Build a document QA system with RAG using Milvus, Cohere, and OpenAI for Google Drive
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 13 nodes and runs on Google Drive events (file created) (plus 1 other trigger). Along the way it connects Embeddings Cohere, Google Drive, Milvus Vector Store and OpenAI Chat Model.
How it runs
Trigger: On Google Drive events (file created) (plus 1 other trigger).
- Download New (Google Drive): download
- RAG Agent (AI Agent): runs an AI agent, with model: OpenAI 4o; 1 tool (Retrieve from Milvus); memory: Memory
- Extract from File: extracts data from a file (pdf)
- Insert into Milvus (Milvus Vector Store): stores documents in the Milvus vector store, with embeddings: Embeddings Cohere; document loader: Default Data Loader
Services it uses
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 RAG Agent (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) RAG Agent (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)
- Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Embeddings Cohere
@n8n/n8n-nodes-langchain.embeddingsCohere - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - Google Drive
n8n-nodes-base.googleDrive - Milvus Vector Store
@n8n/n8n-nodes-langchain.vectorStoreMilvus - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Extract from File
n8n-nodes-base.extractFromFile
From the author
Template Description This template creates a powerful Retrieval Augmented Generation (RAG) AI agent workflow in n8n. It monitors a specified Google Drive folder for new PDF files, extracts their content, generates vector embeddings using Cohere, and stores…