Work with data
Vector Search
Work with data
Vector Search
We support lightning fast vector search on massive scale data. Following performance data shows search latency from a 1M dataset with warmed up cache.
| Percentile | Latency |
|---|---|
| P50 | 25ms |
| P90 | 26ms |
| P99 | 35ms |
| Max | 49ms |
Other than latency, users can also tune the following parameters for better search quality.
- nprobes: the number of partitions to search (probe)
- refine factor: a multiplier to control how many additional rows are taken during the refine step
Metadata filtering combined with the vector search is also supported, with as low as 65ms query latency on a 15M dataset. Our benchmark tests have more details.