Auto-update knowledge base with Drive, LlamaIndex & Azure OpenAI embeddings
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 10 nodes and runs on Google Drive events (specific file). Along the way it connects Embeddings Azure OpenAI and Google Drive. It also calls api.cloud.llamaindex.ai over HTTP.
How it runs
Trigger: On Google Drive events (specific file).
- Download Knowledge Document (Google Drive): download
- Parse Document via LlamaIndex (HTTP Request): calls api.cloud.llamaindex.ai (POST)
- Monitor Document Processing (HTTP Request): calls an HTTP API
- Check Parsing Completion (If): checks a condition and branches into true / false
- Retrieve Parsed Content (HTTP Request): calls an HTTP API
- Wait: waits 10 seconds
- Insert Data to Store (Simple Vector Store): stores documents in the Simple vector store, with embeddings: Embeddings Azure OpenAI; document loader: Default Data Loader
Services it uses
HTTP calls to: api.cloud.llamaindex.ai
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 (8)
- Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Embeddings Azure OpenAI
@n8n/n8n-nodes-langchain.embeddingsAzureOpenAi - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - If
n8n-nodes-base.if - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - Google Drive
n8n-nodes-base.googleDrive - HTTP Request
n8n-nodes-base.httpRequest - Wait
n8n-nodes-base.wait
From the author
This Workflow auto-ingests Google Drive documents, parses them with LlamaIndex, and stores Azure OpenAI embeddings in an in-memory vector store—cutting manual update time from ~30 minutes to under 2 minutes per doc. Last updated: September 2026. Why Use This…