All limits reset daily at 00:00 UTC https://developers.cloudflare.com/workers-ai/platform/pricing/
Cloudflare Docs
Workers AI will begin billing for usage on non-beta models after April 1, 2024.
0Yes. It was test after sharing account Id with Micheal
AHi, team, do u have plan to add more Text Embeddings models that support other languages, looks like the BAAI model have Multilingual languages support https://huggingface.co/BAAI/bge-base-en-v1.5
MThank you for this (and sorry for the delayed response). I'm still a little hazy, however, on how the call to my user-defined function influences (if at all) the AI response. In the CF docs there's an example of an embedded function to get the next N days' weather. It seems as though the AI response takes account of the API response, but it does not repeat it verbatim. Is there a way to have the user-defined function form the AI response, or am I still missing something? (To be clear, I want the user-defined function to control the response, rather than AI deriving its own conversational response.)
RRight now your option is pretty much to use "traditional" function calling. When you call runWithTools it's the LLM that generates the response, i.e. you can't make it return the result of your user-defined function(s).
AHow to use the Model Search API with task query param? I tried
?task=c329a1f9-323d-4e91-b2aa-582dd4188d34 and ?task=Text%20Generation, both of them returned error.
SAny plans to support the new llama 3.1?
DThe Cloudflare Blog
Cloudflare is excited to be a launch partner with Meta to introduce Workers AI support for Llama 3.1.
SOh that made my day
SThanks
Kis the rest api reference accurate, cause it says that llama 3.1 accepts a prompt of up to 131k characters but when calling the api with a prompt of over 30k ish characters it responds with an empty message
K
K
RThere's also a token limit that depends on which model you use. Looks like llama 3.1 on Cloudflare currently has a limit of ~6000 tokens.
Kyea but i cant find any info on the token limits
RYeah I know.. With a few exceptions, you won't be able to find it. Ideally, one should be able to get info about limits, token counts, default prompt, supported params/features etc etc via methods and API calls. In any case, here's a list of tokens limits that covers most of the models, based on my own tests: https://gist.github.com/Raylight-PWL/e92b298850625c80efa6ca4ddd206662
Kow that's great
Kthank you very much :firSweet:
RFound a somewhat weird bug: models that start with
@hf/thebloke won't generate a response if max_tokens is set to 597 or higher. (Fails with "3025: Unknown internal error".)
DHey Everyone!
We’re super excited to launch this awesome demo playground where you can use audio, video, images, and text to create multimodal AI applications. We ask that you take it for a spin, try it out and post what you build. There are some preloaded examples to get you started but feel free to build whatever you like! We’ll retweet your posts on X. Try it here https://multi-modal.ai.cloudflare.com/
We’re super excited to launch this awesome demo playground where you can use audio, video, images, and text to create multimodal AI applications. We ask that you take it for a spin, try it out and post what you build. There are some preloaded examples to get you started but feel free to build whatever you like! We’ll retweet your posts on X. Try it here https://multi-modal.ai.cloudflare.com/
DHere's me using it to turn an image from Cloudflare's website to HTML code
UUhm, did the
runWithTools syntax change?UWhen I call
runWithTools I get Error in runWithTools: Error in runAndProcessToolCall: Bad input: must have required property 'prompt', must have required property 'name', must have required property 'description', must have required property 'parameters', must have required property 'type', must have required property 'properties', must match exactly one schema in oneOf, must match exactly one schema in oneOf,Ui cant seem to find where the "Bad input" part comes from, is it an upstream issue rather than an ai-utils issue?
EHello everyone
! Please tell me if it is possible to understand how many Neurons were used in each request to the model?
! Please tell me if it is possible to understand how many Neurons were used in each request to the model?
USorry for the ping, @Dhravya Shah, but you're the only know I can think of who can help with this xD
Usame code snippet as last time produces this error, no changes were made
UQwen 
UStill trying to figure out functions with qwen :ye:
U@cf/qwen/qwen1.5-14b-chat-awq
UMy immediate guess is the upstream api changed and ai-utils is no longer sending the right data
Ubecause the only parts of the error that I could find in ai-utils was
Error in runWithTools: Error in runAndProcessToolCall: , making me think that maybe the "Bad input" part was a response from the apiUis it maybe the tool parsing?
Ui dont see where the "prompt" property would come in as I don't see that documented anywhere, but everything else is properties of a tool
KHi all, anyway to speed up workers ai through rest api? responses are taking up to 30s, while I have a local llama3.1 running on a rtx3080 and it only takes like 6s?
OWhat's the pricing for neurons on text to image generation?
RThese error messages can be quite cryptic. Omitting the property "type" inside a single parameter of a single tool would produce the same error, for example. In your example with
parameters: {} I got past the error by changing it to parameters: { type: "object", properties: {} }.UInteresting.
UThat is very cryptic indeed
UI feel like this is definitely an issue with upstream
AI see that four of the text generation models support LoRA adapters. Is LoRA support for text-to-image models currently in the works?
Hhey this side mrinal I have a prior project on cloudflare using workers-ai, but when started with another project using ai it showed me the there is likely additional logging output above
Hany soution for that ?
RAnyone know of a full (working) example project with supporting files for an AI worker utilizing OpenAI tool usage? Not just a snippet that assumes everything else is gtg. So far my project is pretty capable of generating frustration and 500 errors.
KAll our text-to-image models are currently in beta, which means they are free to use until they graduate from beta
https://developers.cloudflare.com/workers-ai/models/#text-to-image
https://developers.cloudflare.com/workers-ai/models/#text-to-image
Kis there a specific model you are interested in using LoRAs with?
