api/services/document_service.py

import io
import pypdf                   

def extract_text_from_pdf(pdf_bytes: bytes) -> str:
    """
    Extracts raw text from a PDF using pypdf (runs locally, no API needed).
    Returns all pages concatenated.
    """
    reader = pypdf.PdfReader(io.BytesIO(pdf_bytes))
    pages = [page.extract_text() or "" for page in reader.pages]
    return "\n".join(pages).strip()