Cloudflare Developers•2y ago

do you mean news?

RRyan do you mean news?

Avocadio•7/8/24, 4:23 PM

yup. or an article

Avocadio•7/8/24, 4:24 PM

I used to use mistral and it was able to do web scraping

RyanOP•7/8/24, 4:57 PM

generally it would be sending a request to the url provided by the user, extracting the text of the article, feeding it into a llm, then sending it back in the worker's response

Avocadio•7/8/24, 5:19 PM

Yes i am wondering is there any ai model that is able to do that

Avocadio•7/8/24, 5:20 PM

That cloudflare supports

Avocadio•7/8/24, 5:21 PM

If not i am gonna scrape content in the url and feed the model but if there is a model that is able to do it then its better choice for me

AAvocadio If not i am gonna scrape content in the url and feed the model but if there is a...

Isaac McFadyen•7/8/24, 7:44 PM

No, there are no models that auto-scrape URLs - it's outside of the scope of an LLM.

Avocadio•7/8/24, 8:54 PM

i thought there were llms that able to web scrape

rob•7/8/24, 9:34 PM

https://github.com/jina-ai/reader

GitHub

GitHub - jina-ai/reader: Convert any URL to an LLM-friendly input w...

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

jina-ai/reader

rob•7/8/24, 9:34 PM

Check this

DDhravya Shah if you wanna do it on cloudflare, https://github.com/dhravya/markdowner

Avocadio•7/9/24, 9:07 PM

Yep i was about to build the same thing

Avocadio•7/9/24, 9:08 PM

Thx a lot

user•7/10/24, 9:14 AM

Does cloudflare AI's qwen model support tools?

user•7/10/24, 2:58 PM

according to qwen's docs, it supports function calling tools & uses openAI syntax

user•7/10/24, 2:58 PM

https://qwen.readthedocs.io/en/stable/framework/function_call.html

Fokke•7/11/24, 5:55 PM

We are building a state-of-the-art retrieval augmented generation chatbot completely on Cloudflare. We are eventually going to publish the whole source to the community, but for starters, we have two blogs that you all might like if you are thinking about building something like this yourself.

Intro - https://liquidmetal.ai/blog/sota-rag-intro/
Data Stores - https://liquidmetal.ai/blog/sota-rag-datastores/
Indexer (coming soon)

LiquidMetal AI - We build AI on Cloudflare

kufeng.•7/12/24, 6:18 AM

Uuser Does cloudflare AI's qwen model support tools?

user•7/12/24, 11:41 AM

any plans on this?

akazwz•7/14/24, 4:07 PM

Hello, I build a LLMs/AI chat platform build and design for Cloudflare worker AI. with many features like function calling, image to text, text to image, text to speech. all build with Cloudflare worker. https://github.com/akazwz/antonai

GitHub

GitHub - akazwz/antonai: a LLMs/AI chat platform build and design f...

a LLMs/AI chat platform build and design for Cloudflare worker AI. with many features like function calling, image to text, text to image, text to speech - akazwz/antonai

Thiago•7/14/24, 7:10 PM

What happened to the quality of the dreamshaper-8-lcmdreamshaper-8-lcm model? Its outputs have been of extremely low quality for the past ~3 days, to the point that they are completely unusable. Below are two examples, 1 month apart. Same prompt.

TThiago What happened to the quality of the `dreamshaper-8-lcm` model? Its outputs have ...

Raylight•7/14/24, 8:56 PM

Looks like the "guidance" parameter has been exposed/activated and it's possible that it doesn't behave as intended. The default of 7.5 will give results like the image on the right. If you add "guidance: 0.0" (or maybe 1.0) you'll get the same or similar results as you got before. You'll get better prompt following with higher numbers, but as of now there's a narrow range before images become degraded to the point of being unusable.

RRaylight Looks like the "guidance" parameter has been exposed/activated and it's possible...

Thiago•7/14/24, 9:53 PM

Oh, that makes perfect sense. Thank you!

akazwz•7/15/24, 12:00 PM

@Rahul it need to use vision model like LLaVA https://developers.cloudflare.com/workers-ai/models/#image-to-text

Cloudflare Docs

Models · Cloudflare Workers AI docs

Browse our entire catalog of models:

akazwz•7/15/24, 12:03 PM

if you want to use the image url in the prompt. you can use function calling to create a tools that use to be vision the image

Aakazwz Hello, I build a LLMs/AI chat platform build and design for Cloudflare worker AI...

akazwz•7/15/24, 12:06 PM

@Rahul In this code. i can simple answer with the image. and u can put it in tools https://github.com/akazwz/antonai/blob/main/app/routes/api.chat.ts#L70

GitHub

antonai/app/routes/api.chat.ts at main · akazwz/antonai

a LLMs/AI chat platform build and design for Cloudflare worker AI. with many features like function calling, image to text, text to image, text to speech - akazwz/antonai

akazwz•7/15/24, 12:21 PM

i write a simple tools to make this work.

akazwz•7/15/24, 1:32 PM

maybe you need some tools to parse the pdf like langchain. i am not sure if it will work

RRahul Thanks <@959078620360486964>

akazwz•7/16/24, 6:19 AM

You're welcome

Ken•7/18/24, 9:45 AM

Ken•7/18/24, 9:45 AM

server down

Ken•7/18/24, 9:45 AM

Ken•7/18/24, 9:45 AM

@cb

KKen Click to see attachment

cb•7/18/24, 10:04 AM

Working for me right now.

Ken•7/18/24, 10:08 AM

naa bro

Ken•7/18/24, 10:08 AM

its not

Ken•7/18/24, 10:08 AM

@cb

Ken•7/18/24, 10:08 AM

KKen <@462316658082709514>

DaniFoldi•7/18/24, 10:12 AM

?pings

Flare•7/18/24, 10:12 AM

Please 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.

threekat•7/19/24, 6:21 PM

poor lonlos has HIV

DDeleted User `@cf/runwayml/stable-diffusion-v1-5-img2img` is generating very low quality and ...

Raylight•7/19/24, 8:54 PM

Try adding the strength parameter. strength: 0.5strength: 0.5 for example. It defaults to 1.0, which pretty much means ignore the input image. Also, you could try to describe the desired output instead, like "a lion sitting on a bench". As for quality, the model - or something in Cloudflare's implementation - seems to have a tendency to produce over-saturated colors. Not sure what's going on. Setting the guidance parameter to a low value helps, but it's not really a solution.

do you mean news?

Similar Threads