Build a RAG system for PDF documents with Google Drive, Unstructured, and OpenAI
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 15 nodes and runs on Google Drive events (file created) (plus 1 other trigger). Along the way it connects OpenAI Chat Model, Pinecone Vector Store, Embeddings OpenAI and Google Drive. It also calls unstructured:8000 and api.openai.com over HTTP.
How it runs
Trigger: On Google Drive events (file created) (plus 1 other trigger).
- Google Drive: download
- Question & Answer (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (Pinecone Vector Store); memory: Simple Memory
- Unstructured Extract (HTTP Request): calls unstructured:8000 (POST)
- Map Data (Code): runs custom JavaScript code
- Pack (Code): runs custom JavaScript code
- HTTP OpenAI Embeddings (HTTP Request): calls api.openai.com (POST)
- Re-expand (Code): runs custom JavaScript code
- Prepare Data for Upsert (Edit Fields (Set)): sets 2 fields: id, metadata
- Pinecone Upsert (HTTP Request): calls an HTTP API (POST)
Services it uses
HTTP calls to: unstructured:8000, api.openai.com
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Question & Answer (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Question & Answer (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (11)
- HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Edit Fields (Set)
n8n-nodes-base.set - Google Drive
n8n-nodes-base.googleDrive - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger
From the author
This template monitors a Google Drive folder, converts PDF documents into clean text chunks with Unstructured, generates OpenAI embeddings, and upserts vectors into Pinecone. It’s a practical, production-ready starting point for Retrieval-Augmented Generation…