Update app.py

app.py

@@ -17,10 +17,10 @@ import nltk
 nltk.download('punkt')
 
 # Function to extract text from a PDF file
-def extract_text_from_pdf(pdf_file):
+def extract_text_from_pdf(pdf_data):
     text = ""
     try:
-        pdf_reader = PyPDF2.PdfReader(io.BytesIO(pdf_file))
+        pdf_reader = PyPDF2.PdfReader(io.BytesIO(pdf_data))
         for page in pdf_reader.pages:
             text += page.extract_text()
     except Exception as e:
@@ -28,10 +28,10 @@ def extract_text_from_pdf(pdf_file):
     return text
 
 # Function to extract text from a Word document
-def extract_text_from_docx(docx_file):
+def extract_text_from_docx(docx_data):
     text = ""
     try:
-        doc = Document(io.BytesIO(docx_file))
+        doc = Document(io.BytesIO(docx_data))
         text = "\n".join([para.text for para in doc.paragraphs])
     except Exception as e:
         print(f"Error extracting text from DOCX: {e}")
@@ -74,9 +74,9 @@ def upload_files(files):
     try:
         for file in files:
             if file.name.endswith('.pdf'):
-                text = extract_text_from_pdf(file.file.read())
+                text = extract_text_from_pdf(file.data)
             elif file.name.endswith('.docx'):
-                text = extract_text_from_docx(file.file.read())
+                text = extract_text_from_docx(file.data)
             else:
                 return {"error": "Unsupported file format"}