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
- distance range: search for vectors within the distance range
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.
By default, pre-filtering is performed to filter prior to vector search. This can be useful to narrow down the search space of a very large dataset to reduce query latency. Post-filtering is also an option that performs the filter on the results returned by the vector search. You can use post-filtering as follows:
need to add order by distance by pass index fast_search