Cloudflare Developers

CD

Cloudflare Developers

Welcome to the official Cloudflare Developers server. Here you can ask for help and stay updated with the latest news

Join

there is something bad going on with

there is something bad going on with vectorize indexes, I tried three times to create a text embeddings index, I defined them with metric cosine and 1536 dimensions. It appears that after inserting a certain amout of vectors my index breaks and my queries starting returning absolutely nonsense "scores" - for example right now my queries to this cosine index are returning scores like 28.955 or something like that (and that is breaking search results)

FYI, submitted API site feedback, https

FYI, submitted API site feedback, https://developers.cloudflare.com/api/operations/vectorize-list-metadata-indexes should be GET not POST; also fails in ⛅️ wrangler 3.71.0 when running $ wrangler vectorize list-metadata-index <index-name>

Question about metadata indexing

Question about metadata indexing behavior: does it apply to existing vectors or only to those created after the metadata index is created? otherwise, does it backfill the index async?

do we need to fill this form to test V2

do we need to fill this form to test V2 or need to subscribe a paid plan?

Can we expect a visualisation window for

Can we expect a visualisation window for Cloudflare Vectorize to manage or monitor our embedding data? Like what we can use in D1 Database

Ui not loading

vectorize ui not loading :pain:

Listing all vectors in an index

Hi! I don't suppose there is a way to get all vectors stored in a vectorize database without knowing the vector IDs, right?

Are you also increasing the number of

Are you also increasing the number of vectors in an index or just the number of indexes? I am working on a use case where we need something close to 20-40MM vectors. We could store those all over multiple indexes, but a single index would be much preferred. Or do you perhaps mean the number of vectors per index is increased to 2MM and the number of indexes stays the same?...

Is there a rough ETA on being able to

Is there a rough ETA on being able to run vectorize locally? For context: I have a worker using a lot of cf services and it seems I have to use the api for vectorize as the —remote flag points all services to remote dev when really my goal is to run as many services locally as possible, then use remote for the unsupported ones. Is there a better way to handle this?...

Metadata filtering · Vectorize

I just started using Vectorize, and the query result shape is different than what's in the @cloudflare/[email protected]: ```{ "count": 1, "matches": [ { "vectorId": "145",...

Can you provide more info about the

Can you provide more info about the response you're getting? If it's a widespread issue we might be able to escalate here.

I suddenly realized that the

I suddenly realized that the functionality of my product is similar to AWS Bedrock's knowledge base management , and I don't have confidence in being able to compete with AWS. I want to know if it's possible for me to join Cloudflare and do the same thing?:blobhaj:

Vector insertion error

Hey guys, I'm try to insert a vector via REST API, but I'm getting ```json { "result": null,...

I will also +đź’Ż this https://discord.com

I will also +đź’Ż this https://discord.com/channels/595317990191398933/1152193114522525726/1195671391228411965 As being able to do > >= < <= and boolean true falseis the only thing stopping me from moving forward with Vectorize ... It would still be super convenient to also have an API:...

I'm using langchain and vectorize with

I'm using langchain and vectorize with ada embedding from openAI. When I do a similarity search I'm getting repeated entries returned. What am I missing?

For the moment, you're going to find (

For the moment, you're going to find (which you may have already spotted) that you're going to dodge one bullet, only to be hit by the next in terms of limits. In some ways, this has actually been a good process, because it made me really think about the data in a much deeper way than otherwise - in order to get some scale out of it, I've got a rotator system in, which binds N indexes to a worker, and I have N workers doing that. With 100 indexes and 200K vectors/index limits, that's about the only way to really push it at the moment - I would suspect/hope we are due for an update soon including limit increases....

I am getting "error code: 502" errors

I am getting "error code: 502" errors for the last few minutes on two different vectorize indices

`https://api.cloudflare.com/client/v4/

https://api.cloudflare.com/client/v4/accounts/920b1a6e159cf77dab28969103a4765b/vectorize/indexes/customers-650a02c2a5be79517a7f79e2/query

Launched: Metadata filtering

Hi folks, it's a fun day because metadata filtering is now available with Vectorize! Check out the docs here, https://developers.cloudflare.com/vectorize/learning/metadata-filtering/. Happy building and please share any feedback or issues!