Hi, I’ve only just started working with n8n and AI/LLM. In a short time, I have managed to build a working RAG system and can successfully query the documents in my vector store.
What I’d now like to do is get the system to provide suggested ‘follow-ups’. OpenWebUI does this ‘out of the box’ (see image).
Describe the problem/error/question
So, how can I take the user’s initial input (via chat or webook) and process this to generate ‘Follow-up’ suggestions and append these to the response?
What is the error message (if any)? n/a
Please share your workflow
n/a
Share the output returned by the last node
n/a
Information on your n8n setup
- n8n version: 1.105.4
- Database (default: SQLite): SQLite for n8n, Supabase for the workflow
- n8n EXECUTIONS_PROCESS setting (default: own, main):
- Running n8n via (Docker, npm, n8n cloud, desktop app): Docker
- Operating system: Debian 12 (Linux)
