Automation library · Data collection

Build a RAG knowledge chatbot with OpenAI and Google Drive

Started by someone opening a chat with it, and works across Google Drive, 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. 17 steps, 1 loop or waits: a working afternoon to understand properly.

MediumCalls a model: OpenAIRetrieval

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

The flow

Starts it 3Model 9Logic 2Service 3

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

  1. 1File UpdatedGoogle Drive triggerStarts it
  2. 2Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
  3. 3File CreatedGoogle Drive triggerStarts it
  4. 4Embeddings OpenAIEmbeddings Open AiModel
  5. 5Postgres Chat MemoryMemory Postgres ChatModel
  6. 6OpenAI Chat ModelLm Chat Open AiModel
  7. 7When chat message receivedChat triggerStarts it
  8. 8Embeddings OpenAI1Embeddings Open AiModel
  9. 9Set File IDSetLogic
  10. 10Default Data LoaderDocument Default Data LoaderModel
  11. 11Supabase Vector StoreVector Store SupabaseModel
  12. 12RAG AI AgentAgentModel
  13. 13RAG Vector storeVector Store SupabaseModel
  14. 14Loop Over ItemsSplit In BatchesLogic
  15. 15Delete a rowSupabaseService
  16. 16Download the fileGoogle DriveService
  17. 17Extract from FileExtract From FileService

How it's built

Starts on
Someone opening a chat with it
Steps
17, 1 loop or waits
Size
Medium: a working afternoon
Connects to
Google Drive, 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 Google Drive, 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. 17 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 17 steps before you point it at anything that matters.