maybe we can have a wait=True for inserts? I mean, I can implement the "confirm that the vector was

maybe we can have a wait=True for inserts?
I mean, I can implement the "confirm that the vector was indexed" pooling on my side, but maybe having this in the api itself is more straightforward...?!

UUtkarsh Saxena Hi, I wanted to know about pricing of vectorization: There are some confusing th...

Utkarsh Saxena•2/11/25, 5:18 AM

Can anyone help me with this

MMarco Aleixo maybe we can have a wait=True for inserts? I mean, I can implement the "confirm ...

garvitg•2/11/25, 5:09 PM

The Vectorize Index Info route provides information on what mutations Vectorize has completed processing: https://developers.cloudflare.com/api/resources/vectorize/subresources/indexes/methods/info/. It includes the mutation id and the timestamp of the last mutation block that Vectorize has processed.

Cloudflare API | Vectorize › Indexes › Get Vectorize Index Info

Interact with Cloudflare's products and services via the Cloudflare API

Sshoo Facing the same issue - not sure what's causing it. query fails. Error: VECTOR_Q...

cloudkite•2/11/25, 6:01 PM

Bump for visibility, also getting this. Hopefully it’s being looked into

Victor•2/14/25, 12:17 AM

https://discord.com/channels/595317990191398933/1040420029080018945/1319662221957271605

So I make an index.
I delete the index.
I make an index with same id.
verify new index info
I try to upsert vector - fails saying index is deleted
I retry the exact same upsert api request (no change) - success

beingmudit [WePlayDOS]•2/14/25, 6:18 AM

Yes because the operations are async. When you get the response. it is just an ack not the actual operation.

Victor•2/15/25, 1:49 AM

I've had it happen even as far as an insert 24h after making the index again. And I get index info after creating it and verify it was created correctly

deo time•2/22/25, 12:31 AM

Hello, I've had a site that uses vectorize for a little over a year now, however just now requests to it have started failing with (error) Error: VECTOR_QUERY_ERROR (code = 4009): Bad Request: the index is disabled(error) Error: VECTOR_QUERY_ERROR (code = 4009): Bad Request: the index is disabled. I've also checked and it looks like my index isn't there anymore, does anyone know why this is happening?

deo time•2/22/25, 12:37 AM

I also get the error code vectorize.index.deletedvectorize.index.deleted when trying to get it via cli, so it looks like it was just forcefully deleted somehow?

ac•2/27/25, 7:48 PM

Hi, I am getting Error: Cloudflare LLM call failed with status code 403Error: Cloudflare LLM call failed with status code 403 trying to insert into a new Vectorize index on production. Works fine locally, and confirmed the bindings are there. It seems related to other auth issues people have posted about in here. Any idea what I'm missing?

grantpowell•3/3/25, 6:37 PM

I am unable to insert vectors into index

noad.eth•3/8/25, 12:39 PM

Hi. I just started using Vectorize this week. Really liking it so far. Nice and simple.

For inserting/upserting vectors using the REST API (or Typescript SDK), it would be nice if the request body could also accept an array of vector objects.

When using the TS package, if I set the body value to be the ndjson string, I was getting a "failed to parse" error. I found I had to wrap the ndjson in a Buffer.from()Buffer.from() to get it to work, but had to ignore a TS error since body is typed as a

string

string

Samko•3/17/25, 10:44 AM

Is vectorize still actively developed and improved https://developers.cloudflare.com/vectorize/platform/changelog/ seems bit outdated. I believe there was feature that would allow dynamic binding and creation of index from worker. Is this still planned or?

SSamko Is vectorize still actively developed and improved https://developers.cloudflare...

Matt Silverlock•3/18/25, 12:16 PM

Still worked on. Dynamic binding has some complexities - we need to solve for more than just Vectorize

Matt Silverlock•3/18/25, 12:17 PM

For many here: Workers AI now has a re-ranker model and a new embeddings models - https://developers.cloudflare.com/changelog/2025-03-17-new-workers-ai-models/

Cloudflare Docs

New models in Workers AI

Matt Silverlock•3/18/25, 12:17 PM

beingmudit [WePlayDOS]•3/21/25, 10:29 PM

Is vectorize down? I am getting Internal Server Errors. Is there a status page for those apis?

beingmudit [WePlayDOS]•3/21/25, 10:32 PM

{

"result": null,
"success": false,
"errors": [
{
"code": 50124,
"message": "vectorize.upstream_error - Internal Server Error"
}
],
"messages": []
}

Bbeingmudit [WePlayDOS]Is vectorize down? I am getting Internal Server Errors. Is there a status page f...

ggu•3/22/25, 2:41 AM

Yeah, we had some heightened error rates due to an upstream dependency error. See status here https://www.cloudflarestatus.com/incidents/v6c7l22vglw5

Increased HTTP Errors for Some Cloudflare Services

Gggu Yeah, we had some heightened error rates due to an upstream dependency error. Se...

Isaac McFadyen•3/22/25, 3:11 AM

Was this R2 by chance?

Isaac McFadyen•3/22/25, 3:22 AM

Cloudflare is investigating an increase in HTTP 5xx errors with R2

Ignore me

Gggu Yeah, we had some heightened error rates due to an upstream dependency error. Se...

MattIPv4•3/22/25, 3:39 AM

Why wasn't Vectorize in the impacted products list for that incident?

MattIPv4•3/22/25, 3:39 AM

Or rather I suppose, why isn't Vectorize on the status page at all unless I've missed it?

IIsaac McFadyen Was this R2 by chance?

ggu•3/22/25, 3:40 AM

Yes

MMattIPv4 Or rather I suppose, why isn't Vectorize on the status page at all unless I've m...

ggu•3/22/25, 3:40 AM

Hmm that’s odd. Will look into it

MattIPv4•3/22/25, 3:40 AM

Appreciate it, ty :MeowHeartCloudflare:

yevgen•3/24/25, 6:38 PM

I've asked internally to add Vectorize to the list of affected services

Nick•3/25/25, 9:19 PM

Hey everyone, I have a question about the pricing model for Vectorize, specifically regarding metadata filtering. I structure my data by using metadata to filter vectors into different collections within a single index. For instance, one index might hold 1 million vectors organized into 1,000 collections, and every query I run is filtered by metadata to target a specific collection.

Does that mean I’m billed based only on the vector dimensions of the filtered collection, or do I incur costs based on the entire index’s dimensions regardless of the metadata filter?

Thanks for any insights!

NNick Hey everyone, I have a question about the pricing model for Vectorize, specifica...

yevgen•3/26/25, 9:32 AM

you are billed based on the entire index's dimensions.

Yyevgen you are billed based on the entire index's dimensions.

lavisht22•3/31/25, 12:01 PM

Are there any suggestions to go around this?

I want to create an index with 1M vectors which will have around 10K namespaces and each query only needs one subset. If entire index's dimensions are used, we would end up with a huge bill.

Llavisht22 Are there any suggestions to go around this? I want to create an index with 1M ...

Matt Silverlock•3/31/25, 12:05 PM

If you store 1M vectors of 1536 dims and query it 1M times a month, it’s about ~$47 - https://developers.cloudflare.com/vectorize/platform/pricing/#usage-examples

Cloudflare Docs

Pricing · Cloudflare Vectorize docs

Vectorize bills are based on:

MMatt Silverlock If you store 1M vectors of 1536 dims and query it 1M times a month, it’s about ~...

lavisht22•3/31/25, 12:35 PM

I think I did my math wrong, let me check this again. Thanks!

lavisht22•4/2/25, 10:41 AM

I have an index with almost 1M vectors. I have also created a metadata index on one of the properties. When i query this index with a metadata filter, I am getting back results in 2-3 seconds, sometimes more. Is this kind of latency normal with Vectorize or am I doing something wrong?

lavisht22•4/2/25, 10:42 AM

I have the same vectors in postgres with pgvector and I was getting similar performance, wanted to try out vectorize to check if there are any performance gains.

Marius B.•4/2/25, 11:19 AM

Is cloudflare currently the most affordable provider for vector databases?

Llavisht22 I have an index with almost 1M vectors. I have also created a metadata index on ...

yevgen•4/4/25, 8:38 PM

this is for cold starts, it's get much better once you start querying data more actively (have more load, more customers). We do in-memory and CDN caching of vectors data for some period of time.

JJonathan Harel Hey team! Is there a way to delete vectors by namespace + metadata and not by ID...

yevgen•4/4/25, 8:38 PM

not at the moment. It's on the roadmap.

MMarius B.Is cloudflare currently the most affordable provider for vector databases?

yevgen•4/4/25, 8:38 PM

We hope so.

jedi•4/4/25, 9:29 PM

hi guys i'm curious about the pricing models. so the pricing model is based on stored and queried vector dimensions. so what if i use metadata filtering so i'm not querying against the whole vdb but rather a smaller set of data? what would the cost structure look like? is the queried vector dimensions is adjusted based on the queried space instead of the total space?

Neckville•4/7/25, 3:47 PM

is there the concept of semantic caching? What about caching for searches based on similarity

S.•4/9/25, 12:00 PM

Hey, is there any doc / link about using Cloudflare Vectorize with llamaindex ?

S.•4/9/25, 1:37 PM

AI AutoRag funnel led to error page

beingmudit [WePlayDOS]•4/9/25, 10:08 PM

Hi CF team, Has there been an issue with Vectorize lately? The indexing is taking more than 5 minutes to be able to query. I know it is an async process but this is a huge time. Can any one provide more details on this?

Bbeingmudit [WePlayDOS]Hi CF team, Has there been an issue with Vectorize lately? The indexing is takin...

yevgen•4/10/25, 9:59 AM

Hi @beingmudit we are seeing increased Vectorize usage since AutoRAG launch, we are scaling our infra for WAL processing to get the metrics back to normal.

yevgen•4/10/25, 10:26 AM

@beingmudit done, it should be under 30 seconds now. Thanks for reporting. Because it didn't cause any errors on our side, we haven't caught the delay in our monitoring.

beingmudit [WePlayDOS]•4/10/25, 11:12 AM

Thanks @yevgen for the resolving this. Yeah I didnt find any issues in the status page as well.

Harshilm•4/12/25, 9:27 PM

@yevgen Is there any way to resync error files in vector db?

Stephen•4/13/25, 7:28 PM

Hi, is there a way of accessing each vecor to add metadata tags to each vector? Used standard R2 ingest but did not add any meta-data and cannot seem to recover a vector based upon id. ID appears to be random value (hash?) I see that each chunk returns the same basic format:
Chunk 4
Cosine Sim.
0.6107
Relevancy
0.0017
Metadata
450db445-638b-4bb9-a0e8-16af21562e23/291385e0-f9c0-4126-96b4-6b1e0c1dfab1/1997-011.pdf
Chunk 1
Cosine Sim.
0.6169
Relevancy
0.0006
Metadata
450db445-638b-4bb9-a0e8-16af21562e23/291385e0-f9c0-4126-96b4-6b1e0c1dfab1/1997-008.pdf
Chunk
3
Cosine Sim.
0.6140
Relevancy
0.0019
Metadata
450db445-638b-4bb9-a0e8-16af21562e23/291385e0-f9c0-4126-96b4-6b1e0c1dfab1/1997-012.pdf

So the metadata appears to be the same apart from the file name and a chunk number. Is there a way of determining these values? I assume the first one is "processeduptoMutation ID" but not sure what the second value might be or perhaps the other way around. Need to understand how to recover this to be able to recover a specific set of vector values for a chunk.

maybe we can have a wait=True for inserts? I mean, I can implement the "confirm that the vector was

Similar Threads