The Vectorize limits aren't artificial but are a result of the internal architecture/technology back

The Vectorize limits aren't artificial but are a result of the internal architecture/technology backing Vectorize. I expect they'll be raised over time (and in fact they were recently) but not lifted altogether.

Isaac McFadyenOP•10/11/24, 2:54 PM

And nothing has zero limits: Pinecone docs say they have them too, it just scales by plan (but there's an upper bound): https://docs.pinecone.io/reference/quotas-and-limits

Pinecone Docs

Quotas and limits - Pinecone Docs

Search through billions of items for similar matches to any object, in milliseconds. It's the next generation of search, an API call away.

IIsaac McFadyen And nothing has *zero* limits: Pinecone docs say they have them too, it just sca...

Bryan•10/11/24, 3:59 PM

Oh I missed this

IIsaac McFadyen The Vectorize limits aren't artificial but are a result of the internal architec...

Bryan•10/11/24, 4:03 PM

I know there must be some limits to protect the platform. But I think, at least, should the total records of the specific index be not limited?

I know I can separate the index manually, but I really hope the platform can auto scale and I don't need to care how many records I will insert.

BBryan I know there must be some limits to protect the platform. But I think, at least,...

Isaac McFadyenOP•10/11/24, 4:10 PM

It's not so much to "protect the platform" but more that the actual underlying storage engine has a limit.

zhawtof•10/13/24, 5:40 PM

Feedback:

One of our biggest fears for Vectorize is that all metadata filters have to be created at index creation.

Wondering if there are plans to allow additional metadata filters to be created after index creation.

Thanks

HHexMan I deleted my Vectorize DB and tried to recreate it with the same name but I get ...

Isaac McFadyenOP•10/13/24, 6:14 PM

Vectorize index names are current single-use even if deleted.

Isaac McFadyenOP•10/13/24, 6:15 PM

https://canary.discord.com/channels/595317990191398933/1152193114522525726/1288526039487610953

Mitya•10/13/24, 6:39 PM

Hi all, I'm new to Vectorize and have been working through this tutorial (request to documentation author: we could really do with a summary of what the code in step 6 does, after the code.)

We previously vectorised a note ("pepparoni is the best pizza topping"), and saved it to the Vectorize DB. I get all that. What I'm less clear on is step 6. I send in a question, presumably something like "what's the best pizza topping?", and then we retrieve the vectors relating to the note closest to that question.

So my question here is: what powers CF's ability to associate that question with that note? Is it because both contain the word pizza? If instead I'd asked "what is the best topping for a common Italian dish?", would it have still returned the vector (my note)?

Mitya•10/13/24, 6:42 PM

Right, so it would make that link even though I myself have only given it one note and one question? (i.e. this suggests preexisting knowledge)

Isaac McFadyenOP•10/13/24, 6:43 PM

As for if you have more than 1 vector though, yes, the model that generates the vectors understands association between topics.

Isaac McFadyenOP•10/13/24, 6:43 PM

If you use a proper embedding model it also understands actual text, not just words - i.e. it would understand your second case there.

Mitya•10/13/24, 6:44 PM

@cf/baai/bge-base-en-v1.5

@cf/baai/bge-base-en-v1.5

a proper embedding model?

Isaac McFadyenOP•10/13/24, 6:44 PM

Vectorize itself is just a DB that stores the vectors. You could throw any vector in there, not just word embeddings - I've used it for facial recognition embeddings, for example.

Isaac McFadyenOP•10/13/24, 6:44 PM

Yes.

Mitya•10/13/24, 6:45 PM

OK great. So it's not like, with just one vector in the DB, it would return that vector whatever my question was?

MMitya OK great. So it's not like, with just one vector in the DB, it would return that...

Isaac McFadyenOP•10/13/24, 6:45 PM

With one vector it would, yeah - that's what Leo was saying. You request the "top <n>" vectors, so it'll always return that 1 vector since you can't request "top 0"

Mitya•10/13/24, 6:45 PM

Ah, gotcha. So this becomes useful only once you've pumped it full of a lot of stuff?

MMitya Ah, gotcha. So this becomes useful only once you've pumped it full of a lot of s...

Isaac McFadyenOP•10/13/24, 6:46 PM

Depends on your use-case, but it will also return a distance.

Mitya•10/13/24, 6:46 PM

Otherwise my users asking "what's the capital of Mongolia" are going to be told about pizza

Isaac McFadyenOP•10/13/24, 6:46 PM

So if you have 1 vector about pizza, and the user asks about Mongolia, and the distance is huge you can return a preset "sorry, I don't know" response.

Isaac McFadyenOP•10/13/24, 6:46 PM

Whereas if the distance is small, the question is likely about pizza.

Mitya•10/13/24, 6:46 PM

OK! That makes sense. I don't think the tut discusses distance

Isaac McFadyenOP•10/13/24, 6:47 PM

Ah OK, yeah - I'm pretty sure it returns distances (or it did last I used it)

PRM•10/13/24, 6:47 PM

someone help me please

PRM•10/13/24, 6:48 PM

#cloudflare-ai

Original message was deleted

Mitya•10/13/24, 6:49 PM

Similarity = distance? The tut (step 6) seems to assume that if it retrieved a vector that it's fine to use with the LLM. No checks on distance/similarity, hence my question.

Mitya•10/13/24, 6:50 PM

Ah that's true. So distance is more important if there's no LLM in play i.e. you just want to return the note, I guess?

Mitya•10/13/24, 6:51 PM

Great, thanks everyone.

Isaac McFadyenOP•10/14/24, 4:05 AM

Also

distance = 1 - similarity

distance = 1 - similarity

similarity of 1 = perfect match
similarity of 0 = absolutely no match
distance of 0 = perfect match
distance of 1 = absolutely no match

Isaac McFadyenOP•10/14/24, 4:05 AM

(sorry for ping)

HHexMan I deleted my Vectorize DB and tried to recreate it with the same name but I get ...

yevgen•10/14/24, 10:23 AM

that should be addressed in the coming weeks.

Zzhawtof Feedback: One of our biggest fears for Vectorize is that all metadata filters h...

yevgen•10/14/24, 10:25 AM

It's possible to create metadata filters after index creation, though metadata search will not apply to already existing data.

Kkingmesal I'm very eager to move off of pinecone, purely from a simplicity perspective. ...

yevgen•10/14/24, 10:26 AM

re #2

an actual view in the dashboard would be a big help

an actual view in the dashboard would be a big help

Index analytics is available in dash

HHexMan Is there any way to add more than 1 namespace to a vector that I am inserting? ...

yevgen•10/14/24, 10:31 AM

You could use https://developers.cloudflare.com/vectorize/best-practices/insert-vectors/#metadata to add multiple fields describing vectors and index each of the metadata fields separately to support filtering.

Cloudflare Docs

Insert vectors | Vectorize

Vectorize indexes allow you to insert vectors at any point: Vectorize will optimize the index behind the scenes to ensure that vector search remains efficient, even as new vectors are added or existing vectors updated.

Kkingmesal I'm very eager to move off of pinecone, purely from a simplicity perspective. ...

yevgen•10/14/24, 10:33 AM

Metadata filtering has to support <, <=, >=, > ... Even a filter for in list or not in list.

Could you please list the order of metadata filtering operations you need the most to get started?

IIsaac McFadyen And nothing has *zero* limits: Pinecone docs say they have them too, it just sca...

yevgen•10/14/24, 10:42 AM

That is so true regarding nothing has zero limits. We are happy to work with customers to increase most of the limits once they are close to hit them.

Yyevgen re #2 `an actual view in the dashboard would be a big help` Index analytics is a...

kingmesal•10/14/24, 1:38 PM

Fair point. Those have been there. I meant a way to view / query something from the dashboard, similar to KV, or D1. An abiltity to perform a sanity check. e.g. In pinecone I had a bug once where I was removing a bunch of vectors before inserting a batch up new records and I had a bug, it died before inserting the new records. In their dashboard I had the ability to see some basic in formation to know that the data was gone.

Yyevgen > Metadata filtering has to support <, <=, >=, > ... Even a filter for in list o...

kingmesal•10/14/24, 1:46 PM

Sure, here are a couple of the examples, in priority order.

I have a few different use cases for putting dates (number format, seconds of ms is normal) on the vectors as a way to only bring back candidates after (>=) X and before (<) Y. Basically, Temporal limitations.
I have a list of arbitrary attributes, call it categorical information. Filter vectors where X is in that list. Or filter vectors where X is not in that list.

Jerome•10/17/24, 9:13 AM

Hi there! Now that V2 has GA'd, we will disable the creation of V1 indexes during this quarter. When this change will be effective, existing V1 indexes will be unaffected and continue operating as normal.

JJerome Hi there! Now that V2 has GA'd, we will disable the **creation** of V1 indexes d...

Isaac McFadyenOP•10/17/24, 2:41 PM

Great to hear! Once it happens (or perhaps a bit ahead) can it be added to https://developers.cloudflare.com/vectorize/platform/changelog/ as well?

Keebs•10/18/24, 12:08 PM

anyone try to create the embedding to query mongodb vendor search?

Yyevgen It's possible to create metadata filters after index creation, though metadata s...

EndiM•10/19/24, 6:26 AM

Hi. Would it apply if i were to upsert on that existing data? So if i create a new metadata index, and upsert the data, can that metadata be used as a filter? Since it overrides, im guessing yes, but i need to make sure!

EndiM•10/19/24, 6:30 AM

Also, one other question. On the filter operation there is only eq and ne. Is there a way to use contains logic? Ex: you search for an address, but on the results its not in the 20 topk. If i were to have a containy on the adress metadata tho, i would force my vector search to isolate my responses on this search option.

Daniel•10/19/24, 5:38 PM

Hi all! I have a beginner question. I am trying to use Vectorize with my NextJS Cloudflare Pages website. In this tutorial https://developers.cloudflare.com/workers-ai/tutorials/build-a-retrieval-augmented-generation-ai/ they say to use

npx wrangler dev --remote

npx wrangler dev --remote

to run locally and iterate.

When I run that, I see:

✘ [ERROR] It looks like you've run a Workers-specific command in a Pages project.

  For Pages, please run `wrangler pages dev` instead.

✘ [ERROR] It looks like you've run a Workers-specific command in a Pages project.

  For Pages, please run `wrangler pages dev` instead.

But when I do that, I see:

❯ npx wrangler pages dev --remote


✘ [ERROR] Unknown argument: remote


wrangler pages dev [directory] [-- command..]

Develop your full-stack Pages application locally

❯ npx wrangler pages dev --remote


✘ [ERROR] Unknown argument: remote


wrangler pages dev [directory] [-- command..]

Develop your full-stack Pages application locally

I need to use

--remote

--remote

because of:

▲ [WARNING] Vectorize bindings are not currently supported in local mode. Please use --remote if you are working with them.

▲ [WARNING] Vectorize bindings are not currently supported in local mode. Please use --remote if you are working with them.

And without that, I see:

✘ [ERROR] Error in GET function: Error: VECTOR_INDEX binding is not available

✘ [ERROR] Error in GET function: Error: VECTOR_INDEX binding is not available

The AI binding and KV binding are working fine, no issues there, but I can't seem to get the Vectorize binding to show up at all. Maybe I'm making an obvious mistake -- I'm somewhat new to Cloudflare. Any help appreciated, thank you!

EEndiM Hi. Would it apply if i were to upsert on that existing data? So if i create a n...

yevgen•10/21/24, 1:31 PM

yes, it will apply, we updated dev docs to reflect that https://developers.cloudflare.com/vectorize/reference/metadata-filtering/#metadata-indexes

Cloudflare Docs

Metadata filtering | Vectorize

In addition to providing an input vector to your query, you can also filter by vector metadata associated with every vector. Query results will only include vectors that match the filter criteria, meaning that filter is applied first, and the topK results are taken from the filtered set.

EEndiM Also, one other question. On the filter operation there is only eq and ne. Is th...

yevgen•10/21/24, 1:36 PM

there is no support for contains. We are planning add support for the following operations:

greater than
- greater than or equal
- less than
- less than or equal
- in s specified array
- not in a specified array

Rahul gangotri•10/21/24, 3:27 PM

is this approach is good of create a unique NS for each user i have and keep their vectors in that namespace?
and multiple indexes for set of users

why is it onnly limited to 100 indexes per account, can we request to increase this?

Rahul gangotri•10/21/24, 3:27 PM

the product i am planning is going to store a lot of vectors

The Vectorize limits aren't artificial but are a result of the internal architecture/technology back

Similar Threads

Similar Threads

Similar Threads