RAG on living data

Switch trigger (optional) If you are on the cloud plan, consider switching to the Notion Trigger Node instead, to save on executions.

Workflow Structure (19 nodes)
100%
Schedule Trigger
Schedule Trigger
Notion Trigger
Notion Trigger
Notion
Get updated pages
No Op
Input Reference
Split In Batches
Loop Over Items
Supabase
Delete old embeddings if exist
Limit
Limit
Notion
Get page blocks
Summarize
Concatenate to single string
Langchain.vector Store Supabase
Supabase Vector Store
Langchain.document Default Data Loader
Default Data Loader
Limit
Limit1
Langchain.chat Trigger
When chat message received
Langchain.lm Chat Open Ai
OpenAI Chat Model
Langchain.chain Retrieval Qa
Question and Answer Chain
Langchain.retriever Vector Store
Vector Store Retriever
Langchain.vector Store Supabase
Supabase Vector Store1
Langchain.embeddings Open Ai
Embeddings OpenAI
Langchain.text Splitter Token Splitter
Token Splitter
Node Types:
default
logic
trigger
action
Requires credentials

Prerequisites

Required Credentials (3)

Notion

Used by: Get page blocks, Notion Trigger +1 more

Docs

OpenAI

Used by: Embeddings OpenAI, OpenAI Chat Model

Docs

Supabase

Used by: Delete old embeddings if exist, Supabase Vector Store1 +1 more

Docs

Multiple services required

This workflow needs 3 different credentials. Make sure you have accounts for all services before importing.

Complexity

Advanced

Expert level. Custom code, complex logic, many integrations.

Setup time: ~50 min
Score: 65/100
Loops
7 Integrations

When to Use This Workflow

Scheduled Operations

Run automated tasks at specific times - daily reports, weekly cleanups, monthly backups.

Set it and forget it - reliable automation that runs on your schedule.

Real-time Response

React instantly when events happen - new orders, form submissions, or API calls.

Zero delay between trigger and action for time-sensitive workflows.

Error Reduction

Eliminate human error from routine processes with consistent automation.

Improve accuracy and reliability across your workflows.

workflow.json
{
  "id": "JxFP8FJ2W7e4Kmqn",
  "meta": {
    "instanceId": "fb8bc2e315f7f03c97140b30aa454a27bc7883a19000fa1da6e6b571bf56ad6d",
    "templateCredsSetupCompleted": true
  },
  "name": "RAG on living data",
  "tags": [],
  "nodes": [
    {
      "id": "49086cdf-a38c-4cb8-9be9-d3e6ea5bdde5",
      "name": "Embeddings OpenAI",
      "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
      "position": [
        1740,
        1040
      ],
      "parameters": {
        "options": {}
      },
...

Workflow Details

Nodes
34
Trigger
Event
Source
awesome
Added
Dec 4, 2025

Need Help?

Check out the official n8n documentation for detailed guides.

Related Workflows

RAG & GenAI App With WordPress Content

Workflow 1 : Initial Embedding Use this workflow to create the initial embedding for your WordPress website content

Embeddingsopenai
Documentdefaultdataloader
Textsplittertokensplitter
Lmchatopenai
53 nodesWebhook
Curated

Supabase Insertion & Upsertion & Retrieval

INSERTING - it's important to use the same embedding model when for any interaction with your vector database (inserting...

Google-drive
Documentdefaultdataloader
Chainretrievalqa
Lmchatopenai
21 nodesEvent
Curated

Store Notion's Pages as Vector Documents into Supabase with OpenAI

Store Notion's Pages as Vector Documents into Supabase This workflow assumes you have a Supabase project with a table th...

Embeddingsopenai
Textsplittertokensplitter
Notion
Documentdefaultdataloader
9 nodesEvent
Curated

AI Agent To Chat With Files In Supabase Storage

Replace Storage name, database ID and credentials.

Http-request
Documentdefaultdataloader
Textsplitterrecursivecharactertextsplitter
Embeddingsopenai
33 nodesEvent
Curated

Advanced AI Demo (Presented at AI Developers #14 meetup)

![h](https://i.postimg.cc/9XLvL5dL/slide-sf-talk.pngfull-width)

Slack
Textsplitterrecursivecharactertextsplitter
Embeddingsopenai
Documentdefaultdataloader
39 nodesEvent
Curated

Ask questions about a PDF using AI

Load data into database Fetch file from Google Drive, split it into chunks and insert into Pinecone index

Google-drive
Textsplitterrecursivecharactertextsplitter
Embeddingsopenai
Documentdefaultdataloader
16 nodesEvent
Curated