Is there a way to Add an API key from an LLM that is not from those listed? We use this LLM called Deepseek and would like to integrate it. Already have the Api keys etc.

AFAIK, no, as Discourse probably only supports those listed. If I am wrong, anyone, feel free to contradict me.

[imagem] oga: Deepseek https://github.com/deepseek-ai/DeepSeek-LLM It works with VLLM, you can can just configure a VLLM endpoint and it should work out of the box.

WOW !! Thanks so much. I will try this out.

Having support for almost every modern LLM that exist was a big focus for release 3.3, and we finally got to it, just in time when open weights LLMs are catching up to closed ones. Let me know if you need help configuring DeepSeek in your instance, this feature is brand new and we are still updatin…

Yes I do need help. Looked around but don’t see how to add it without VLLM. VLLM is another overhead I would rather avoid due the requirements. Would be great if there’s an integration not only for Deepseek, but for many other Open source LLMs. I am of the opinion that’s where this LLM race is head…

[imagem] oga: From what we see, companies are hesitant handing out their Data to the “cloud”. Open source that allows them to run local instances using tools like GPT4ALL, HuggingFace will end up being the preferred model. Yes, I agree with that, which is why we support running your own LLM f…

Thanks, from my reading, {may have read it wrong) don’t I need a new Droplet [Digital Ocean] aka, VPS to deploy a VLLM? or can it be deployed on the same Droplet that hosts my Discourse Instance? If yes, on the same instance, would it be on the same directory as Discourse or a separate Directory? …

What exact droplet are you running your current Discourse site? The $6 one ?

The $15 one. I think it is 2 GB ram. Once we finish testing I will scale it up. Thanks

[imagem] oga: The $15 one. Hmm, are you aware that a droplet to run this Deepseek model you want will cost you like $10,000 a month?

Posso adicionar outros LLM?

Suporte

sam (Sam Saffron) Agosto 1, 2024, 12:01am 3

Funciona com VLLM, você pode configurar um endpoint VLLM e ele deve funcionar imediatamente.

Debugging adding new LLM

Rebuilding Discourse after invalid GitHub repo addition

Tópico		Respostas	Visualizações
DeepSeek provider support? What to do when model provider isn't in "Provider" list? Support ai	12	1092	3 de Fevereiro de 2025
Debugging adding new LLM Support ai	8	483	23 de Agosto de 2024
How to configure Discourse to use a locally installed LLM? Support ai	7	358	3 de Junho de 2025
Self-Hosting an OpenSource LLM for DiscourseAI Self-Hosting ai	12	3909	6 de Julho de 2026
I need help to configure LLM DeepSeek R1 0528 - free for Automatic translations with Discourse AI Support content-localization	33	885	3 de Dezembro de 2025

Posso adicionar outros LLM?

Tópicos relacionados