92 lines
3.8 KiB
Python
92 lines
3.8 KiB
Python
"""
|
|
FILE: app/core/ingestion/ingestion_chunk_payload.py
|
|
DESCRIPTION: Baut das JSON-Objekt für 'mindnet_chunks'.
|
|
Fix v2.4.2: Audit-Check (Cleanup pop, Config-Resolution Hierarchie).
|
|
VERSION: 2.4.2
|
|
STATUS: Active
|
|
"""
|
|
from __future__ import annotations
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Resolution Helpers (Audited)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def _as_list(x):
|
|
if x is None: return []
|
|
return x if isinstance(x, list) else [x]
|
|
|
|
def _resolve_val(note_type: str, reg: dict, key: str, default: Any) -> Any:
|
|
"""Hierarchische Suche: Type > Default."""
|
|
types = reg.get("types", {})
|
|
if isinstance(types, dict):
|
|
t_cfg = types.get(note_type, {})
|
|
if isinstance(t_cfg, dict):
|
|
val = t_cfg.get(key) or t_cfg.get(key.replace("ing", "")) # chunking_ vs chunk_
|
|
if val is not None: return val
|
|
defs = reg.get("defaults", {}) or reg.get("global", {})
|
|
if isinstance(defs, dict):
|
|
val = defs.get(key) or defs.get(key.replace("ing", ""))
|
|
if val is not None: return val
|
|
return default
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Haupt-API
|
|
# ---------------------------------------------------------------------------
|
|
|
|
def make_chunk_payloads(note: Dict[str, Any], note_path: str, chunks_from_chunker: List[Any], **kwargs) -> List[Dict[str, Any]]:
|
|
"""Erstellt die Payloads für die Chunks inklusive Audit-Resolution."""
|
|
if isinstance(note, dict) and "frontmatter" in note: fm = note["frontmatter"]
|
|
else: fm = note or {}
|
|
|
|
reg = kwargs.get("types_cfg") or {}
|
|
note_type = fm.get("type") or "concept"
|
|
title = fm.get("title") or fm.get("id") or "Untitled"
|
|
tags = _as_list(fm.get("tags") or [])
|
|
|
|
# Audit: Resolution Hierarchie
|
|
cp = fm.get("chunking_profile") or fm.get("chunk_profile")
|
|
if not cp: cp = _resolve_val(note_type, reg, "chunking_profile", "sliding_standard")
|
|
|
|
rw = fm.get("retriever_weight")
|
|
if rw is None: rw = _resolve_val(note_type, reg, "retriever_weight", 1.0)
|
|
try: rw = float(rw)
|
|
except: rw = 1.0
|
|
|
|
out: List[Dict[str, Any]] = []
|
|
for idx, ch in enumerate(chunks_from_chunker):
|
|
is_dict = isinstance(ch, dict)
|
|
cid = getattr(ch, "id", None) if not is_dict else ch.get("id")
|
|
nid = getattr(ch, "note_id", None) if not is_dict else ch.get("note_id")
|
|
index = getattr(ch, "index", idx) if not is_dict else ch.get("index", idx)
|
|
text = getattr(ch, "text", "") if not is_dict else ch.get("text", "")
|
|
window = getattr(ch, "window", text) if not is_dict else ch.get("window", text)
|
|
prev_id = getattr(ch, "neighbors_prev", None) if not is_dict else ch.get("neighbors_prev")
|
|
next_id = getattr(ch, "neighbors_next", None) if not is_dict else ch.get("neighbors_next")
|
|
section = getattr(ch, "section_title", "") if not is_dict else ch.get("section", "")
|
|
|
|
pl: Dict[str, Any] = {
|
|
"note_id": nid or fm.get("id"),
|
|
"chunk_id": cid,
|
|
"title": title,
|
|
"index": int(index),
|
|
"ord": int(index) + 1,
|
|
"type": note_type,
|
|
"tags": tags,
|
|
"text": text,
|
|
"window": window,
|
|
"neighbors_prev": _as_list(prev_id),
|
|
"neighbors_next": _as_list(next_id),
|
|
"section": section,
|
|
"path": note_path,
|
|
"source_path": kwargs.get("file_path") or note_path,
|
|
"retriever_weight": rw,
|
|
"chunk_profile": cp
|
|
}
|
|
|
|
# Audit: Cleanup Pop (Alias Felder entfernen)
|
|
for alias in ("chunk_num", "Chunk_Number"):
|
|
pl.pop(alias, None)
|
|
|
|
out.append(pl)
|
|
return out |