diff --git a/apps/docs/pages/guides/ai/choosing-instance-type.mdx b/apps/docs/pages/guides/ai/choosing-instance-type.mdx index c4074ecc693..674c14e45dc 100644 --- a/apps/docs/pages/guides/ai/choosing-instance-type.mdx +++ b/apps/docs/pages/guides/ai/choosing-instance-type.mdx @@ -70,9 +70,9 @@ Each test is run for at least 30-40 minutes and includes a series of experiments As a general recommendation, we suggest using a concurrency level of 5 and more for most workloads and 30 and more for high-load workloads. -## Work in progress +## Future benchmarks -This page is a work in progress. We'll add more information about benchmarking with datasets of different vector dimensions and `lists` or `probes` values. Stay tuned for more information about how it may affect the performance and precision of your queries. +We'll continue to add more benchmarks on datasets consisting of different vector dimensions, number of `lists` in the index, and number of `probes` in the index. Stay tuned for more information about how it may affect the performance and precision of your queries. export const Page = ({ children }) =>