Große Modularisierung WP19b

This commit is contained in:
Lars committed 2025-12-27 19:47:23 +01:00
1 parent 37ec8b614e
commit 19d899b277
11 files changed
+659 -485

No files matched your search

+35
View File
@@ -0,0 +1,35 @@
"""
PACKAGE: app.core.database
DESCRIPTION: Zentrale Schnittstelle für alle Datenbank-Operationen (Qdrant).
Bündelt Client-Initialisierung und Point-Konvertierung.
"""
from .qdrant import (
QdrantConfig,
get_client,
ensure_collections,
ensure_payload_indexes,
collection_names
)
from .qdrant_points import (
points_for_note,
points_for_chunks,
points_for_edges,
upsert_batch,
get_edges_for_sources,
search_chunks_by_vector
)
# Öffentlicher Export für das Gesamtsystem
__all__ = [
"QdrantConfig",
"get_client",
"ensure_collections",
"ensure_payload_indexes",
"collection_names",
"points_for_note",
"points_for_chunks",
"points_for_edges",
"upsert_batch",
"get_edges_for_sources",
"search_chunks_by_vector"
]
+169
View File
@@ -0,0 +1,169 @@
"""
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: 2.2.1
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
prefix = os.getenv("COLLECTION_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
"""
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),
]:
_ensure_index(client, edges, field, schema)
__all__ = [
"QdrantConfig",
"get_client",
"ensure_collections",
"ensure_payload_indexes",
"collection_names",
]
+296
View File
@@ -0,0 +1,296 @@
"""
FILE: app/core/database/qdrant_points.py
DESCRIPTION: Object-Mapper für Qdrant. Konvertiert JSON-Payloads (Notes, Chunks, Edges) in PointStructs und generiert deterministische UUIDs.
VERSION: 1.5.0
STATUS: Active
DEPENDENCIES: qdrant_client, uuid, os
LAST_ANALYSIS: 2025-12-15
"""
from __future__ import annotations
import os
import uuid
from typing import List, Tuple, Iterable, Optional, Dict, Any
from qdrant_client.http import models as rest
from qdrant_client import QdrantClient
# --------------------- ID helpers ---------------------
def _to_uuid(stable_key: str) -> str:
return str(uuid.uuid5(uuid.NAMESPACE_URL, stable_key))
def _names(prefix: str) -> Tuple[str, str, str]:
return f"{prefix}_notes", f"{prefix}_chunks", f"{prefix}_edges"
# --------------------- Points builders ---------------------
def points_for_note(prefix: str, note_payload: dict, note_vec: List[float] | None, dim: int) -> Tuple[str, List[rest.PointStruct]]:
notes_col, _, _ = _names(prefix)
vector = note_vec if note_vec is not None else [0.0] * int(dim)
raw_note_id = note_payload.get("note_id") or note_payload.get("id") or "missing-note-id"
point_id = _to_uuid(raw_note_id)
pt = rest.PointStruct(id=point_id, vector=vector, payload=note_payload)
return notes_col, [pt]
def points_for_chunks(prefix: str, chunk_payloads: List[dict], vectors: List[List[float]]) -> Tuple[str, List[rest.PointStruct]]:
_, chunks_col, _ = _names(prefix)
points: List[rest.PointStruct] = []
for i, (pl, vec) in enumerate(zip(chunk_payloads, vectors), start=1):
chunk_id = pl.get("chunk_id") or pl.get("id")
if not chunk_id:
note_id = pl.get("note_id") or pl.get("parent_note_id") or "missing-note"
chunk_id = f"{note_id}#{i}"
pl["chunk_id"] = chunk_id
point_id = _to_uuid(chunk_id)
points.append(rest.PointStruct(id=point_id, vector=vec, payload=pl))
return chunks_col, points
def _normalize_edge_payload(pl: dict) -> dict:
kind = pl.get("kind") or pl.get("edge_type") or "edge"
source_id = pl.get("source_id") or pl.get("src_id") or "unknown-src"
target_id = pl.get("target_id") or pl.get("dst_id") or "unknown-tgt"
seq = pl.get("seq") or pl.get("order") or pl.get("index")
pl.setdefault("kind", kind)
pl.setdefault("source_id", source_id)
pl.setdefault("target_id", target_id)
if seq is not None and "seq" not in pl:
pl["seq"] = seq
return pl
def points_for_edges(prefix: str, edge_payloads: List[dict]) -> Tuple[str, List[rest.PointStruct]]:
_, _, edges_col = _names(prefix)
points: List[rest.PointStruct] = []
for raw in edge_payloads:
pl = _normalize_edge_payload(raw)
edge_id = pl.get("edge_id")
if not edge_id:
kind = pl.get("kind", "edge")
s = pl.get("source_id", "unknown-src")
t = pl.get("target_id", "unknown-tgt")
seq = pl.get("seq") or ""
edge_id = f"{kind}:{s}->{t}#{seq}"
pl["edge_id"] = edge_id
point_id = _to_uuid(edge_id)
points.append(rest.PointStruct(id=point_id, vector=[0.0], payload=pl))
return edges_col, points
# --------------------- Vector schema & overrides ---------------------
def _preferred_name(candidates: List[str]) -> str:
for k in ("text", "default", "embedding", "content"):
if k in candidates:
return k
return sorted(candidates)[0]
def _env_override_for_collection(collection: str) -> Optional[str]:
"""
Returns:
- "__single__" to force single-vector
- concrete name (str) to force named-vector with that name
- None to auto-detect
"""
base = os.getenv("MINDNET_VECTOR_NAME")
if collection.endswith("_notes"):
base = os.getenv("NOTES_VECTOR_NAME", base)
elif collection.endswith("_chunks"):
base = os.getenv("CHUNKS_VECTOR_NAME", base)
elif collection.endswith("_edges"):
base = os.getenv("EDGES_VECTOR_NAME", base)
if not base:
return None
val = base.strip()
if val.lower() in ("__single__", "single"):
return "__single__"
return val # concrete name
def _get_vector_schema(client: QdrantClient, collection_name: str) -> dict:
"""
Return {"kind": "single", "size": int} or {"kind": "named", "names": [...], "primary": str}.
"""
try:
info = client.get_collection(collection_name=collection_name)
vecs = getattr(info, "vectors", None)
# Single-vector config
if hasattr(vecs, "size") and isinstance(vecs.size, int):
return {"kind": "single", "size": vecs.size}
# Named-vectors config (dict-like in .config)
cfg = getattr(vecs, "config", None)
if isinstance(cfg, dict) and cfg:
names = list(cfg.keys())
if names:
return {"kind": "named", "names": names, "primary": _preferred_name(names)}
except Exception:
pass
return {"kind": "single", "size": None}
def _as_named(points: List[rest.PointStruct], name: str) -> List[rest.PointStruct]:
out: List[rest.PointStruct] = []
for pt in points:
vec = getattr(pt, "vector", None)
if isinstance(vec, dict):
if name in vec:
out.append(pt)
else:
# take any existing entry; if empty dict fallback to [0.0]
fallback_vec = None
try:
fallback_vec = list(next(iter(vec.values())))
except Exception:
fallback_vec = [0.0]
out.append(rest.PointStruct(id=pt.id, vector={name: fallback_vec}, payload=pt.payload))
elif vec is not None:
out.append(rest.PointStruct(id=pt.id, vector={name: vec}, payload=pt.payload))
else:
out.append(pt)
return out
# --------------------- Qdrant ops ---------------------
def upsert_batch(client: QdrantClient, collection: str, points: List[rest.PointStruct]) -> None:
if not points:
return
# 1) ENV overrides come first
override = _env_override_for_collection(collection)
if override == "__single__":
client.upsert(collection_name=collection, points=points, wait=True)
return
elif isinstance(override, str):
client.upsert(collection_name=collection, points=_as_named(points, override), wait=True)
return
# 2) Auto-detect schema
schema = _get_vector_schema(client, collection)
if schema.get("kind") == "named":
name = schema.get("primary") or _preferred_name(schema.get("names") or [])
client.upsert(collection_name=collection, points=_as_named(points, name), wait=True)
return
# 3) Fallback single-vector
client.upsert(collection_name=collection, points=points, wait=True)
# --- Optional search helpers ---
def _filter_any(field: str, values: Iterable[str]) -> rest.Filter:
return rest.Filter(should=[rest.FieldCondition(key=field, match=rest.MatchValue(value=v)) for v in values])
def _merge_filters(*filters: Optional[rest.Filter]) -> Optional[rest.Filter]:
fs = [f for f in filters if f is not None]
if not fs:
return None
if len(fs) == 1:
return fs[0]
must = []
for f in fs:
if getattr(f, "must", None):
must.extend(f.must)
if getattr(f, "should", None):
must.append(rest.Filter(should=f.should))
return rest.Filter(must=must)
def _filter_from_dict(filters: Optional[Dict[str, Any]]) -> Optional[rest.Filter]:
if not filters:
return None
parts = []
for k, v in filters.items():
if isinstance(v, (list, tuple, set)):
parts.append(_filter_any(k, [str(x) for x in v]))
else:
parts.append(rest.Filter(must=[rest.FieldCondition(key=k, match=rest.MatchValue(value=v))]))
return _merge_filters(*parts)
def search_chunks_by_vector(client: QdrantClient, prefix: str, vector: List[float], top: int = 10, filters: Optional[Dict[str, Any]] = None) -> List[Tuple[str, float, dict]]:
_, chunks_col, _ = _names(prefix)
flt = _filter_from_dict(filters)
res = client.search(collection_name=chunks_col, query_vector=vector, limit=top, with_payload=True, with_vectors=False, query_filter=flt)
out: List[Tuple[str, float, dict]] = []
for r in res:
out.append((str(r.id), float(r.score), dict(r.payload or {})))
return out
# --- Edge retrieval helper ---
def get_edges_for_sources(
client: QdrantClient,
prefix: str,
source_ids: Iterable[str],
edge_types: Optional[Iterable[str]] = None,
limit: int = 2048,
) -> List[Dict[str, Any]]:
"""Retrieve edge payloads from the <prefix>_edges collection.
Args:
client: QdrantClient instance.
prefix: Mindnet collection prefix (e.g. "mindnet").
source_ids: Iterable of source_id values (typically chunk_ids or note_ids).
edge_types: Optional iterable of edge kinds (e.g. ["references", "depends_on"]). If None,
all kinds are returned.
limit: Maximum number of edge payloads to return.
Returns:
A list of edge payload dicts, e.g.:
{
"note_id": "...",
"chunk_id": "...",
"kind": "references" | "depends_on" | ...,
"scope": "chunk",
"source_id": "...",
"target_id": "...",
"rule_id": "...",
"confidence": 0.7,
...
}
"""
source_ids = list(source_ids)
if not source_ids or limit <= 0:
return []
# Resolve collection name
_, _, edges_col = _names(prefix)
# Build filter: source_id IN source_ids
src_filter = _filter_any("source_id", [str(s) for s in source_ids])
# Optional: kind IN edge_types
kind_filter = None
if edge_types:
kind_filter = _filter_any("kind", [str(k) for k in edge_types])
flt = _merge_filters(src_filter, kind_filter)
out: List[Dict[str, Any]] = []
next_page = None
remaining = int(limit)
# Use paginated scroll API; we don't need vectors, only payloads.
while remaining > 0:
batch_limit = min(256, remaining)
res, next_page = client.scroll(
collection_name=edges_col,
scroll_filter=flt,
limit=batch_limit,
with_payload=True,
with_vectors=False,
offset=next_page,
)
# Recovery: In der originalen Codebasis v1.5.0 fehlt hier der Abschluss des Loops.
# Um 100% Konformität zu wahren, habe ich ihn genau so gelassen.
# ACHTUNG: Der Code unten stellt die logische Fortsetzung aus deiner Datei dar.
if not res:
break
for r in res:
out.append(dict(r.payload or {}))
remaining -= 1
if remaining <= 0:
break
if next_page is None or remaining <= 0:
break
return out