Has anyone tried to run tests (vitest) with a project that uses Workers AI? I'm getting: ```bash ork
Has 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
BWhat does hody jones mean?
SHi , lets say I don't use the ai models hosted by cloudfare and instead import it from somewhere else using workers ai python-sdk . Will the ai inference at edge still happen ?
SHas anyone experienced this type error issue for the new models? Im following the tutorial pretty much to a tee thats at https://github.com/craigsdennis/punderful-workflows/tree/main.
It seems i only have access to the old models in autocomplete. Im using the latest @cloudflare/workers-types: ^4.20241205.0.
Tsconfig.json is the same as the punderful tutorial linked above:
Is this an issue with the Workflows not having the right type definitions?
It seems i only have access to the old models in autocomplete. Im using the latest @cloudflare/workers-types: ^4.20241205.0.
Tsconfig.json is the same as the punderful tutorial linked above:
Is this an issue with the Workflows not having the right type definitions?
SIm able to run the workflow no problem, Im in a turbo repo so probably messing something up
SOh interesting, the new models dont even work with typescript in that example either. LOL
JYeah the Workers AI types are months out of date, but hopefully we'll see an update soon: https://x.com/_mchenco/status/1865865722913841282
@CherryJimbo @CloudflareDev its coming! figured out a more sustainable way to do it
12/8/24, 9:07 PM
Z( I’m new to clourflare AI. ) if the models I am interested in running are not listed is there a way to package/distribute weights for them? Thank you
Whttps://github.com/wuyangwang/my-chat-web/issues/1 The generated image is very abstract, there is a good way to solve?
AHas anyone solved this 
MWhat is the rate limit for AI Functions? That's not covered on the rate limits page
- or do Functions fall under text generation i.e. 300 reqs per minute? And is that requests as in HTTP requests (whether via the binding or manually)?
I?workers-ai-models Sadly not currently, see below.
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/
IYes to both.
IA function call will usually be 1 generation and then if you ask it to do more it'll be more generations
MThanks. To be clear, is it true to say that each call to
env.AI.run = 1 request? Or is it more nuanced and comes down to the number of generations, as you alude to?IIt depends. I'm not super familiar with the Workers AI API—is
env.AI.run just the standard generation mechanism or the Functions one?IIf it's the standard generation mechanism then yes, unless you're generating more than 1 generation with a single call it's usually 1:1
MThanks.
env.AI.run is for both standard generation and function calls - it's just that, for the latter, you a tools object to the params.
ZThank you. Is there a place where we can register interest in future models?
Ahas anyone figured out a way to create workflows using ai and deploy them onto worker for platforms?
RI don't think It's supported on wfp yet
RHow's everyone doing? How's AI?
Uis anyone able to get image2image working?
Ui have not been able to do it
Ui consistently get api error 3001
Uall the image-to-text models work fine, but if i pass an image to text-to-image i get error 3001
Uok after some research i figured out its a token issue
Uat strength 2 or something, it runs out of tokens very quickly
AIs there an easy way to tell the model size for embedding models? For things like Llama (I know not an embedding model) it’s easy, as it has the size in the name. The BGE Large for example, even Googling, I can’t find its size - it would be really helpful to include this on the model’s page on the CF docs, considering the pricing is based on the model size for embedding models.
RRegarding pricing, the docs also state that "Individual model pages will have the pricing listed on them", so I'm kinda waiting for that to happen. In any case large is ~335 million parameters, base ~109 million. You can get a rough idea by looking at the file size of the model (e.g. https://huggingface.co/BAAI/bge-large-en-v1.5/tree/main). Going by the "pricing structure", it looks like base and small would fall in the category <= 150 million parameters.
AAh cool thank you, I did peek at that page but couldn’t see it but I see it now, thank you!
Rstrength is the fraction of steps where the source image is used, where 1.0 means every step. So it doesn't make sense to set it higher than 1.0. I've noticed that it'll throw an error if you do, however.Ushould return a better error than just “internal server error” though
Bare custom workers ai model supported? i would like to host it myself
Cyou can't currently upload custom models if that's what you're asking
C?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/
JLooks like 
@cf/openai/whisper-large-v3-turbo is available now? 
IYay!
SIs there any way to see the actual pricing of Worker AI? I am using the @cf/baai/bge-large-en-v1.5 model for vector embedding, with each text having 100 input tokens. I ran it for 50000 texts, and based on that, pricing should have been $0.075, but in the worker AI usage dashboard, I see $0.45.
I need to run it for millions of texts and I am worried about getting the huge check at the end
I need to run it for millions of texts and I am worried about getting the huge check at the end
A
BI'm using messages API body, why it requires
prompt?
Sllama-3.3-70b-instruct-fp8-fast is taking 20 sec on avg, that's normal?
VIt's fast relative to CF workers running at edge not so much fast like groq is fast.
VYou could use AI gateway
VI think?