mindnet/app/core/note_payload.py
Lars af36c410b4
All checks were successful
Deploy mindnet to llm-node / deploy (push) Successful in 3s
app/core/note_payload.py aktualisiert
2025-11-09 10:11:19 +01:00

160 lines
4.6 KiB
Python

# note_payload.py
"""
Mindnet - Note Payload Builder
Version: 1.4.3
Beschreibung:
- Robust gegenüber alten/neuen Aufrufsignaturen (toleriert *args, **kwargs).
- Liest Typ-Defaults aus ./config/config.yaml oder ./config/types.yaml.
- Setzt in mindnet_notes u.a.:
- retriever_weight (Frontmatter > Typ-Defaults > ENV > 1.0)
- chunk_profile (Frontmatter > Typ-Defaults > ENV > "medium")
- edge_defaults (Frontmatter > Typ-Defaults > [])
- path, type, title, note_id, tags, created/modified/date (falls vorhanden)
- Garantiert JSON-serialisierbare Payloads.
"""
from __future__ import annotations
from typing import Any, Dict, Optional
import os
import json
import pathlib
import yaml
def _as_dict(note: Any) -> Dict[str, Any]:
if isinstance(note, dict):
return note
d: Dict[str, Any] = {}
for attr in (
"id",
"note_id",
"title",
"path",
"frontmatter",
"meta",
"body",
"text",
"type",
"created",
"modified",
"chunks",
"tags",
):
if hasattr(note, attr):
d[attr] = getattr(note, attr)
# manche Parser nutzen "metadata" statt "frontmatter"
if "frontmatter" not in d and hasattr(note, "metadata"):
d["frontmatter"] = getattr(note, "metadata")
return d
def _load_types_config(explicit: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
if isinstance(explicit, dict):
return explicit
for rel in ("config/config.yaml", "config/types.yaml"):
p = pathlib.Path(rel)
if p.exists():
with p.open("r", encoding="utf-8") as f:
data = yaml.safe_load(f) or {}
# zulässig: {"types": {...}} oder direkt {...}
if isinstance(data, dict) and "types" in data and isinstance(data["types"], dict):
return data["types"]
return data if isinstance(data, dict) else {}
return {}
def _get_front(n: Dict[str, Any]) -> Dict[str, Any]:
fm = n.get("frontmatter") or n.get("meta") or {}
return fm if isinstance(fm, dict) else {}
def _coalesce(*vals):
for v in vals:
if v is not None:
return v
return None
def _env_float(name: str, default: float) -> float:
try:
return float(os.environ.get(name, default))
except Exception:
return default
def _ensure_list(x) -> list:
if x is None:
return []
if isinstance(x, list):
return [str(i) for i in x]
if isinstance(x, (set, tuple)):
return [str(i) for i in list(x)]
return [str(x)]
def make_note_payload(note: Any, *args, **kwargs) -> Dict[str, Any]:
"""
Build JSON-serialisable payload for a Note.
Accepts legacy extra args/kwargs (e.g. types_config, vault_root) without error.
"""
n = _as_dict(note)
types_cfg = kwargs.get("types_config") or (args[0] if args else None)
types_cfg = _load_types_config(types_cfg)
fm = _get_front(n)
note_type = str(fm.get("type") or n.get("type") or "note")
cfg_for_type = types_cfg.get(note_type, {}) if isinstance(types_cfg, dict) else {}
default_rw = _env_float("MINDNET_DEFAULT_RETRIEVER_WEIGHT", 1.0)
retriever_weight = _coalesce(
fm.get("retriever_weight"),
cfg_for_type.get("retriever_weight"),
default_rw,
)
try:
retriever_weight = float(retriever_weight)
except Exception:
retriever_weight = default_rw
chunk_profile = _coalesce(
fm.get("chunk_profile"),
cfg_for_type.get("chunk_profile"),
os.environ.get("MINDNET_DEFAULT_CHUNK_PROFILE", "medium"),
)
if not isinstance(chunk_profile, str):
chunk_profile = "medium"
edge_defaults = _ensure_list(
_coalesce(fm.get("edge_defaults"), cfg_for_type.get("edge_defaults"), [])
)
note_id = n.get("note_id") or n.get("id") or fm.get("id")
title = n.get("title") or fm.get("title") or ""
path = n.get("path")
if isinstance(path, pathlib.Path):
path = str(path)
payload: Dict[str, Any] = {
"note_id": note_id,
"title": title,
"type": note_type,
"path": path,
"retriever_weight": retriever_weight,
"chunk_profile": chunk_profile,
"edge_defaults": edge_defaults,
}
tags = fm.get("tags") or fm.get("keywords") or n.get("tags")
if tags:
payload["tags"] = _ensure_list(tags)
for k in ("created", "modified", "date"):
v = fm.get(k) or n.get(k)
if v:
payload[k] = str(v)
# Validierungs-RTT (stellt JSON-Serialisierbarkeit sicher)
json.loads(json.dumps(payload, ensure_ascii=False))
return payload