Use Gemini's fine tuned model in "Gemini Chat Model" node

Questions
1

Describe the problem/error/question

I just fine tuned a Gemini-1.5-flash model and I 'have been trying to use it in my n8n work flow, in the “Gemini Chat Model” node.

Inside the node, I set the “Model” field to {{ "models/tunedModels/my-fine-tuned-models-name" }}.

In the fine-tuned model, I assigned permissions to the project.

When I run the workflow, I get the below error message.

Am I doing something wrong, or is it just not possible to call a fine tuned model from the “Gemini Chat Model” node?

What is the error message (if any)?

Error in sub-node ‘Google Gemini Chat Model‘
[GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/tunedModels/fine-tune--sku-and-units-examples-es81ya:generateContent: [400 Bad Request] Developer instruction is not enabled for tunedModels/fine-tune--sku-and-units-examples-es81ya

Information on your n8n setup

  • n8n version: 1.77.3
  • Database (default: SQLite): SQLite
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • Running n8n via (Docker, npm, n8n cloud, desktop app): Docker
  • Operating system: Linux Debian
2

Sorry, I have to bump this for visibility - still struggling with this

3

Hey @rmol two quick questions:

  1. Are you sending your fine tuned model system instructions?
  2. Are you asking for responses in JSON format?