Skip to main content

Categorize Revolut transactions automatically with GPT-4 and Supabase

Workflow preview

Workflow preview
100%
Categorize Revolut transactions automatically with GPT-4 and Supabase preview
Open on n8n.io

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Revolut Extracts Analyzer This n8n template processes Revolut statements, normalizes transactions, and uses AI to categorize expenses automatically. Use cases include detecting subscriptions, separ...

Best for

  • Document Extraction automation workflows
  • AI Summarization automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.manualtrigger, n8n-nodes-base.stickynote, n8n-nodes-base.googledrive, n8n-nodes-base.supabase, n8n-nodes-base.set, n8n-nodes-base.code, n8n-nodes-base.splitinbatches, @n8n/n8n-nodes-langchain.chainllm

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Jose Luis Segura.

Original n8n.io source

1.1 Workflow description

Title
Categorize Revolut transactions automatically with GPT-4 and Supabase
Workflow name
Categorize Revolut transactions automatically with GPT-4 and Supabase

Revolut Extracts Analyzer

This n8n template processes Revolut statements, normalizes transactions, and uses AI to categorize expenses automatically.

Use cases include detecting subscriptions, separating internal transfers, and building dashboards to track spending.


How it works

  • Get Categories from Supabase
  • Download & Transform
  • Loop Over Items
  • LLM Categorizer
  • Insert into Supabase

How to use

  • Start with the manual trigger node or replace it with a schedule/webhook.
  • Connect Google Drive to provide Revolut CSV files.
  • Ensure Supabase has tables for transactions and categories.
  • Extend with notifications, reports, or BI tools.

Requirements

  • Google Drive for CSV files
  • Supabase tables for categories & transactions
  • LLM provider (OpenAI/Gemini)

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - When clicking ‘Execute workflow’

Type / Role
n8n-nodes-base.manualTrigger - manualTrigger
Config choices
Version 1

Block 2 - Sticky Note

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 3 - Download extract

Type / Role
n8n-nodes-base.googleDrive - googleDrive
Config choices
Version 3

Block 4 - Create a row

Type / Role
n8n-nodes-base.supabase - supabase
Config choices
Version 1

Block 5 - Normalize content

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 6 - Extract merchant

Type / Role
n8n-nodes-base.code - code
Config choices
Version 2

Block 7 - Loop Over Items

Type / Role
n8n-nodes-base.splitInBatches - splitInBatches
Config choices
Version 3

Block 8 - Category extraction

Type / Role
@n8n/n8n-nodes-langchain.chainLlm - chainLlm
Config choices
Version 1.7

Block 9 - Merge

Type / Role
n8n-nodes-base.merge - merge
Config choices
Version 3.2

Block 10 - Output Parser

Type / Role
@n8n/n8n-nodes-langchain.outputParserStructured - outputParserStructured
Config choices
Version 1.3

Block 11 - Get many rows

Type / Role
n8n-nodes-base.supabase - supabase
Config choices
Version 1

Block 12 - Aggregate

Type / Role
n8n-nodes-base.aggregate - aggregate
Config choices
Version 1

Block 13 - Sticky Note1

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 14 - Sticky Note2

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 15 - Sticky Note3

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 16 - Sticky Note4

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 17 - Uniq Hash

Type / Role
n8n-nodes-base.crypto - crypto
Config choices
Version 1

Block 18 - gpt-4.1-mini

Type / Role
@n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices
Version 1.2

Block 19 - Extract from File

Type / Role
n8n-nodes-base.extractFromFile - extractFromFile
Config choices
Version 1

3. Summary Table

Workflow Categorize Revolut transactions automatically with GPT-4 and Supabase
Complexity advanced
Nodes 19
Categories Document Extraction, AI Summarization
Author Jose Luis Segura
Published 21 Sept 2025

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/8807/8807.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

    Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.

  4. 4. Test with sample data

    Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.

  5. 5. Activate and monitor

    Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Frequently asked questions

What does Categorize Revolut transactions automatically with GPT-4 and Supabase do?

Revolut Extracts Analyzer This n8n template processes Revolut statements, normalizes transactions, and uses AI to categorize expenses automatically. Use cases include detecting subscriptions, separ...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Document Extraction, AI Summarization use case.