Detect semantic duplicate website pages with Google Drive, Ollama and Postgres
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 29 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Google Drive, Postgres, Postgres PGVector Store and Embeddings Ollama.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Clear Vector Table (Postgres): delete table
- Clear Scraped Pages Table (Postgres): delete table
- Scan Source Directory (Google Drive): work with file folder
- Isolate Target Documents (Filter): keeps only the items that match a condition
- Loop Source File (Loop Over Items (Split in Batches)): loops over the items in batches
- Batches for Embedding (Loop Over Items (Split in Batches)): loops over the items in batches
- GDrive Download Document (Google Drive): download
- Create HNSW Index (Postgres): run a query
- Get Unprocessed Scraped Text (Postgres): run a query
- Extract Raw Text Content (HTML): parses or builds HTML
…plus 15 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (14)
- Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Google Drive
n8n-nodes-base.googleDrive - HTML
n8n-nodes-base.html - Postgres
n8n-nodes-base.postgres - Postgres PGVector Store
@n8n/n8n-nodes-langchain.vectorStorePGVector - Embeddings Ollama
@n8n/n8n-nodes-langchain.embeddingsOllama - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Remove Duplicates
n8n-nodes-base.removeDuplicates - Manual Trigger
n8n-nodes-base.manualTrigger - Filter
n8n-nodes-base.filter - Convert to File
n8n-nodes-base.convertToFile - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code
From the author
Quick overview This workflow scans HTML files in a Google Drive folder, extracts and stores page text in Postgres, generates embeddings with Ollama and PGVector, then computes chunk-level and page-level semantic similarity to identify likely duplicate pages…