Gafaik the Resnet50 will create a 2048 dimensions per vector, but the vectorize seems has limitations of 1536 dimensions per vector, do you have any tips on reducing the dimensions?
SPlease do not ping community members for non-moderation reasons. Doing so will not solve your issue faster and will make people less likely to want to help you.
RBeen a while, but last time I checked the model had a limit of ~2800 tokens (input + output). Longer than that and you'd get a blank response. Most of the models give blank or truncated responses when reaching their limits, so that's the first thing I'd check.
BIs there a way to get the number of tokens consumed by each request, both for input and output token?
SIs there any zero-shot classification model available in Workers AI models, such as the one provided by Hugging Face (e.g., facebook/bart-large-mnli)?
AAny chance Claude Haiku or Sonnet will come to workers ai?
IWorkers AI models are hosted by Cloudflare (all are open-source models), they're not external providers like Claude or OpenAI, so no they won't be coming.
IYou can use AI Gateway to proxy requests to Anthropic's Claude, though.
ACluade licenses to Google, Amazon, and others. I was hoping Cloudflare would also strike a deal with them.
IWhile that might be possible, it would have to be a whole new product - Workers AI isn't designed for that. Plus, there's really not much point. The reason cloud providers license models like Claude is so that you can have unified billing if you already use that provider.
Ccan someone help me with @cf/black-forest-labs/flux-1-schnell
Cwhen I save the file it doesn't open
CI used
atob()am I supposed to do something else?
Coh wait there's an example
Cthe example doesn't work
Kyou have to convert from base64 to binary. in js I do
Buffer.from(base64Image, 'base64')oh cool. that's a lot better than the thing cloudflare's example did
Cthanks
CBuffer isn't in workers
Kmight have to do something here https://developers.cloudflare.com/workers/runtime-apis/nodejs/buffer/
Cloudflare Docs
The Buffer API in Node.js is one of the most commonly used Node.js APIs for manipulating binary data. Every Buffer instance extends from the standard Uint8Array 
class, but adds a range of unique capabilities such as built-in base64 and hex encoding/decoding, byte-order manipulation, and encoding-aware substring searching.
class, but adds a range of unique capabilities such as built-in base64 and hex encoding/decoding, byte-order manipulation, and encoding-aware substring searching.Cnah I'll just keep using
Uint8Array.from(binaryString, (m) => m.codePointAt(0));thanks tho
JI asked this in the wrangler chat, but am I the only one who has to re-auth/re-allow wrangler to access workers AI locally every hour or two?
CI don't have that issue
Coh wait locally?
CI didn't even know it worked locally. never used to
IIt now calls out to the remote Workers AI endpoint when developing locally, yeah.
JYeah it works, but it's irritating how I gave to re-auth it a few times a day
AWhy can't I use workers ai with auth and api gateway?
works if i do it without api gateway. with api gateway everytime i get an unathorised error. i have done it with just this header cf-aig-authorization and all the other headers on their own. I am doing open ai requests through my gateway its just workers ai. 0 examples in the dcos doing config.ai.run with an auth tokens. i just assumed i would add the auth to the extra header or something
works if i do it without api gateway. with api gateway everytime i get an unathorised error. i have done it with just this header cf-aig-authorization and all the other headers on their own. I am doing open ai requests through my gateway its just workers ai. 0 examples in the dcos doing config.ai.run with an auth tokens. i just assumed i would add the auth to the extra header or something
MWhisper v3 turbo is on cf workers ???
CNeed help with Cloudflare Vectorize + Workers AI embedding query. Getting 'invalid query vector, expected 768 dimensions, and got 0 dimensions' despite vector data being present. Here's my code:
Logs show embedding.data[0] contains 768 values but query fails. Tried multiple query formats. Any suggestions?
Logs show embedding.data[0] contains 768 values but query fails. Tried multiple query formats. Any suggestions?
PIs hosting of custom models something that is expected to be a feature relatively soon for ai workers?
I?workers-ai-models
SWorkers AI currently only supports popular open-source models provided by the Cloudflare team, as well as your own LoRAs that can be applied on top of the Cloudflare-provided models. You cannot currently upload your own models or use a model from HuggingFace. See the documentation for the list of Cloudflare-provided models: https://developers.cloudflare.com/workers-ai/models/
I^ TLDR: probably not, no
BI noticed my friend has a workers AI page which shows usage, but mine doesn't. My friend did find a bug in the usage values though. It just shows "Welcome to Workers AI" on https://dash.cloudflare.com/$accountId/ai/workers-ai
Is the detailed workers page a feature being AB tested?
Is the detailed workers page a feature being AB tested?
Ais the workers ai limit charged per worker
Aor is it global
Ain other words i have 10 workers
Ais the effective limit 3200 per minute
Avs 320 per minute across 10 workers
A320 per minute seemed pretty low
Afor text generation
Asorry it's actually 300
BHas anyone tried to run tests (vitest) with a project that uses Workers AI? I'm getting:
Ahody jones?
IIf you're only using beta models they won't show usage.
BI've been using non-beta models (identical code/commit to my friend, sitting next to them) but mine doesn't show usage. We've been using non-beta models the entire day