can we use pinecone or upstash vector db in cf workers??
can we use pinecone or upstash vector db in cf workers??
MGetting an error while connecting : const pinecone = new Pinecone({ apiKey: '' });
Ieval or new Function cannot be used in Workers for security reasons. Based on the error message I assume it's trying to do some sort of schema validation which often uses new Function.IIf you have control over it then you can switch to a schema library that doesn't use new Function but if it's part of the pinecode library then that on't work.
IYou might be able to manually connect to Pinecone over HTTP if they have an HTTP API, or (more work) over TCP if needed.
Cencountered a similar issue. From my reading of the documentation, it seems that the only required input parameter is audio. However, I'm also interested in utilizing other parameters such as prompt, which are crucial for standardizing transcription format and providing hot words. Can anyone guide me on how to use these additional parameters with Whisper? Additionally, I'm looking for an OpenAI-compatible whisper endpoint, so I can migrate OpenAI services to Cloudflare. Any help would be greatly appreciated!
FI am working using '@hf/meta-llama/meta-llama-3-8b-instruct' in stream mode. the JSON answer has the below structure : data: {"response":" to","p":"abcdef"}
data: {"response":"Once","p":"abcdef"} . I not sure what's means the "p" parameter . any comments
data: {"response":"Once","p":"abcdef"} . I not sure what's means the "p" parameter . any comments
FFor example in this case "p" has a single letter data: {"response":" this","p":"a"}
CThe Cloudflare Blog
The Workers AI and AI Gateway team recently collaborated closely with security researchers at Ben Gurion University regarding a report submitted through our Public Bug Bounty program. Through this process, we discovered and fully patched a vulnerability affecting all LLM providers. Here’s the story
Cit's a defense against that
p is just random data
J@noman did you figure out why this is happening, I"m getting the same thing today with no reason as to why it might be happening?
POST http://workers-binding.ai/run?version=3 - Canceled @ 24/05/2024, 06:28:16
Sany news on the whisper webm format support? seems be reported several times on discord , quite importnat for web support
I@scotto have you tried this? I know you're targeting mobile and I'm not sure this will work on mobile, but it's definitely worth a shot since it might be a while still until WebM support is added natively to Workers AI.
LIs there a way to use the AI gateway URL with AI workers in an OpenAI compatible way? It seems like workers AI has a different response and thus I can't just swap out my openai routes with CF AI when using AI gateway :/
there is this https://developers.cloudflare.com/workers-ai/configuration/open-ai-compatibility/ but it seems it doesn't work this way with AI gateway, because these URLs are fixed including the model name and do not expect /embeddings or /chat/completions
there is this https://developers.cloudflare.com/workers-ai/configuration/open-ai-compatibility/ but it seems it doesn't work this way with AI gateway, because these URLs are fixed including the model name and do not expect /embeddings or /chat/completions
Danyone tested finetune mistral with using collab t4 gpu? im not sure if it is not capable to do that and need to subscribe pro due to this error im having "subprocess.CalledProcessError: Command '['/usr/bin/python3', '-m', 'autotrain.trainers.clm', '--training_config', 'my-autotrain-llm/training_params.json']' died with <Signals.SIGKILL: 9>." or basically collab need more ram?
Dthis is using autotrain huggingface suggested in documentation
RAfaik, Cloudflare is running the 1-step version so I'd expect it to be faster, but yeah.. width, height (as well as other parameters and features not yet but team said params are on the would be nice.
ROn the topic of https://developers.cloudflare.com/workers-ai/models/stable-diffusion-xl-lightning/. Noticed that the model now returns (heavily) compressed JPGs instead of PNGs. Is this intentional?
Jcc @michelle
WWe are considering migrating our existing Azure Whisper integration to use Cloudflare Whisper model instead. We have both setup but finding Cloudflare whisper seems to be less accurate. Technically is there a difference in the model that could cause this?
ICloudflare's Whisper model is the
base version of the model. Depending on what you're using on Azure it maybe be more accurate (I believe above base there is small, medium, and large, all of which will be more accurate)Wok thanks for the info
Jwill it default back to png as documented?
THi, I have a question about links between AI and R2. I want to use a model for captioning images from R2, do I have to make a fetch in my worker code of the R2 image path before sending it to cf AI or is there a better way?
(example : https://developers.cloudflare.com/workers-ai/models/uform-gen2-qwen-500m/)
(example : https://developers.cloudflare.com/workers-ai/models/uform-gen2-qwen-500m/)
KHi, I have a problem with Cloudflare Workers + Hono + Cloudflare AI, I have a route defined (i.e. /v1/chat/completions) and when the user triggers that route I try to run env.AI.run([model], [etc]), but I get this error:
Also tried removing the
TypeError: Cannot read properties of undefined (reading 'AI'). This is my Env interface:Also tried removing the
const env = [...] and running AI inside a function with function exampleFunction(env: Env) but it also didn't work.
LIs it possible for workers-ai to support OpenAI format API?
Jany updates here @michelle ? Is this an expected breaking change, or will this be reverted back to png?
NHi guys, how can use this worker ai ? Have someone the Java script for it ?
IYou can follow any of these guides. Use CLI or Dashboard if you want to deploy a Worker, use the API one for if you want to access it externally without a Worker: https://developers.cloudflare.com/workers-ai/get-started/
JWill llama 3 loras be supported soon? https://developers.cloudflare.com/workers-ai/fine-tunes/loras/
Cloudflare Docs
Upload and use LoRA adapters to get fine-tuned inference on Workers AI.
PHi, are there any startups that are using "Workers for Platforms"?
IThis would probably be a better question for #workers-for-platforms. This channel is for Workers AI.
RHmm.. quite a lot going on with that model right now. Was going to give feedback on the compression level as the immediate issue, but now the model is broken for deployed workers that are using SDK 1.0.53 or earlier. Which is kinda.. more immediate. Feels like the model is actively being worked on right in the open, so I'm thinking.. should I just hold off a bit, or try to play catch up with feedback?
