The flow
Starts it 3Model 9Logic 2
The steps in the order they run, from what starts it.
- 1Webhook - Ingest Internal DocsWebhookStarts it
- 2Embeddings OpenAI - IngestEmbeddings Open AiModel
- 3Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
- 4Chat Trigger - Internal RAG ChatChat triggerStarts it
- 5OpenAI Chat Model - AnswerLm Chat Open AiModel
- 6Embeddings OpenAI - RetrieveEmbeddings Open AiModel
- 7Code - Normalize and Validate DocsCodeLogic
- 8Supabase Vector Store - Insert DocumentsVector Store SupabaseModel
- 9Default Data Loader - JSON ContentDocument Default Data LoaderModel
- 10Question and Answer Chain - RAGChain Retrieval QaModel
- 11Supabase Vector Store - RetrieveVector Store SupabaseModel
- 12Respond - Ingest DoneRespond To WebhookStarts it
- 13Set - Chat OutputSetLogic
- 14Vector Store RetrieverRetriever Vector StoreModel
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 14
- Size
- Medium: a working afternoon
- Connects to
- Supabase vectors
- Model
- OpenAI
- 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 OpenAI. 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 OpenAI. 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. 14 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 14 steps before you point it at anything that matters.