Is there a way to implement other open-sourced LLM?

Hey community,
I’m playing with n8n for a while, ChatTrigger feature is fantastic. However, in my version (1.27) only few built-in LLMs are allowed (OpenAI, Google, Mistral). I am wondering how to implement some other new LLMs like Grok-1 to my workflow. Is there a way/tutorial to wrap other model as a ChatModel node?

It looks like your topic is missing some important information. Could you provide the following if applicable.

  • n8n version:
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app):
  • Operating system:
  • n8n version: 1.27.3
  • Database (default: SQLite): SQLite
  • n8n EXECUTIONS_PROCESS setting (default: own, main): own
  • Running n8n via (Docker, npm, n8n cloud, desktop app): Dokcer
  • Operating system: Ubuntu

Hey @zeech,

We are adding new LLMs fairly often so it is always worth checking the release notes, if you wanted to add something that is missing though you could create a community node using the existing nodes as an example.

Thanks Jon!

I’m also looking forward other LLMs to be supported.

Since I have played with different LLMs for a while, I came out a simple solution and wonder if the community could provide a customized LLM node which is implemented as HTTP request. It means we can just trigger a LLM with API call (with base url, header, body etc., just like a HTTP node). As far as I know, we can call any LLM through this approach.

Besides, I have played Agents capabilities of n8n, I am also looking for the same HTTP capabilities for the Tool node.

1 Like

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.