Build a self-updating RAG system with OpenAI, Qdrant and Google Drive

by Davide Boizza ✓ · 1,576 views · created 2025-08-20 · AI RAG, Multimodal AI

What this workflow does

This AI workflow has 25 nodes and runs manually, when you click “Execute workflow” (plus 2 other triggers). Along the way it connects Embeddings OpenAI, Google Drive, Qdrant Vector Store and Google Gemini Chat Model. It also calls collections over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 2 other triggers).

1. Create collection (HTTP Request): calls collections (PUT)
2. Clear collection (HTTP Request): calls an HTTP API (POST)
3. Set file_id (Edit Fields (Set)): sets 1 field: file_id
4. Question and Answer Chain: answers questions over your documents (RAG), with model: Google Gemini Chat Model; retriever: Vector Store Retriever
5. Search files (Google Drive): work with file folder
6. Delete points by file_id (HTTP Request): calls an HTTP API (POST)
7. Get file (Google Drive): download
8. Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
9. Update file (Qdrant Vector Store): stores documents in the Qdrant vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
10. Get files (Google Drive): download

…plus 2 more steps. See the full node list below.

Services it uses

Embeddings OpenAIGoogle DriveQdrant Vector StoreGoogle Gemini Chat Model

HTTP calls to: collections

Before you upgrade to n8n 3.0

Nodes used (15)

• Manual Triggern8n-nodes-base.manualTrigger
• Embeddings OpenAI@n8n/n8n-nodes-langchain.embeddingsOpenAi
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• HTTP Requestn8n-nodes-base.httpRequest
• Recursive Character Text Splitter@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Edit Fields (Set)n8n-nodes-base.set
• Google Driven8n-nodes-base.googleDrive
• Waitn8n-nodes-base.wait
• Qdrant Vector Store@n8n/n8n-nodes-langchain.vectorStoreQdrant
• Chat Trigger@n8n/n8n-nodes-langchain.chatTrigger
• Question and Answer Chain@n8n/n8n-nodes-langchain.chainRetrievalQa
• Google Gemini Chat Model@n8n/n8n-nodes-langchain.lmChatGoogleGemini
• Vector Store Retriever@n8n/n8n-nodes-langchain.retrieverVectorStore
• Google Drive Triggern8n-nodes-base.googleDriveTrigger

From the author

This workflow implements a Retrieval-Augmented Generation (RAG) system that integrates Google Drive and Qdrant. This setup creates a powerful, self-updating knowledge base that provides accurate, context-aware answers to user queries. --- Key Advantages…

View the original on n8n.io → Check your own copy