDFLoader
 
 def extract_text_from_pdf(pdf_file):
-    # Open the PDF file
-    pdf_document = fitz.open(pdf_file.name)
+    # Load the PDF file using PyPDFLoader
+    loader = PyPDFLoader(pdf_file.name)
+    documents = loader.load()
     text = ""
     
-    # Extract text from each page
-    for page_num in range(len(pdf_document)):
-        page = pdf_document.load_page(page_num)
-        text += page.get_text()
+    # Extract text from each document
+    for document in documents:
+        text += document.page_content
     
     return text
 

requirements.txt

@@ -66,5 +66,5 @@ urllib3==2.0.3
 uvicorn==0.22.0
 websockets==11.0.3
 yarl==1.9.2
-pypdf
+pypdf==3.10.0
 pypdf2