Maintain RAG embeddings with OpenAI, Postgres and auto drift rollback
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 27 nodes and runs on a schedule (every day at 02:00) (plus 1 other trigger). Along the way it connects Postgres, Embeddings OpenAI and OpenAI Chat Model.
How it runs
Trigger: On a schedule (every day at 02:00) (plus 1 other trigger).
- Workflow Configuration (Edit Fields (Set)): sets 6 fields: documentSourceUrl, chunkSize, chunkOverlap…
- Fetch Documents from Source (HTTP Request): calls an HTTP API
- Fetch Previous Chunk Hashes (Postgres): run a query
- Chunk Documents & Compute Hash (Code): runs custom JavaScript code
- Detect Changed Chunks (Compare Datasets): uses Compare Datasets
- New Vector Store (Candidate) (Simple Vector Store): stores documents in the Simple vector store, with embeddings: OpenAI Embeddings; document loader: Document Loader
- Store Embedding Metadata (Code): runs custom JavaScript code
- Save Embedding Version Metadata (Postgres): uses Postgres
- Fetch Golden Questions (Postgres): run a query
- Fetch Previous Embeddings (Postgres): run a query
…plus 9 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)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Webhook
n8n-nodes-base.webhook - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - Postgres
n8n-nodes-base.postgres - Compare Datasets
n8n-nodes-base.compareDatasets - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - If
n8n-nodes-base.if - AI Agent
@n8n/n8n-nodes-langchain.agent
From the author
Overview This workflow implements a self-healing Retrieval-Augmented Generation (RAG) maintenance system that automatically updates document embeddings, evaluates retrieval quality, detects embedding drift, and safely promotes or rolls back embedding updates.…