OpenWebUI + Anthropic / Claude

[chetbaker]

yup, I'm trying to find a reasonable nice interfase to deal with claude

[p44]

@chetbaker OpenUI could be one of the best, but limited technological knowledge and these problems do not allow us to use it.

Meanwhile you can use https://www.typingmind.com/ but is not for free.

[eddowding]

I'm now having similar problems integrating perplexity.

[p44]

@eddowding same error?

[chetbaker]

I'm receiving the same error I wonder if the app is usable

[p44]

@chetbaker App is totally unusable and unuseful at this point... Especially for those like me don't have right skills and knowledge to move forward...

[marcusquinn]

Can confirm, this works really well. Just search for the model you want, eg: "anthropic", and pick the most popular: https://openwebui.com/functions?query=

Then it's a bit of copy/paste (Name, Description/Content) into Open WebUI > Admin Panel > Functions > +

Recommend you stick at it. It does work, and there's quite a bit more to this app that meets the eye. Worth figuring out, it's not technical, just a but unfamiliar way of working at first.

[p44]

@marcusquinn Thanks a lot I will re-install again and try to do as suggested. Thanks again

[marcusquinn]

@p44 I think it's worth the effort, as the app actually has a ton of potential when setup, it's kinda like poe.com but more, because you can get into web scraping, content repurposing, lots of things with models, tools, functions.

[p44]

@marcusquinn Actually I was using https://www.typingmind.com/ but take a lot of time to load and little bit concerned about privacy.

I tried to install Anthropic from https://openwebui.com/functions?query=, but it seems require a login to download that. Can you confirm that I need to be a registered user to download?

Thanks again for your patience

[marcusquinn]

@p44 Open WebUI is just an interface (don't bother with the local Ollama on a VPS without a GPU).

Yes, you have to create an account with each API service to get a key, and usually deposit a few dollars for them to work.

Short-term cost, but long-term saving from having subscriptions for thing you won't use that much.

So far I've setup the Functions / Pipes for: OpenAI, Anthropic V2, Google GenAI, Deepseek, Grok.

All pretty much the same process, and then gives you the ability to quickly compare responses from multiple models in the same chat window.

[p44]

@marcusquinn Ok Marcus Thanks

[timconsidine]

Is there a hosted version of Ollama ?
(because my cloudron instance does not have GPU)

[robi]

@timconsidine no, but you can get GPU servers with AI niceties from Koyeb. I think They have a Ollama installer.