136 lines
5.1 KiB
Python
136 lines
5.1 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
app/core/chunk_payload.py (Mindnet V2 — types.yaml authoritative)
|
|
- neighbors_prev / neighbors_next sind Listen ([], [id]).
|
|
- retriever_weight / chunk_profile kommen aus types.yaml (Frontmatter wird ignoriert).
|
|
- Fallbacks: defaults.* in types.yaml; sonst 1.0 / "default".
|
|
- WP-11 Update: Injects 'title' into chunk payload for Discovery Service.
|
|
"""
|
|
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(note_type: str, reg: dict) -> str:
|
|
types = _get_types_map(reg)
|
|
if isinstance(types, dict):
|
|
t = types.get(note_type, {})
|
|
if isinstance(t, dict) and isinstance(t.get("chunk_profile"), str):
|
|
return t["chunk_profile"]
|
|
defs = _get_defaults(reg)
|
|
if isinstance(defs, dict) and isinstance(defs.get("chunk_profile"), str):
|
|
return defs["chunk_profile"]
|
|
return "default"
|
|
|
|
def _resolve_retriever_weight(note_type: str, reg: dict) -> float:
|
|
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)
|
|
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]]:
|
|
fm = (note or {}).get("frontmatter", {}) or {}
|
|
note_type = fm.get("type") or note.get("type") or "concept"
|
|
|
|
# WP-11 FIX: Title Extraction für Discovery Service
|
|
# Wir holen den Titel aus Frontmatter oder Fallback ID/Untitled
|
|
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()
|
|
|
|
# types.yaml authoritative
|
|
cp = _resolve_chunk_profile(note_type, reg)
|
|
rw = _resolve_retriever_weight(note_type, reg)
|
|
|
|
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 oder Keys (Chunk-Objekt oder Dict)
|
|
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, # <--- HIER: Titel in Payload einfügen
|
|
"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,
|
|
}
|
|
# Aufräumen von Alt-Feldern
|
|
for alias in ("chunk_num", "Chunk_Number"):
|
|
pl.pop(alias, None)
|
|
|
|
out.append(pl)
|
|
|
|
return out |