Fetch all page content from website and store with Gemini embedding in Pinecone

by Zain Khan ✓ · 460 views · created 2025-07-27 · Document Extraction, AI RAG

What this workflow does

This AI workflow has 15 nodes and runs when someone submits an n8n form. Along the way it connects Embeddings Google Gemini and Pinecone Vector Store.

How it runs

Trigger: When someone submits an n8n form.

1. Switch: routes items into branches
2. Split Pages URL (Code): runs custom JavaScript code
3. Fetch Sitemap (HTTP Request): calls an HTTP API
4. Merge: merges the data from its input branches
5. XML: converts between XML and JSON
6. Remove Duplicate URLs (Remove Duplicates): removes duplicate items
7. Extract Page URLs (Code): runs custom JavaScript code
8. Loop Over Page URLs (Loop Over Items (Split in Batches)): loops over the items in batches
9. Extract Content (HTML): parses or builds HTML
10. Fetch Page HTML For content (HTTP Request): calls an HTTP API

…plus 2 more steps. See the full node list below.

Services it uses

Embeddings Google GeminiPinecone Vector Store

Before you upgrade to n8n 3.0

Nodes used (13)

• Coden8n-nodes-base.code
• XMLn8n-nodes-base.xml
• HTTP Requestn8n-nodes-base.httpRequest
• Mergen8n-nodes-base.merge
• Remove Duplicatesn8n-nodes-base.removeDuplicates
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• HTMLn8n-nodes-base.html
• Waitn8n-nodes-base.wait
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Embeddings Google Gemini@n8n/n8n-nodes-langchain.embeddingsGoogleGemini
• Pinecone Vector Store@n8n/n8n-nodes-langchain.vectorStorePinecone
• n8n Form Triggern8n-nodes-base.formTrigger
• Switchn8n-nodes-base.switch

From the author

Fetch and Extract all Website Pages Content and Store in Pinecone Vector Database as KnowledgeBase with Google Gemini Embeddings Use cases are many: Populate a custom chatbot's knowledge base, create a powerful search index for your website, or build a…

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