32 lines
944 B
Python
32 lines
944 B
Python
"""
|
|
FILE: app/core/chunking/chunking_models.py
|
|
DESCRIPTION: Datenklassen für das Chunking-System.
|
|
"""
|
|
from dataclasses import dataclass, field
|
|
from typing import List, Dict, Optional, Any
|
|
|
|
@dataclass
|
|
class RawBlock:
|
|
"""Repräsentiert einen logischen Block aus dem Markdown-Parsing."""
|
|
kind: str
|
|
text: str
|
|
level: Optional[int]
|
|
section_path: str
|
|
section_title: Optional[str]
|
|
exclude_from_chunking: bool = False # WP-24c v4.2.0: Flag für Edge-Zonen, die nicht gechunkt werden sollen
|
|
|
|
@dataclass
|
|
class Chunk:
|
|
"""Das finale Chunk-Objekt für Embedding und Graph-Speicherung."""
|
|
id: str
|
|
note_id: str
|
|
index: int
|
|
text: str
|
|
window: str
|
|
token_count: int
|
|
section_title: Optional[str]
|
|
section_path: str
|
|
neighbors_prev: Optional[str]
|
|
neighbors_next: Optional[str]
|
|
candidate_pool: List[Dict[str, Any]] = field(default_factory=list)
|
|
suggested_edges: Optional[List[str]] = None |