Skip to content
NEWError doctor and Watchtower: failed n8n runs explained in plain words, and emailed to you. See what is new

Library / Web Scraping & Research

Web Scraping & Research

Extract Job Listings with Firecrawl and a Vector Store

When triggered by an app event, the workflow scrapes job listings with Firecrawl, uses a Supabase vector store with OpenAI to process them and notifies Telegram.

Import it free Sign in to open it

What it does

## RAG DATA Double click to edit me. Guide

The steps

  1. Search File
  2. Get Data
  3. Supabase Vector Store
  4. Embeddings OpenAI
  5. Default Data Loader
  6. Recursive Character Text Splitter
  7. Loop Over Items
  8. Supabase Vector Store1
  9. Embeddings OpenAI1
  10. Google Drive Trigger
  11. 📥 New Job Link via Telegram
  12. 🔧 Prepare URL for Extraction
  13. 🧮 Map Job Type & Category IDs
  14. 📥 Download Company Logo

51 steps in total.

Similar automations

Web Scraping & ResearchExtract Structured Web Data with Firecrawl Extract7 stepsRAG & Knowledge BasesPost Notion Job Listings with OpenAI RAG and Supabase11 stepsRAG & Knowledge BasesChat with Supabase Vector Store and Postgres Memory12 stepsData Sync & ETLSync Google Drive Files to an OpenAI Vector Store27 steps