Airline web check-in data extraction with Ollama AI, Google Sheets & Postgres Vector DB
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 13 nodes and runs when a chat message arrives. Along the way it connects Google Sheets, Ollama Chat Model, Embeddings Ollama and Postgres PGVector Store.
How it runs
Trigger: When a chat message arrives.
- Fetch Airline URLs (Google Sheets): uses Google Sheets
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Scrape Airline Webpage (HTTP Request): calls an HTTP API (POST)
- Extract Info with LLM (Basic LLM Chain): sends a prompt to an LLM, with model: Chat Model
- Wait: pauses before continuing
- Store Extracted Info (Google Sheets): update
- Save to Vector DB (Postgres PGVector Store): stores documents in the Postgres PGVector Store vector store, with embeddings: Generate Embeddings; document loader: Prepare Text for Vector DB
- Wait: waits 15 seconds
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 (11)
- Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Google Sheets
n8n-nodes-base.googleSheets - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - HTTP Request
n8n-nodes-base.httpRequest - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Ollama Chat Model
@n8n/n8n-nodes-langchain.lmChatOllama - Wait
n8n-nodes-base.wait - Embeddings Ollama
@n8n/n8n-nodes-langchain.embeddingsOllama - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Token Splitter
@n8n/n8n-nodes-langchain.textSplitterTokenSplitter - Postgres PGVector Store
@n8n/n8n-nodes-langchain.vectorStorePGVector
From the author
Overview This workflow retrieves airline web check-in URLs from Google Sheets, scrapes their content, employs an LLM to generate structured JSON data, refreshes the sheet, creates embeddings, and saves them in a Postgres vector DB for future semantic searches…