The flow
Starts it 2Model 7Service 1
The steps in the order they run, from what starts it.
- 1Default Data LoaderDocument Default Data LoaderModel
- 2Simple MemoryMemory Buffer WindowModel
- 3When chat message receivedChat triggerStarts it
- 4When clicking ‘Execute workflow’Manual triggerStarts it
- 5Google Gemini Chat ModelLm Chat Google GeminiModel
- 6Embeddings Google GeminiEmbeddings Google GeminiModel
- 7Supabase Vector StoreVector Store SupabaseModel
- 8AI AgentAgentModel
- 9HTTP RequestHttp RequestService
- 10Retrieve Supabase VectorVector Store SupabaseModel
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 10
- Size
- Medium: a working afternoon
- Connects to
- Supabase vectors
- Model
- Gemini
- Retrieval
- Answers are drawn from documents you supply, not from the model alone
Questions
What does it need to run?
An n8n account, plus your own Supabase vectors account, and a key for Gemini. You connect your own accounts after importing it; none are included.
What starts it?
It starts on someone opening a chat with it.
Does it use AI?
Yes. It calls Gemini. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 10 steps is enough that you should read each one before running it.
How do I import it?
Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.
Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 10 steps before you point it at anything that matters.