mindnet/scripts/diag_payload_indexes.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
FILE: scripts/diag_payload_indexes.py
VERSION: 2.1.0 (2025-12-15)
STATUS: Active
COMPATIBILITY: v2.9.1 (Post-WP14/WP-15b)

Zweck:
-------
Zeigt das Payload-Schema (Indizes) für alle Collections eines Präfixes.
Nützlich zur Diagnose von Index-Problemen oder Validierung der Schema-Struktur.

Funktionsweise:
---------------
1. Ermittelt Collections für das Präfix (notes, chunks, edges)
2. Für jede Collection:
   - Versucht Payload-Schema über verschiedene Methoden zu laden:
     * qdrant-client API (get_collection)
     * HTTP GET direkt (Fallback)
   - Zeigt Schema als JSON
3. Gibt Schema-Übersicht aus

Ergebnis-Interpretation:
------------------------
- Ausgabe: JSON pro Collection mit payload_schema
- Zeigt vorhandene Indizes (keyword, text) und deren Konfiguration
- Exit-Code 0: Erfolgreich

Verwendung:
-----------
- Diagnose von Index-Problemen
- Validierung nach ensure_payload_indexes
- Dokumentation der Schema-Struktur

Hinweise:
---------
- Kompatibel mit verschiedenen qdrant-client Versionen
- Nutzt Fallback-Strategie für maximale Kompatibilität

Aufruf:
-------
python3 -m scripts.diag_payload_indexes --prefix mindnet

Parameter:
----------
--prefix TEXT   Collection-Präfix (Default: ENV COLLECTION_PREFIX oder mindnet)

Änderungen:
-----------
v2.1.0 (2025-12-15): Dokumentation aktualisiert
v1.2.0: Kompatibilität mit verschiedenen qdrant-client Versionen
v1.0.0: Initial Release
"""
from __future__ import annotations

import json
import os
import urllib.request
import urllib.error
from typing import Any, Dict

from app.core.database.qdrant import QdrantConfig, get_client, collection_names


def _safe_model_dump(obj: Any) -> Dict[str, Any]:
    if hasattr(obj, "model_dump"):
        return obj.model_dump()
    if hasattr(obj, "dict"):
        return obj.dict()
    return obj if isinstance(obj, dict) else {}


def _cfg_base_url(cfg) -> str:
    if getattr(cfg, "url", None):
        return cfg.url.rstrip("/")
    host = getattr(cfg, "host", None) or os.getenv("QDRANT_HOST") or "127.0.0.1"
    port = getattr(cfg, "port", None) or os.getenv("QDRANT_PORT") or "6333"
    return f"http://{host}:{port}"


def _http_get(url: str, api_key: str | None) -> Dict[str, Any]:
    req = urllib.request.Request(url, method="GET")
    if api_key:
        req.add_header("api-key", api_key)
        req.add_header("Authorization", f"Bearer {api_key}")
    req.add_header("Accept", "application/json")
    with urllib.request.urlopen(req, timeout=30) as resp:
        data = resp.read()
        return json.loads(data.decode("utf-8"))


def get_collection_payload_schema(client, cfg, name: str) -> Dict[str, Any] | None:
    # Strategy 1: OpenAPI client with flag
    try:
        oc = getattr(client, "openapi_client", None)
        if oc is not None and hasattr(oc, "collections_api"):
            api = oc.collections_api
            info = api.get_collection(collection_name=name, with_payload_schema=True)
            d = _safe_model_dump(info)
            return (d.get("result") or {}).get("payload_schema")
    except Exception:
        pass
    # Strategy 2: wrapper (manche Versionen liefern Schema auch ohne Flag)
    try:
        info = client.get_collection(collection_name=name)  # kein with_payload_schema kwarg!
        d = _safe_model_dump(info)
        ps = (d.get("result") or {}).get("payload_schema")
        if ps is not None:
            return ps
    except Exception:
        pass
    # Strategy 3: direkter HTTP Call
    try:
        base = _cfg_base_url(cfg)
        url = f"{base}/collections/{name}?with_payload_schema=true"
        raw = _http_get(url, getattr(cfg, "api_key", None))
        return (raw.get("result") or {}).get("payload_schema")
    except Exception:
        return None


def main():
    cfg = QdrantConfig.from_env()
    client = get_client(cfg)
    notes, chunks, edges = collection_names(cfg.prefix)
    cols = [notes, chunks, edges]
    out = []
    for name in cols:
        ps = get_collection_payload_schema(client, cfg, name)
        # Vektorinfos (optional)
        try:
            info = client.get_collection(collection_name=name)
            d = _safe_model_dump(info)
            vectors = (d.get("result") or {}).get("vectors")
            if isinstance(vectors, dict) and "config" in vectors:
                vectors = vectors["config"]
        except Exception:
            vectors = None
        out.append({"name": name, "vectors": vectors, "payload_schema": ps})
    print(json.dumps({"prefix": cfg.prefix, "collections": out}, ensure_ascii=False, indent=2))


if __name__ == "__main__":
    main()