← zurück zur Übersicht

2026-06-16T15-28-23Z_pgvector-S0-B-hybrid-r1

pgvectorStufe S0 · 2.00 GBhybridStatus: ok

Metriken

Throughput
35.6 QPS
Latenz ⌀
28.05 ms
Latenz p50
22.52 ms
Latenz p95
44.95 ms
Latenz p99
115.72 ms
Recall@1
10.30%
Recall@10
26.80%
Recall@100
32.46%
Precision@10
26.80%
NDCG@10
36.91%

Rohdaten

Konfiguration

Config-Name
pgvector-S0-B-hybrid
DB-Version
Image
Index-Typ
ivfflat
Index-Params
{"lists":500,"probes":10}
Dataset
S0 · 550.000 Vektoren · dim 1024 · Variante B · 2.00 GB
Queries
2.000 (Concurrency 1)

Lauf

Gestartet
16.06.2026, 17:28:23
Beendet
16.06.2026, 17:29:30
Dauer
7267s
Index-Bauzeit
41.8s
Index-Größe
4300.8 MB
CPU ⌀ / Peak
0.61 / 0.96 cores
RAM ⌀ / Peak
7517 / 7686 MB
Disk read (Paging)
1810 MB
Disk write
73 MB
Pod-RAM-Limit
8 GiB
Warmup-Queries
1.000
K8s
v1.31.4+k3s1
Nodes
4

Notizen

measured: in-cluster
decoupled: true
ingested_at: 2026-06-16T15:21:23Z
ingest_config: pgvector-S0-B-ivfflat
insert_time_s: 190.1
n_vectors_actual: 550000
has_metadata: true
mem_limit_gb: 8
pre_run_reset: skipped (decoupled, warmup-discard)
n_queries_executed: 1000
n_warmup: 1000
gt_file: ground_truth_hybrid_alpha_50_ids.npy
mode: measure-only
repeat_group: 2026-06-16T15-28-23Z_pgvector-S0-B-hybrid
repeat_index: 1
repeat_total: 6