Reindex markdown RAG chunks with Supabase pgvector and webhooks

by Filip Mijic ✓ · 27 views · created 2026-06-15 · Document Extraction, AI RAG

What this workflow does

This workflow has 9 nodes and runs on a schedule (every day at 02:00) (plus 1 other trigger). Along the way it connects Postgres. It also calls kairesume.fit and jhccfsyytbkfmdvduvds.supabase.co over HTTP.

How it runs

Trigger: On a schedule (every day at 02:00) (plus 1 other trigger).

1. Fetch Sources (FAQ + Blog) (HTTP Request): calls kairesume.fit
2. Chunk and Batch (Code): runs custom JavaScript code
3. Loop Batches (Loop Over Items (Split in Batches)): loops over the items in batches
4. Delete Stale Chunks (Postgres): run a query
5. Embed Batch (Supabase) (HTTP Request): calls jhccfsyytbkfmdvduvds.supabase.co (POST)
6. Build Upsert SQL (Code): runs custom JavaScript code
7. Upsert Chunks (Postgres): run a query

Services it uses

Postgres

HTTP calls to: kairesume.fit, jhccfsyytbkfmdvduvds.supabase.co

Before you upgrade to n8n 3.0

Nodes used (6)

• Schedule Triggern8n-nodes-base.scheduleTrigger
• HTTP Requestn8n-nodes-base.httpRequest
• Coden8n-nodes-base.code
• Postgresn8n-nodes-base.postgres
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Webhookn8n-nodes-base.webhook

From the author

Quick Overview This workflow reindexes Markdown documentation into a Supabase Postgres pgvector table by fetching source docs from an HTTP API, chunking and embedding them via a Supabase Edge Function, upserting the vectors, and deleting stale chunks on a…

View the original on n8n.io → Check your own copy