import pymupdf from io import BytesIO import docx2txt def extract_text_from_bytes(pdf_bytes): try: memory_stream = BytesIO(pdf_bytes) doc = pymupdf.open(stream=memory_stream, filetype="pdf") text = "" for page in doc: text += page.get_text() doc.close() return text except Exception as e: return f"Error reading PDF: {str(e)}" def extract_text_from_docx(docx_bytes): try: docx_stream = BytesIO(docx_bytes) text = docx2txt.process(docx_stream) return text except Exception as e: return f"Error reading DOCX: {str(e)}"