← zurück zur Übersicht

2026-06-14T15-15-40Z_pgvector-S1-ivfflat-hybrid-r2

pgvectorStufe S1 · 5.00 GBhybridStatus: ok

Metriken

Throughput
7.1 QPS
Latenz ⌀
139.94 ms
Latenz p50
122.25 ms
Latenz p95
223.14 ms
Latenz p99
332.96 ms
Recall@1
10.40%
Recall@10
25.53%
Recall@100
30.80%
Precision@10
25.53%
NDCG@10
35.44%

Rohdaten

Konfiguration

Config-Name
pgvector-S1-ivfflat-hybrid
DB-Version
Image
Index-Typ
ivfflat
Index-Params
{"lists":1200,"probes":10}
Dataset
S1 · 1.350.000 Vektoren · dim 1024 · Variante A · 5.00 GB
Queries
2.000 (Concurrency 1)

Lauf

Gestartet
14.06.2026, 17:15:40
Beendet
14.06.2026, 17:20:26
Dauer
7486s
Index-Bauzeit
157.83s
Index-Größe
10556.3 MB
CPU ⌀ / Peak
0.46 / 1.39 cores
RAM ⌀ / Peak
7440 / 7455 MB
Disk read (Paging)
33385 MB
Disk write
100 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: 2026-06-14T15:00:37Z
ingest_config: pgvector-S1-ivfflat
insert_time_s: 522.73
n_vectors_actual: 1350000
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: 2026-06-14T15-10-44Z_pgvector-S1-ivfflat-hybrid
repeat_index: 2
repeat_total: 3