2026-06-16T07-35-05Z_weaviate-XS-hybrid-r3
weaviateStufe XS · 410 MBhybridStatus: ok
Metriken
Throughput
89.9 QPS
Latenz ⌀
11.10 ms
Latenz p50
7.34 ms
Latenz p95
32.49 ms
Latenz p99
60.90 ms
Recall@1
33.10%
Recall@10
45.97%
Recall@100
56.26%
Precision@10
45.97%
NDCG@10
50.94%
Rohdaten
summary.json ↗Vollständige Run-Metrikenhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T07-35-05Z_weaviate-XS-hybrid-r3/summary.jsonconfig.json ↗Eingesetzte Konfigurationhttps://raw.githubusercontent.com/unrealshape/bachelor-db-benchmark/main/results/2026-06-16T07-35-05Z_weaviate-XS-hybrid-r3/config.jsonDatensatz · 410 MB ↗Generator + Bauanleitung im RepoRun-Ordner auf GitHub ↗Beide Rohdateien im Verzeichnis
Konfiguration
- Config-Name
- weaviate-XS-hybrid
- DB-Version
- —
- Image
- —
- Index-Typ
- hnsw
- Index-Params
- {"ef":64,"ef_construction":128,"M":16}
- Dataset
- XS · 150.000 Vektoren · dim 1024 · Variante A · 410 MB
- Queries
- 2.000 (Concurrency 1)
Lauf
- Gestartet
- 16.06.2026, 09:35:05
- Beendet
- 16.06.2026, 09:35:45
- Dauer
- 7240s
- Index-Bauzeit
- 91.17s
- Index-Größe
- 958.9 MB
- CPU ⌀ / Peak
- 0.75 / 1.29 cores
- RAM ⌀ / Peak
- 1244 / 1442 MB
- Disk read (Paging)
- 0 MB
- Disk write
- 0 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: 2026-06-16T07:26:48Z
ingest_config: weaviate-XS-latency
insert_time_s: 57.48
n_vectors_actual: 150000
has_metadata: true
mem_limit_gb: 8
pre_run_reset: rollout-restart
timeout_s: 180
gomemlimit_mib: 7000
query_mem_gb: 8
n_queries_executed: 1000
n_warmup: 1000
gt_file: ground_truth_hybrid_alpha_50_ids.npy
server_latency_ms: {"source":"weaviate_prometheus","metric":"queries_durations_ms","class_name":"Bench","query_type":"get_graphql","count":1000,"count_all_types":1000,"mean_ms":10.152,"windowed":true,"p50_ms":7.205,"p95_ms":45.31,"p99_ms":68.75}
mode: measure-only
repeat_group: 2026-06-16T07-33-29Z_weaviate-XS-hybrid
repeat_index: 3
repeat_total: 6