Lars
17b548e9b0
All checks were successful
Deploy mindnet to llm-node / deploy (push) Successful in 3s
93 lines
2.9 KiB
Python
93 lines
2.9 KiB
Python
"""
|
||
app/core/graph_adapter.py — Adjazenzaufbau & Subgraph-Expansion (WP-04)
|
||
|
||
Zweck:
|
||
Baut aus Qdrant-Edges (Collection: *_edges) einen leichten In-Memory-Graph
|
||
und liefert Edge-basierte Kennzahlen (In-Degree, Out-Degree, edge_bonus).
|
||
Kompatibilität:
|
||
Python 3.12+, qdrant-client 1.x
|
||
Version:
|
||
0.1.0 (Erstanlage)
|
||
Stand:
|
||
2025-10-07
|
||
Bezug:
|
||
- WP-04 Edge-Gewichtungen und Heuristiken
|
||
- app/core/qdrant_points.py (get_edges_for_sources)
|
||
Nutzung:
|
||
from app.core.graph_adapter import expand
|
||
Änderungsverlauf:
|
||
0.1.0 (2025-10-07) – Erstanlage.
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
from typing import Dict, List, Optional, DefaultDict
|
||
from collections import defaultdict
|
||
from qdrant_client import QdrantClient
|
||
from app.core.qdrant_points import get_edges_for_sources
|
||
|
||
EDGE_BASE_WEIGHTS = {
|
||
"references": 0.20,
|
||
"belongs_to": 0.10,
|
||
"next": 0.06,
|
||
"prev": 0.06,
|
||
"backlink": 0.04,
|
||
"references_at": 0.08,
|
||
}
|
||
|
||
|
||
class Subgraph:
|
||
"""Leichtgewichtiger Subgraph mit Adjazenzlisten & einfachen Kennzahlen."""
|
||
|
||
def __init__(self):
|
||
self.adj: DefaultDict[str, List[Dict]] = defaultdict(list)
|
||
self.in_degree: DefaultDict[str, int] = defaultdict(int)
|
||
self.out_degree: DefaultDict[str, int] = defaultdict(int)
|
||
|
||
def add_edge(self, e: Dict):
|
||
src = e["source"]; tgt = e["target"]; kind = e["kind"]
|
||
weight = e.get("weight", EDGE_BASE_WEIGHTS.get(kind, 0.0))
|
||
self.adj[src].append({"target": tgt, "kind": kind, "weight": weight})
|
||
self.out_degree[src] += 1
|
||
self.in_degree[tgt] += 1
|
||
|
||
def aggregate_edge_bonus(self, node_id: str) -> float:
|
||
return sum(edge["weight"] for edge in self.adj.get(node_id, []))
|
||
|
||
def centrality_bonus(self, node_id: str) -> float:
|
||
import math
|
||
# Log-gedämpfter Bonus, hart begrenzt
|
||
return min(math.log1p(self.in_degree.get(node_id, 0)) / 10.0, 0.15)
|
||
|
||
|
||
def expand(client: QdrantClient, prefix: str, seeds: List[str],
|
||
depth: int = 1, edge_types: Optional[List[str]] = None) -> Subgraph:
|
||
"""
|
||
Expandiert ab Seeds entlang von Edges (bis depth), optional gefiltert nach Typen.
|
||
Seeds sind stabile payload-IDs (z. B. note_id, chunk_id).
|
||
"""
|
||
sg = Subgraph()
|
||
frontier = set(seeds)
|
||
visited = set()
|
||
|
||
for _ in range(max(depth, 0)):
|
||
if not frontier:
|
||
break
|
||
|
||
edges = get_edges_for_sources(client, prefix, list(frontier), edge_types=edge_types, limit=2048)
|
||
next_frontier = set()
|
||
for pl in edges:
|
||
e = {
|
||
"source": pl.get("source_id"),
|
||
"target": pl.get("target_id"),
|
||
"kind": pl.get("kind", "edge"),
|
||
"weight": pl.get("weight", EDGE_BASE_WEIGHTS.get(pl.get("kind", "edge"), 0.0)),
|
||
}
|
||
sg.add_edge(e)
|
||
if e["target"]:
|
||
next_frontier.add(e["target"])
|
||
|
||
visited |= frontier
|
||
frontier = next_frontier - visited
|
||
|
||
return sg
|