mindnet/app/core/database/qdrant.py

"""
FILE: app/core/database/qdrant.py
DESCRIPTION: Qdrant-Client Factory und Schema-Management. 
             Erstellt Collections und Payload-Indizes.
             MODULARISIERUNG: Verschoben in das database-Paket für WP-14.
VERSION: 2.2.2 (WP-Fix: Index für target_section)
STATUS: Active
DEPENDENCIES: qdrant_client, dataclasses, os
"""
from __future__ import annotations

import os
import logging
from dataclasses import dataclass
from typing import Optional, Tuple, Dict, List

from qdrant_client import QdrantClient
from qdrant_client.http import models as rest

logger = logging.getLogger(__name__)

# ---------------------------------------------------------------------------
# Konfiguration
# ---------------------------------------------------------------------------

@dataclass
class QdrantConfig:
    """Konfigurationsobjekt für den Qdrant-Verbindungsaufbau."""
    host: Optional[str] = None
    port: Optional[int] = None
    url: Optional[str] = None
    api_key: Optional[str] = None
    prefix: str = "mindnet"
    dim: int = 384
    distance: str = "Cosine"        # Cosine | Dot | Euclid
    on_disk_payload: bool = True

    @classmethod
    def from_env(cls) -> "QdrantConfig":
        """Erstellt die Konfiguration aus Umgebungsvariablen."""
        # Entweder URL ODER Host/Port, API-Key optional
        url = os.getenv("QDRANT_URL") or None
        host = os.getenv("QDRANT_HOST") or None
        port = os.getenv("QDRANT_PORT")
        port = int(port) if port else None
        api_key = os.getenv("QDRANT_API_KEY") or None
        # WP-24c v4.5.10: Harmonisierung - Unterstützt beide Umgebungsvariablen für Abwärtskompatibilität
        # COLLECTION_PREFIX hat Priorität, MINDNET_PREFIX als Fallback
        prefix = os.getenv("COLLECTION_PREFIX") or os.getenv("MINDNET_PREFIX") or "mindnet"
        dim = int(os.getenv("VECTOR_DIM") or 384)
        distance = os.getenv("DISTANCE", "Cosine")
        on_disk_payload = (os.getenv("ON_DISK_PAYLOAD", "true").lower() == "true")
        
        return cls(
            host=host, port=port, url=url, api_key=api_key,
            prefix=prefix, dim=dim, distance=distance, on_disk_payload=on_disk_payload
        )


def get_client(cfg: QdrantConfig) -> QdrantClient:
    """Initialisiert den Qdrant-Client basierend auf der Konfiguration."""
    # QdrantClient akzeptiert entweder url=... oder host/port
    if cfg.url:
        return QdrantClient(url=cfg.url, api_key=cfg.api_key, timeout=60.0)
    return QdrantClient(host=cfg.host or "127.0.0.1", port=cfg.port or 6333, api_key=cfg.api_key, timeout=60.0)


# ---------------------------------------------------------------------------
# Collections
# ---------------------------------------------------------------------------

def collection_names(prefix: str) -> Tuple[str, str, str]:
    """Gibt die standardisierten Collection-Namen zurück."""
    return f"{prefix}_notes", f"{prefix}_chunks", f"{prefix}_edges"


def _vector_params(dim: int, distance: str) -> rest.VectorParams:
    """Erstellt Vektor-Parameter für das Collection-Schema."""
    # Distance: "Cosine" | "Dot" | "Euclid"
    dist = getattr(rest.Distance, distance.capitalize(), rest.Distance.COSINE)
    return rest.VectorParams(size=dim, distance=dist)


def ensure_collections(client: QdrantClient, prefix: str, dim: int) -> None:
    """Legt notes, chunks und edges Collections an, falls nicht vorhanden."""
    notes, chunks, edges = collection_names(prefix)

    # notes
    if not client.collection_exists(notes):
        client.create_collection(
            collection_name=notes,
            vectors_config=_vector_params(dim, os.getenv("DISTANCE", "Cosine")),
            on_disk_payload=True,
        )
    # chunks
    if not client.collection_exists(chunks):
        client.create_collection(
            collection_name=chunks,
            vectors_config=_vector_params(dim, os.getenv("DISTANCE", "Cosine")),
            on_disk_payload=True,
        )
    # edges (Dummy-Vektor, da primär via Payload gefiltert wird)
    if not client.collection_exists(edges):
        client.create_collection(
            collection_name=edges,
            vectors_config=_vector_params(1, "Dot"),
            on_disk_payload=True,
        )


# ---------------------------------------------------------------------------
# Payload-Indizes
# ---------------------------------------------------------------------------

def _ensure_index(client: QdrantClient, collection: str, field: str, schema: rest.PayloadSchemaType) -> None:
    """Idempotentes Anlegen eines Payload-Indexes für ein spezifisches Feld."""
    try:
        client.create_payload_index(collection_name=collection, field_name=field, field_schema=schema, wait=True)
    except Exception as e:
        # Fehler ignorieren, falls Index bereits existiert
        logger.debug(f"Index check for {field} in {collection}: {e}")


def ensure_payload_indexes(client: QdrantClient, prefix: str) -> None:
    """
    Stellt sicher, dass alle benötigten Payload-Indizes für die Suche existieren.
    - notes:  note_id, type, title, updated, tags
    - chunks: note_id, chunk_id, index, type, tags
    - edges:  note_id, kind, scope, source_id, target_id, chunk_id, target_section
    """
    notes, chunks, edges = collection_names(prefix)

    # NOTES
    for field, schema in [
        ("note_id",  rest.PayloadSchemaType.KEYWORD),
        ("type",     rest.PayloadSchemaType.KEYWORD),
        ("title",    rest.PayloadSchemaType.TEXT),
        ("updated",  rest.PayloadSchemaType.INTEGER),
        ("tags",     rest.PayloadSchemaType.KEYWORD),
    ]:
        _ensure_index(client, notes, field, schema)

    # CHUNKS
    for field, schema in [
        ("note_id",  rest.PayloadSchemaType.KEYWORD),
        ("chunk_id", rest.PayloadSchemaType.KEYWORD),
        ("index",    rest.PayloadSchemaType.INTEGER),
        ("type",     rest.PayloadSchemaType.KEYWORD),
        ("tags",     rest.PayloadSchemaType.KEYWORD),
    ]:
        _ensure_index(client, chunks, field, schema)

    # EDGES
    for field, schema in [
        ("note_id",   rest.PayloadSchemaType.KEYWORD),
        ("kind",      rest.PayloadSchemaType.KEYWORD),
        ("scope",     rest.PayloadSchemaType.KEYWORD),
        ("source_id", rest.PayloadSchemaType.KEYWORD),
        ("target_id", rest.PayloadSchemaType.KEYWORD),
        ("chunk_id",  rest.PayloadSchemaType.KEYWORD),
        # NEU: Index für Section-Links (WP-15b)
        ("target_section", rest.PayloadSchemaType.KEYWORD),
    ]:
        _ensure_index(client, edges, field, schema)


__all__ = [
    "QdrantConfig",
    "get_client",
    "ensure_collections",
    "ensure_payload_indexes",
    "collection_names",
]