mindnet/app/core/chunk_payload.py

176 lines
6.2 KiB
Python

"""
FILE: app/core/chunk_payload.py
DESCRIPTION: Baut das JSON-Objekt für 'mindnet_chunks'.
FEATURES:
- Inkludiert Nachbarschafts-IDs (prev/next) und Titel.
- FIX 3: Robuste Erkennung des Inputs (Frontmatter-Dict vs. Note-Objekt), damit Overrides ankommen.
VERSION: 2.3.0
STATUS: Active
DEPENDENCIES: yaml, os
EXTERNAL_CONFIG: config/types.yaml
"""
from __future__ import annotations
from typing import Any, Dict, List, Optional
import os, yaml
def _env(n: str, d: Optional[str]=None) -> str:
v = os.getenv(n)
return v if v is not None else (d or "")
def _load_types() -> dict:
p = _env("MINDNET_TYPES_FILE", "./config/types.yaml")
try:
with open(p, "r", encoding="utf-8") as f:
return yaml.safe_load(f) or {}
except Exception:
return {}
def _get_types_map(reg: dict) -> dict:
if isinstance(reg, dict) and isinstance(reg.get("types"), dict):
return reg["types"]
return reg if isinstance(reg, dict) else {}
def _get_defaults(reg: dict) -> dict:
if isinstance(reg, dict) and isinstance(reg.get("defaults"), dict):
return reg["defaults"]
if isinstance(reg, dict) and isinstance(reg.get("global"), dict):
return reg["global"]
return {}
def _as_float(x: Any):
try: return float(x)
except Exception: return None
def _resolve_chunk_profile_from_config(note_type: str, reg: dict) -> Optional[str]:
# 1. Type Level
types = _get_types_map(reg)
if isinstance(types, dict):
t = types.get(note_type, {})
if isinstance(t, dict):
cp = t.get("chunking_profile") or t.get("chunk_profile")
if isinstance(cp, str) and cp: return cp
# 2. Defaults Level
defs = _get_defaults(reg)
if isinstance(defs, dict):
cp = defs.get("chunking_profile") or defs.get("chunk_profile")
if isinstance(cp, str) and cp: return cp
return None
def _resolve_retriever_weight_from_config(note_type: str, reg: dict) -> float:
"""
Liest Weight nur aus Config (Type > Default).
Wird aufgerufen, wenn im Frontmatter nichts steht.
"""
# 1. Type Level
types = _get_types_map(reg)
if isinstance(types, dict):
t = types.get(note_type, {})
if isinstance(t, dict) and (t.get("retriever_weight") is not None):
v = _as_float(t.get("retriever_weight"))
if v is not None: return float(v)
# 2. Defaults Level
defs = _get_defaults(reg)
if isinstance(defs, dict) and (defs.get("retriever_weight") is not None):
v = _as_float(defs.get("retriever_weight"))
if v is not None: return float(v)
return 1.0
def _as_list(x):
if x is None: return []
if isinstance(x, list): return x
return [x]
def make_chunk_payloads(note: Dict[str, Any],
note_path: str,
chunks_from_chunker: List[Any],
*,
note_text: str = "",
types_cfg: Optional[dict] = None,
file_path: Optional[str] = None) -> List[Dict[str, Any]]:
"""
Erstellt die Payloads für die Chunks.
Argument 'note' kann sein:
A) Ein komplexes Objekt/Dict mit Key "frontmatter" (Legacy / Tests)
B) Direkt das Frontmatter-Dictionary (Call aus ingestion.py)
"""
# --- FIX 3: Intelligente Erkennung der Input-Daten ---
# Wir prüfen: Ist 'note' ein Container MIT 'frontmatter', oder IST es das 'frontmatter'?
if isinstance(note, dict) and "frontmatter" in note and isinstance(note["frontmatter"], dict):
# Fall A: Container (wir müssen auspacken)
fm = note["frontmatter"]
else:
# Fall B: Direktes Dict (so ruft ingestion.py es auf!)
fm = note or {}
note_type = fm.get("type") or note.get("type") or "concept"
# Title Extraction (Fallback Chain)
title = fm.get("title") or note.get("title") or fm.get("id") or "Untitled"
reg = types_cfg if isinstance(types_cfg, dict) else _load_types()
# --- Profil-Ermittlung ---
# Da wir 'fm' jetzt korrekt haben, funktionieren diese lookups:
cp = fm.get("chunking_profile") or fm.get("chunk_profile")
if not cp:
cp = _resolve_chunk_profile_from_config(note_type, reg)
if not cp:
cp = "sliding_standard"
# --- Retriever Weight Ermittlung ---
rw = fm.get("retriever_weight")
if rw is None:
rw = _resolve_retriever_weight_from_config(note_type, reg)
try:
rw = float(rw)
except Exception:
rw = 1.0
tags = fm.get("tags") or []
if isinstance(tags, str):
tags = [tags]
out: List[Dict[str, Any]] = []
for idx, ch in enumerate(chunks_from_chunker):
# Attribute extrahieren
cid = getattr(ch, "id", None) or (ch.get("id") if isinstance(ch, dict) else None)
nid = getattr(ch, "note_id", None) or (ch.get("note_id") if isinstance(ch, dict) else fm.get("id"))
index = getattr(ch, "index", None) or (ch.get("index") if isinstance(ch, dict) else idx)
text = getattr(ch, "text", None) or (ch.get("text") if isinstance(ch, dict) else "")
window = getattr(ch, "window", None) or (ch.get("window") if isinstance(ch, dict) else text)
prev_id = getattr(ch, "neighbors_prev", None) or (ch.get("neighbors_prev") if isinstance(ch, dict) else None)
next_id = getattr(ch, "neighbors_next", None) or (ch.get("neighbors_next") if isinstance(ch, dict) else None)
pl: Dict[str, Any] = {
"note_id": nid,
"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": getattr(ch, "section", None) or (ch.get("section") if isinstance(ch, dict) else ""),
"path": note_path,
"source_path": file_path or note_path,
"retriever_weight": float(rw),
"chunk_profile": cp, # Jetzt endlich mit dem Override-Wert!
}
# Cleanup
for alias in ("chunk_num", "Chunk_Number"):
pl.pop(alias, None)
out.append(pl)
return out