from typing import List, Dict, Any from dataclasses import dataclass, field, asdict @dataclass class Chunk: chunk_id: int doc_id: str text: str tokens: int topic: str = "" domain: str = "" task_type: str = "" topic_purity: float = 1.0 summary: str = "" keywords: List[str] = field(default_factory=list) concepts: List[str] = field(default_factory=list) questions: List[str] = field(default_factory=list)