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

Thanks for correcting the understanding.

Thanks for correcting the understanding. Unfortunately, this also doesnot solve my AIM (= "Isolated private Vectorize DB "per User"), as i shall be hitting the limit "Vectorize Indexes per account 50,000 (Workers Paid)" ...

I had errors had to switch to the api

I had errors had to switch to the api

I can't just search by criteria, can I?

I can't just search by criteria, can I? For example, searching for all data with EId=14 in Metedata

The worker has a serious bug. I tested

The worker has a serious bug. I tested the output logs and found no issues with the data. However, the accuracy was lost after uploading.

I hope to increase the ability to batch

I hope to increase the ability to batch query the Id list in the vector, because sometimes my database data doesn't seem to correspond here. I deleted data from my database, but there is still data here.

I am getting 500 when I try and insert a

I am getting 500 when I try and insert a new vector record: Error: VECTOR_INSERT_ERROR: Status + 500

How can search directly filter scores?

How can search directly filter scores? Do I have to search and filter by myself?

What techniques should I use to cache

What techniques should I use to cache the data read from the vector using a worker? What about KV?

After I store the image, I immediately

After I store the image, I immediately retrieve the vector through the ID. However, he may not be able to retrieve it and may experience a delay of 2-3 seconds.

I want to use queries extensively now,

I want to use queries extensively now, but who knows if workers really don't limit frequency like HTTP interfaces do?

Hey CF Team, is something off with

Hey CF Team, is something off with vectorize indexing latencies? I am continously getting vectors not found via getByIds. Can anyone update the status?

Is there a way to use CF's AI to extract

Is there a way to use CF's AI to extract image embeddings?

```

vectorize.index.invalid_config - Dimensions must
be in range: [32, 1536] [code: 3003]
vectorize.index.invalid_config - Dimensions must
be in range: [32, 1536] [code: 3003]
...

I'm getting the following error locally

I'm getting the following error locally
✘ [ERROR] Uncaught (in promise) TypeError: Cannot read properties of undefined (reading 'insert')
env.VECTORIZE.insert(vectors)
env.VECTORIZE.insert(vectors)
...

Hi, why can't we use BGE-M3 embedding

Hi, why can't we use BGE-M3 embedding model (@cf/baai/bge-m3) to create vector index? Only these model are available to choose from: [ "@cf/baai/bge-small-en-v1.5", "@cf/baai/bge-base-en-v1.5", "@cf/baai/bge-large-en-v1.5", "openai/text-embedding-ada-002", "cohere/embed-multilingual-v2.0" ]...

Anyone have any repos/guides/videos of

Anyone have any repos/guides/videos of RAG pipelines being built fully on Clouldflare stack? Looking for some inspo

**Quick question: **For Vectorize

Quick question: For Vectorize billing calculation, is the total count of vectors is used? Or does namespace and metadata filtering reduced the number of billable Queried Vector Dimensions for that request? I have multiple tenants with different sets of vector, so looking for an efficient way to manage these. Creating one index per tenant would work, but it seems to complicate the bindings a bit. https://developers.cloudflare.com/vectorize/platform/pricing/...

AutoRAG today doesn’t support metadata

AutoRAG today doesn’t support metadata filtering — but can I just append metadata anyway and manually query the database with these outside of the AutoRAG endpoint?

Hi Team, Getting these errors very often

Hi Team, Getting these errors very often for some time. Vectorize API error: upstream request timeout Can anyone verify?...