Automation library · Customer support

Answer questions from documents with RAG and Supabase

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

MediumCalls a model: OpenAI, OpenRouterRetrieval

Download free
19 stepsMedium: a working afternoon
0Branches: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 2Model 14Logic 1Service 2

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

  1. 1Default Data LoaderDocument Default Data LoaderModel
  2. 2When chat message receivedChat triggerStarts it
  3. 3GPT 4.1-miniLm Chat Open RouterModel
  4. 4Reranker CohereReranker CohereModel
  5. 5GPT 4.1-mini1Lm Chat Open RouterModel
  6. 6Reranker Cohere1Reranker CohereModel
  7. 7Embeddings OpenAI2Embeddings Open AiModel
  8. 8Embeddings OpenAI1Embeddings Open AiModel
  9. 9Embeddings OpenAIEmbeddings Open AiModel
  10. 10Manual TriggerManual triggerStarts it
  11. 11Upload to SupabaseVector Store SupabaseModel
  12. 12RAG AgentAgentModel
  13. 13Supabase Vector StoreVector Store SupabaseModel
  14. 14RAG Agent 2AgentModel
  15. 15Metadata AgentAgentModel
  16. 16Supabase Vector Store1Vector Store SupabaseModel
  17. 17Download FileGoogle DriveService
  18. 18Extract from FileExtract From FileService
  19. 19CodeCodeLogic

How it's built

Starts on
Someone opening a chat with it
Steps
19
Size
Medium: a working afternoon
Connects to
Google Drive, Supabase vectors
Model
OpenAI, OpenRouter
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 Google Drive and Supabase vectors accounts, and a key for OpenAI and OpenRouter. 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 and OpenRouter. 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.