RAG on Living Data

Name: RAG on Living Data
Rating: 4.0 (1 reviews)
Author: Free N8N

Beginner

0 nodes connected

detail.loadingPreview

Free N8N Temples

13 views

0 downloads

Community Contributedautomationdata indexinggenerative ainotionopenairagvector store

Integrates RAG (Retrieval-Augmented Generation) with dynamic, living data sources to provide context-aware answers.

🚀Ready to Deploy This Workflow?

⚡Deploy on Zeabur 🎁Get $200 Credit on DigitalOcean

About This Workflow

Overview

This workflow implements a Retrieval-Augmented Generation (RAG) system that continuously processes and indexes living data. It leverages OpenAI embeddings and a vector store retriever to provide up-to-date, contextually relevant answers to user queries.

Key Features

Real-time data ingestion and indexing from Notion.
Dynamic updates of embeddings based on Notion page modifications.
Token splitting for efficient processing of large text chunks.
OpenAI's GPT models for generating responses.
Vector store for efficient semantic search and retrieval.

How To Use

Configure the Notion credentials and database ID.
Ensure OpenAI API credentials are set up.
Connect to your vector store (e.g., Supabase).
Adjust chunk size and overlap in the 'Token Splitter' node for optimal performance.
The workflow will automatically process updates from the specified Notion database.

Apps Used

automation

data indexing

generative ai

notion

openai

rag

vector store

Workflow JSON

{
  "id": "6b7c28d8-3b53-4108-a379-3ef84c2c5ffb",
  "name": "RAG on Living Data",
  "nodes": 0,
  "category": "Community Contributed",
  "status": "active",
  "version": "1.0.0"
}

Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.