Build and update RAG system with Google Drive, Qdrant, and Gemini Chat

by Davide Boizza ✓ · 8,612 views · created 2025-06-23 · Internal Wiki, AI RAG

What this workflow does

This AI workflow has 24 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Embeddings OpenAI, Qdrant Vector Store, Google Drive and Google Gemini Chat Model. It also calls qdranturl over HTTP.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).

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

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

Services it uses

Embeddings OpenAIQdrant Vector StoreGoogle DriveGoogle Gemini Chat Model

HTTP calls to: qdranturl

Before you upgrade to n8n 3.0

Nodes used (14)

• Manual Triggern8n-nodes-base.manualTrigger
• Embeddings OpenAI@n8n/n8n-nodes-langchain.embeddingsOpenAi
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Qdrant Vector Store@n8n/n8n-nodes-langchain.vectorStoreQdrant
• HTTP Requestn8n-nodes-base.httpRequest
• Recursive Character Text Splitter@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Waitn8n-nodes-base.wait
• Google Driven8n-nodes-base.googleDrive
• 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
• Edit Fields (Set)n8n-nodes-base.set

From the author

This workflow automates the creation and management of a Retrieval-Augmented Generation (RAG) system using Qdrant as a vector store and Google Drive as the document source. It enables full or incremental updates to documents in the Qdrant vector database and…

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