QPS
A metric measuring the number of requests per second an API endpoint can accept. Rate limiting is typically applied server-side per account or per key over a time window, independently for each.
Timeline (last 90 days)
The core metrics for evaluating vector indexes include recall (Recall@k), P99 latency, QPS (throughput), index build time and memory.
The fairness of a benchmark depends on whether a recall target is fixed (e.g. comparing latency at Recall@10=0.95 for all), otherwise simply comparing QPS numbers can easily be misleading.
The key variables that determine the actual performance of this architecture include actual QPS, the complexity of dynamic computation, and cache hit rate.
All Facts (3)
The core metrics for evaluating vector indexes include recall (Recall@k), P99 latency, QPS (throughput), index build time and memory.
50%UnverifiedThe fairness of a benchmark depends on whether a recall target is fixed (e.g. comparing latency at Recall@10=0.95 for all), otherwise simply comparing QPS numbers can easily be misleading.
50%UnverifiedThe key variables that determine the actual performance of this architecture include actual QPS, the complexity of dynamic computation, and cache hit rate.
50%