Any plans to support arrays in metadata filtering ?

Any plans to support arrays in metadata filtering ?
11 Replies
hannojg
hannojg•6mo ago
Hey, quick question: its expected that on the web dashboard you don't see any of the vector indexes you've created (while in wrangler you do) ? ah that has already been answered here https://discord.com/channels/595317990191398933/1279371665859674132/1280103851298394145 thanks! Is there a limit to how many vector indexes we can create? Edit: found the limits docs, all good
yevgen
yevgen•6mo ago
@maro Vectorize is ready for production use, we are planning to transition out of beta soon.
hannojg
hannojg•6mo ago
Cool! Are there any early details on how the limits will increase? 😊
ac
ac•6mo ago
Is there any way to upgrade a v1 Vectorize index to v2, or do I need to create a completely new one?
Unknown User
Unknown User•6mo ago
Message Not Public
Sign In & Join Server To View
Isaac McFadyen
Isaac McFadyen•6mo ago
TIL that you can link a slash command in a message 😄
yevgen
yevgen•6mo ago
So far we haven't observed anyone using Vectorize to encounter our current limits, what exactly you have in mind?
Unknown User
Unknown User•6mo ago
Message Not Public
Sign In & Join Server To View
hannojg
hannojg•6mo ago
In our use case we don’t have a lot of data belonging to one category, but a lot of smaller data belonging to many segments. So I am wondering how I can segment the vectors. The options I see are: - creating an index per segment - using namespaces in the same index - metadata filtering (less preferred) Both indexes and namespaces have quite a tight limit for our use case Kind of like this - if we already have 20.000 customers, and each customer has ~15 projects for which I’d need separate segments, it’s hard to do that with the current limits
yevgen
yevgen•6mo ago
I think metadata filtering is the best way forward. If you prefer using namespace for whaterever reason (nothing special other then we index it by default) we can lift # of namespaces limit for your account. Creating an index per segment could be an option as long as your index size will be at least 50k vectors, otherwise one index for all data is probably a better match. yes, Q1 2025 we plan to ship support for Vectorize dynamic bindings.
cosbgn
cosbgn•6mo ago
Can someone give me a brief guide/bullet points on how to use vectorize for a saas? - Should I create a namespace per user and query that namespace? - Should I just add them all in one namespace and query for metatags? What's the best proactice? 1000 namespaces for now it would be enough to have one per user, but that can eventually be increased, right? Also, is there any restriction on saving the original text in the metadata? It would save me an extra call to D1 10KiB of metadata is enough to store most text

Did you find this page helpful?