Fetch Website Content, Gemini Embeddings to Pinecone KB
Fetches all pages from a website via sitemap or URLs, extracts clean text, generates Gemini embeddings, and stores in Pinecone for semantic search and RAG chatbots.
This n8n workflow automates the complete process of building a knowledge base from any website. It starts by collecting URLs from a provided sitemap XML or a manual list, parses the sitemap to extract all page links, merges them, and removes duplicates for efficiency. Then, it iterates through the unique URLs, politely fetching HTML content with delays to respect server limits.
Next, it processes the HTML to extract meaningful text from the page body, stripping out images, scripts, and noise fo
Platform
n8n
Category
Development & IT
Price
$24.99
Creator
Bryce Yu
web-scraping
gemini
pinecone
embeddings
knowledge-base
RAG
vector-database
data-extraction
n8n
automation
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.