the.ai

Inference / Adaptive

verified

Semantic Cache

Return a stored answer when a new question means the same as an old one. An exact-match cache misses "how do I reset my password" against "password reset steps"; a semantic cache embeds both, finds them close, and serves the earlier answer — turning a model call into a vector lookup.

Viz primitive · threshold-sweepseparation = 2 · threshold = 1.4 · base-rate = 0.25
let throughcutflagged

247 of 1000 flagged. 74% of them were right and 63 were false alarms; 74% of what should have been caught was, leaving 66 missed.

Questions a cached answer genuinely fits against ones it does not, by embedding similarity. Drag the threshold up to watch false hits vanish and the hit rate go with them — a miss costs one model call and a false hit costs a wrong answer, so the bar belongs well to the right.

1.4

Reviewed by opendroid · 2026-08-18

  • arXiv:2305.05176 — FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
  • arXiv:2309.06180 — Efficient Memory Management for Large Language Model Serving with PagedAttention