Automation library · Documents and files

Two-stage document retrieval chatbot with OpenAI and Supabase

Started by someone opening a chat with it, and works across Supabase. It hands the judgement calls to OpenAI. 11 steps: a working afternoon to understand properly.

MediumCalls a model: OpenAI

11 stepsMedium: a working afternoon
0Branches: places the flow splits
0Loops or waits
1Service it connects to

The flow

Starts it 2Model 2Logic 4Service 3

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

  1. 1Database retrieval1Tool CodeModel
  2. 2When chat message receivedChat triggerStarts it
  3. 3When clicking ‘Execute workflow’Manual triggerStarts it
  4. 4OpenAIOpen AiModel
  5. 5Find FilesCodeLogic
  6. 6GetFileSupabaseService
  7. 7Set OutputSetLogic
  8. 8Filter similarityFilterLogic
  9. 9OpenAI CreateEmbeddingsHttp RequestService
  10. 10Aggregate filesAggregateLogic
  11. 11UpdateEmbeddingSupabaseService

How it's built

Starts on
Someone opening a chat with it
Steps
11
Size
Medium: a working afternoon
Connects to
Supabase
Model
OpenAI

Questions

What does it need to run?

An n8n account, plus your own Supabase 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. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 11 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 11 steps before you point it at anything that matters.