Automation library · Documents and files

Upsert huge documents in a vector store with Supabase

Started by someone opening a chat with it, and works across Notion, Supabase and Supabase vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 19 steps, 1 loop or waits: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

19 stepsMedium: a working afternoon
0Branches: places the flow splits
1Loop or waits
3Services it connects to

The flow

Starts it 3Model 8Logic 4Service 4

The steps in the order they run, from what starts it.

  1. 1Embeddings OpenAIEmbeddings Open AiModel
  2. 2Token SplitterText Splitter Token SplitterModel
  3. 3OpenAI Chat ModelLm Chat Open AiModel
  4. 4When chat message receivedChat triggerStarts it
  5. 5Schedule TriggerSchedule triggerStarts it
  6. 6Notion TriggerNotion triggerStarts it
  7. 7Supabase Vector StoreVector Store SupabaseModel
  8. 8Supabase Vector Store1Vector Store SupabaseModel
  9. 9Default Data LoaderDocument Default Data LoaderModel
  10. 10Question and Answer ChainChain Retrieval QaModel
  11. 11Get updated pagesNotionService
  12. 12Input ReferenceNo OpLogic
  13. 13Limit1LimitLogic
  14. 14Vector Store RetrieverRetriever Vector StoreModel
  15. 15Loop Over ItemsSplit In BatchesLogic
  16. 16Delete old embeddings if existSupabaseService
  17. 17LimitLimitLogic
  18. 18Get page blocksNotionService
  19. 19Concatenate to single stringSummarizeService

How it's built

Starts on
Someone opening a chat with it
Steps
19, 1 loop or waits
Size
Medium: a working afternoon
Connects to
Notion, Supabase, 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 Notion, Supabase and Supabase vectors accounts, 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. 19 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.

Before you run it

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 19 steps before you point it at anything that matters.