pdf_classes.py

# pdf_classes.py
from docarray import BaseDoc
from docarray import DocList
from docarray.typing import ImageTensor, NdArray
from typing import Dict, Optional

class PDFSegment(BaseDoc):
    page_number: int
    segment_type: str  # 'text', 'image', 'table', or 'hybrid'
    content: Optional[str]
    image: Optional[ImageTensor]
    position: Dict[str, int]  # {x, y, width, height}
    relationships: Dict[str, Optional[str]]  # {'prev': id, 'next': id, 'parent': id}
    embedding: Optional[NdArray[768]]

class PDFPage(BaseDoc):
    page_number: int
    screenshot: ImageTensor
    embedding: Optional[NdArray[768]] = None

class RichPDFDocument(BaseDoc):
    file_path: str
    num_pages: int
    segments: DocList[PDFSegment]
    pages: DocList[PDFPage]