← zurück zur Übersicht

2026-06-21T12-59-50Z_pinecone-S1-topk

pineconeStufe S1 · 5.00 GBtopkStatus: ok

Metriken

Throughput
Latenz ⌀
19.62 ms
Latenz p50
17.00 ms
Latenz p95
27.00 ms
Latenz p99
68.00 ms
Recall@1
93.30%
Recall@10
92.76%
Recall@100
91.48%
Precision@10
92.76%
NDCG@10

Rohdaten

Konfiguration

Config-Name
pinecone-S1-topk
DB-Version
serverless
Image
Index-Typ
serverless
Index-Params
{"spec":"serverless","region":"aws-us-east-1","metric":"cosine"}
Dataset
S1 · 1.350.000 Vektoren · dim 1024 · Variante A · 5.00 GB
Queries
1.000 (Concurrency 1)

Lauf

Gestartet
21.06.2026, 14:59:50
Beendet
21.06.2026, 14:59:50
Dauer
0s
Index-Bauzeit
6.99s
Index-Größe
CPU ⌀ / Peak
— / — cores
RAM ⌀ / Peak
— / — MB
Disk read (Paging)
Disk write
Pod-RAM-Limit
Default
Warmup-Queries
K8s
Nodes
undefined

Notizen

measured: host-side (pinecone-bench)
latency_source: x-envoy-upstream-service-time (server-side)
client_latency_ms_p50: 498.5
response_duration_ms_p50: 112
n_vectors_actual: 1350000
gt_file: ground_truth_ids.npy
gt_note: null
serverless: true
insert_time_s: 4899.9