Automation library · Data collection

Reindex markdown RAG chunks with Supabase

Started by another system calling it, and works across Postgres. 9 steps, 1 loop or waits: a working afternoon to understand properly.

Medium

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

The flow

Starts it 2Logic 3Service 4

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

  1. 1Schedule: Daily ReindexSchedule triggerStarts it
  2. 2Deploy WebhookWebhookStarts it
  3. 3Fetch Sources (FAQ + Blog)Http RequestService
  4. 4Chunk and BatchCodeLogic
  5. 5Loop BatchesSplit In BatchesLogic
  6. 6Delete Stale ChunksPostgresService
  7. 7Embed Batch (Supabase)Http RequestService
  8. 8Build Upsert SQLCodeLogic
  9. 9Upsert ChunksPostgresService

How it's built

Starts on
Another system calling it
Steps
9, 1 loop or waits
Size
Medium: a working afternoon
Connects to
Postgres
Model
None. This is plumbing, not judgement

Questions

What does it need to run?

An n8n account, plus your own Postgres account. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

No. Every step is fixed logic or a call to a service, so it does the same thing every time.

How long does it take to set up?

Plan an afternoon. 9 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 9 steps before you point it at anything that matters.