Performance
Choosing your embedding dimension
Memory cost per vector, how dimension affects recall, quantization and truncation: how to decide before indexing a large corpus.
Index latency, throughput and memory footprint
Measuring and cutting tail latency, sizing memory, and balancing recall against speed.
Memory cost per vector, how dimension affects recall, quantization and truncation: how to decide before indexing a large corpus.
Why the tail degrades before the median: efSearch, metadata filtering, reindexing, and how memory pressure shows up in high percentiles.