Skip to content
Forums
Forums
How To
How to integrate a ...
 
Notifications
Clear all

How to integrate a custom LLM with the AI agent module

 
How To
Last Post by system 9 months ago
5 Posts
4 Users
0 Reactions
6 Views
RSS
simonator
 simonator
(@simonator)
Posts: 3
Active Member
Topic starter
 

Describe the problem/error/question

I am attempting to utilize the AI agent module. However, within the LLM input section, I can only select from a predefined list of LLMs. I am wondering if it's possible to connect to my own LLM via an HTTP call and feed the output into the module.

What is the error message (if any)?

It simply does not permit non-predefined LLMs to be fed into the module.

Please share your workflow

A straightforward AI agent that takes my chat message as input and then feeds it into this AI agent. Instead of using the original set of LLMs, I would like to connect to my own using an API call via the HTTP module.

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

Share the output returned by the last node

Information on your callin.io setup

  • callin.io version:
  • Database (default: SQLite):
  • callin.io EXECUTIONS_PROCESS setting (default: own, main):
  • Running callin.io via (Docker, npm, callin.io cloud, desktop app):
  • Operating system:
 
Posted : 21/08/2024 3:37 pm
n8n
 n8n
(@n8n)
Posts: 97
Trusted Member
 

It appears your topic is missing some crucial details. Could you please provide the following information, if relevant?

  • callin.io version:
  • Database (default: SQLite):
  • callin.io EXECUTIONS_PROCESS setting (default: own, main):
  • Running callin.io via (Docker, npm, callin.io cloud, desktop app):
  • Operating system:

Please provide the requested information.

 
Posted : 21/08/2024 3:37 pm
ria
 ria
(@ria)
Posts: 48
Eminent Member
 

Hi there!

Thanks for posting and welcome to the community!

:partying_face:

We've just launched our locally run AI Starter Kit, which allows you to use custom models as well (at least from the Ollama library).

Currently, the HTTP request node isn't designed to be used as a sub-node for defining a model. However, this sounds like a great feature request – feel free to add it and give it a vote!

:wink:

 
Posted : 23/08/2024 2:18 pm
simonator
 simonator
(@simonator)
Posts: 3
Active Member
Topic starter
 

Thank you for your response and for the warm welcome.

:smiley:

Unfortunately, the AI starter kit might not be suitable for my situation since I cannot run these models locally. I have just submitted a feature request.

Thanks again for your feedback!

 
Posted : 23/08/2024 3:54 pm
system
 system
(@system)
Posts: 332
Reputable Member
 

This thread was automatically closed 90 days following the last response. New replies are no longer permitted.

 
Posted : 21/11/2024 3:54 pm
Forum Jump:
  Previous Topic
Next Topic  
Share: