Cloudflare Developers•3y ago

Only 100 indexes of 200,000 vectors rn though, right? That's a mighty small user count for a startup

Only 100 indexes of 200,000 vectors rn though, right? That's a mighty small user count for a startup.

wesleyyue•10/26/23, 4:57 PM

Is there any bench mark on Vectorize? Something like this? https://supabase.com/blog/increase-performance-pgvector-hnsw

Supabase

pgvector v0.5.0: Faster semantic search with HNSW indexes

Increase performance in pgvector using HNSW indexes

wadefletchOP•10/26/23, 5:29 PM

@Matt Any flexibility on the 100 indexes limit? Is that something exceptions could be granted for within the beta? In what ballpark do you expect the final (paid) limit to land?

Wwadefletch @Matt Any flexibility on the 100 indexes limit? Is that something exceptions cou...

Matt Silverlock•10/26/23, 5:30 PM

We expect to land metadata filtering soon, which is going to be the better solution here. We will increase the index limit too but not immediately.

Wwadefletch @Matt Any flexibility on the 100 indexes limit? Is that something exceptions cou...

Matt Silverlock•10/26/23, 5:31 PM

(Do you have a need for more than 100 indexes right now or within the next few weeks, or is this forward looking?)

MMatt Silverlock (Do you have a need for more than 100 indexes _right now_ or within the next few...

wadefletchOP•10/26/23, 5:32 PM

Very forward looking, just spec'ing infra options.

MMatt Silverlock We expect to land metadata filtering soon, which is going to be the better solut...

wadefletchOP•10/26/23, 5:32 PM

Ok, great! Thanks!

Wwadefletch Very forward looking, just spec'ing infra options.

Matt Silverlock•10/26/23, 5:34 PM

Got it. Right now our focus is:

1. Metadata filtering
2. Increasing overall performance and per-index vector limits
3. User-facing analytics

Wwadefletch Only 100 indexes of 200,000 vectors rn though, right? That's a mighty small user...

charl.dev•10/26/23, 9:49 PM

Ment per tenant, not user

Wwadefletch Very forward looking, just spec'ing infra options.

charl.dev•10/26/23, 9:52 PM

Cf limits are mostly soft limits that can be increased if you ask nicely, so I wouldn’t let the limits deter you

charl.dev•10/27/23, 12:14 PM

when creating a vector index, im getting:

"message": "vectorize.index.invalid_name - Index name \"user_29w83sxmDNGwOuEthce5gg56FcC\""

"message": "vectorize.index.invalid_name - Index name \"user_29w83sxmDNGwOuEthce5gg56FcC\""

Its within the char limit, not sure what other restrictions there are?

charl.dev•10/27/23, 12:19 PM

also tried without the underscore

zegevlier•10/27/23, 12:20 PM

Perhaps it's too long?

zegevlier•10/27/23, 12:21 PM

From https://developers.cloudflare.com/vectorize/platform/limits/#limits

Maximum index name length: 63 bytes

zegevlier•10/27/23, 12:21 PM

This is only 32, so that's not it. hmm

zegevlier•10/27/23, 12:24 PM

Ah I found it, you aren't allowed to use capital letters in the name

charl.dev•10/27/23, 12:29 PM

ah, is that intentional or might change?

charl.dev•10/27/23, 12:33 PM

with a limit of 100ish indexes, chances of collision atm are not a worry if I make them all lowercase - but seems that capital letters should be allowed?

Ccharl.dev ah, is that intentional or might change?

Matt Silverlock•10/27/23, 12:43 PM

Might change. Again, keep in mind metadata filtering and (in the future) increased total index limits will both land.

MMatt Silverlock Might change. Again, keep in mind metadata filtering and (in the future) increas...

zegevlier•10/27/23, 12:45 PM

I was just making a PR to the docs to clarify this on the getting started pages. Should I still make it or hold off for now?

Zzegevlier I was just making a PR to the docs to clarify this on the getting started pages....

Matt Silverlock•10/27/23, 12:51 PM

I would still PR it

Zzegevlier I was just making a PR to the docs to clarify this on the getting started pages....

Matt Silverlock•10/27/23, 12:51 PM

(And thanks!)

charl.dev•10/27/23, 1:14 PM

and not sure if this is a thing, the delete index is only returning 204, no body. From the docs, is says response would be 200 with:

{
  "errors": [],
  "messages": [],
  "result": {},
  "success": true
}

{
  "errors": [],
  "messages": [],
  "result": {},
  "success": true
}

futuristick•10/28/23, 12:45 AM

Might be missing something but filtering by namespace doesn't seem to be working for me. I'm inserting vectors as ndjson via Wrangler, formatted as

{ id: "id", values: [], metadata: {}, namespace: "namespace" }

{ id: "id", values: [], metadata: {}, namespace: "namespace" }

then trying to query it via

INDEX.query(embeddings, { returnVectors: true, namespace: "namespace" });

INDEX.query(embeddings, { returnVectors: true, namespace: "namespace" });

but introducing namespace results in 0 matches

Ffuturistick Might be missing something but filtering by namespace doesn't seem to be working...

charl.dev•10/28/23, 6:14 AM

where did you see that namespace is an allowed prop?

Ccharl.dev where did you see that namespace is an allowed prop?

huw•10/28/23, 7:58 AM

It’s in the TypeScript types

huw•10/28/23, 7:58 AM

It’s not documented tho

Ffuturistick Might be missing something but filtering by namespace doesn't seem to be working...

huw•10/28/23, 1:47 PM

Oh yep, looks like

query

query

doesn’t return namespace info in the vectors

futuristick•10/28/23, 1:48 PM

Right, I knew it isn't returned, but I figured filtering by namespace at least worked

Ffuturistick Right, I knew it isn't returned, but I figured filtering by namespace at least w...

Old Man Maker•10/28/23, 6:16 PM

Not yet - Its very close by all accounts and hopefully will be released soon.

futuristick•10/28/23, 6:17 PM

Gotcha, thanks

Zzach @Matt 200K vectors per index is the real limitation. Index count limit not reall...

Matt Silverlock•10/30/23, 1:58 PM

What do you need per index / do you have 200k vectors today elsewhere, or is this forward-looking?

Zzach @futuristick Namespace filtering works for me with a traditional/in-code insert ...

futuristick•10/30/23, 2:04 PM

Interesting, thanks for the pointer!

Zzach Forward-looking bc I want to offer users the ability to index and query various ...

Matt Silverlock•10/30/23, 10:10 PM

Got it. Per the docs, 200k is a beta limitation and one that will grow over time. Metadata filtering will solve the other part for you and we expect that to land this month.

Zzach Metadata filtering comes *after* the vector search, whereas Namespace filtering ...

Matt Silverlock•10/30/23, 10:45 PM

Metadata is before.

Sam•10/31/23, 2:27 PM

Hey guys. Getting this error trying to upload my vectors using the cli:

✘ [ERROR] Received a malformed response from the API

POST /accounts/ab18c413a5487e485eb510e76de1e6de/vectorize/indexes/coaching-index/insert -> 200 OK

Any clues why?