Split web pages into vector-ready chunks with Ragfeed
Go to Workflow
Leif Albrand (Ragfeed)
Description
Quick Overview
This workflow runs manually to send a webpage URL to the Ragfeed scraping API, which returns the page content split into token-bounded text chunks, then outputs one n8n item per chunk ready for embedding and storage in a vector database.
How it works
Runs when you execute the workflow manually.
Sets the target webpage URL and the maximum chunk size in tokens.
Sends a POST request to the Ragfeed API (/v2/scrape) to scrape the URL and return the content in chunk format.
Splits Ragfeed’s data.chunks array into one item per chunk so each record can be embedded or stored independently.
Setup
Create an n8n Header Auth credential that sends an Authorization: Bearer header.
Select that credential in the HTTP request that calls https://api.ragfeed.de/v2/scrape.
Update the URL and maxTokens values to match the page you want to process and your preferred chunk size.
This workflow was created by Leif Albrand (Ragfeed) and shared publicly on the n8n community template library. n8nFind indexes it for discovery — the workflow remains the property of its original creator.