Raul Carlomagno

> @raulcarlomagno, if you could please request that feature on Airlfow's Github, we can handle that together! Done! @kacperlukawski https://github.com/apache/airflow/issues/25901

is this feature planned for 1.0 release?

> **Is your feature request related to a problem? Please describe.** In some scenarios the client may have an array of vectors / records ids and not the vectors themselves....

is there any plan to add support for braycurtis and canberra distances? thanks

up 👍

this could be great feature for custom sharding

the use case is i have much data (60 million records of more than 300 dimensions, unordered, not previously sharded) and i can't split them before, i read them in...

hi guys @generall @e-ivkov do you know why this could be happening? and if there is a way to fix it? maybe an airflow expert could light us thank you

https://github.com/erikbern/ann-benchmarks/pull/318

thank you for answering @generall the main reason would be payload filtering, as you said, json gets "complicated" for advanced filtering use cases when working on jupyter notebooks, analyzing, researching,...