Files
mdmem/eval/queries.synthetic.yaml
T
Markus 8e5e3e6309 feat(p5): eval harness — metrics, bootstrap CIs, ablation matrix, MIN_SCORE calibration
Every variant runs at the same char budget; dim variants build and delete their
own index. pick_default() only names a new default when its nDCG@10 CI clears
the baseline's. First run is synthetic (fake embeddings, 18 queries) and is
recorded as a machinery check, not a tuning result — defaults stay RRF/2560.
2026-09-12 08:12:34 +00:00

23 lines
2.4 KiB
YAML

# Synthetic query set over eval/corpus (12 seeded notes). It exists so the
# harness itself can be exercised offline with --fake-embeddings. It is NOT a
# tuning set: the vectors are hashed word bags, not Qwen3, and 18 queries over
# 12 notes cannot separate fusion variants. Real tuning needs eval/queries.yaml.
- {q: "Welcher Router verteilt meine lokalen Modelle?", relevant: ["01M00000000000000000000SWP"], category: single, lang: de}
- {q: "llama-swap", relevant: ["01M00000000000000000000SWP"], category: single, lang: de}
- {q: "Which gateway sits in front of llama-swap?", relevant: ["01M00000000000000000000BFR"], category: single, lang: en}
- {q: "Wo hält Bifrost die virtuellen Schlüssel?", relevant: ["01M00000000000000000000BFR"], category: single, lang: de}
- {q: "Wie heißt die GPU-Box?", relevant: ["01M00000000000000000000EVX"], category: single, lang: de}
- {q: "storage class for persistent volumes", relevant: ["01M00000000000000000000STG"], category: single, lang: en}
- {q: "Welche StorageClass nutzt der Cluster?", relevant: ["01M00000000000000000000STG"], category: single, lang: de}
- {q: "Wie oft laufen die Backups?", relevant: ["01M00000000000000000000VSY"], category: single, lang: de}
- {q: "restic snapshot schedule", relevant: ["01M00000000000000000000VSY"], category: single, lang: en}
- {q: "Wie melde ich mich bei den Web-UIs an?", relevant: ["01M00000000000000000000PKT"], category: single, lang: de}
- {q: "Wie entkalke ich die Kaffeemaschine?", relevant: ["01M00000000000000000000KAF"], category: single, lang: de}
- {q: "Pegel am Traunsee", relevant: ["01M00000000000000000000TRN"], category: single, lang: de}
- {q: "Wie heißt der Modellrouter jetzt?", relevant: ["01M00000000000000000000BFR"], category: update, lang: de}
- {q: "Welches Embedding-Modell und welche Quantisierung?", relevant: ["01M00000000000000000000QWN"], category: multi, lang: de}
- {q: "Woher kommen die Container-Images und wer rollt sie aus?", relevant: ["01M00000000000000000000HRB", "01M00000000000000000000FXC"], category: multi, lang: de}
- {q: "Was wurde am 11. September 2026 entschieden?", relevant: ["01M00000000000000000000VSY"], category: temporal, lang: de, since: "2026-09-01T00:00:00Z", until: "2026-12-31T00:00:00Z"}
- {q: "Wie ist die Telefonnummer meines Zahnarztes?", relevant: [], category: abstain, lang: de}
- {q: "Wann fährt der letzte Zug nach Wien?", relevant: [], category: abstain, lang: de}