OpenAI Run additional_instructions

Questions
,
1

Need to inject Run additional_instructions

OpenAI Assistants API offers the ability to pass additional_instructions for each Run. This will allow me to add message-specific context. how can I do this in OpenAI Assistants Node? Or other OpenAI node? I know I can build out my entire API workflow using HTTP request nodes, but trying to avoid that heavy handed approach.

Information on your n8n setup

  • n8n version: 1.67.1
  • Database (default: SQLite): sqllite
  • n8n EXECUTIONS_PROCESS setting (default: own, main): default
  • Running n8n via (Docker, npm, n8n cloud, desktop app): npm
  • Operating system: windows 10

cc @oleg

2

Hi!
I built the entire process of sending message, run assistant and get messages with HTTP requests. You can find it here - Telegram Bot with Supabase memory and OpenAI assistant integration | n8n workflow template

3

thank you @Mark_S - I was hoping that I can get support from the n8n team to build this as a property into the OpenAI node, but I appreciate you sharing your workflow!

I’ve created a feature request asking for additional_instructions support. Please vote!

1 Like