Scrape and ingest web content into Supabase pgvector with Firecrawl

by Firecrawl ✓ · 961 views · created 2026-03-06 · Document Extraction, AI RAG

What this workflow does

This AI workflow has 18 nodes and runs when an HTTP POST request hits its webhook URL (plus 1 other trigger). Along the way it connects Supabase, Embeddings OpenAI, OpenRouter Chat Model and Reranker Cohere and 2 more.

How it runs

Trigger: When an HTTP POST request hits its webhook URL (plus 1 other trigger).

1. Validate and normalize URL (Code): runs custom JavaScript code
2. Answer query from enriched leads (AI Agent): runs an AI agent, with model: OpenRouter LLM; 1 tool (Retrieve documents from Supabase); memory: Chat memory
3. Check for duplicate in Supabase (Supabase): get
4. Return URL validation error (Respond to Webhook): sends the response back to the webhook caller
5. Skip if already ingested (If): checks a condition and branches into true / false
6. Return duplicate notice (Respond to Webhook): sends the response back to the webhook caller
7. Scrape company website with Firecrawl (Firecrawl): scrape
8. Store embeddings in Supabase (Supabase Vector Store): stores documents in the Supabase vector store, with embeddings: Generate OpenAI embeddings; document loader: Load scraped content
9. Return ingestion result (Respond to Webhook): sends the response back to the webhook caller

Services it uses

SupabaseEmbeddings OpenAIOpenRouter Chat ModelReranker CohereSupabase Vector StoreFirecrawl (community)

Uses Firecrawl. New users get 10% off with our link.

Before you upgrade to n8n 3.0

Nodes used (14)

• Webhookn8n-nodes-base.webhook
• Coden8n-nodes-base.code
• Supabasen8n-nodes-base.supabase
• Respond to Webhookn8n-nodes-base.respondToWebhook
• Firecrawl@mendable/n8n-nodes-firecrawl.firecrawl
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Embeddings OpenAI@n8n/n8n-nodes-langchain.embeddingsOpenAi
• Chat Trigger@n8n/n8n-nodes-langchain.chatTrigger
• AI Agent@n8n/n8n-nodes-langchain.agent
• OpenRouter Chat Model@n8n/n8n-nodes-langchain.lmChatOpenRouter
• Simple Memory@n8n/n8n-nodes-langchain.memoryBufferWindow
• Reranker Cohere@n8n/n8n-nodes-langchain.rerankerCohere
• Ifn8n-nodes-base.if
• Supabase Vector Store@n8n/n8n-nodes-langchain.vectorStoreSupabase

From the author

What this does Receives a URL via webhook, uses Firecrawl to scrape the page into clean markdown, and stores it as vector embeddings in Supabase pgvector. A visual, self-hosted ingestion pipeline for RAG knowledge bases. Adding a new source is as simple as…

View the original on n8n.io → Check your own copy