Build a RAG system with automatic citations using Qdrant, Gemini & OpenAI

by Davide Boizza ✓ · 3,437 views · created 2025-06-18 · 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 Gemini Chat Model and Google Drive. 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. chatInput (Edit Fields (Set)): sets 1 field: chatInput
3. Get folder (Google Drive): work with file folder
4. Question and Answer Chain: answers questions over your documents (RAG), with model: Google Gemini Chat Model; retriever: Vector Store Retriever
5. Retrive sources (Qdrant Vector Store): searches the Qdrant vector store, with embeddings: Embeddings OpenAI
6. Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
7. Merge: merges the data from its input branches
8. Aggregate: combines items into one
9. Get file (Google Drive): download
10. Response (Code): runs custom JavaScript code

…plus 4 more steps. See the full node list below.

Services it uses

Embeddings OpenAIQdrant Vector StoreGoogle Gemini Chat ModelGoogle Drive

HTTP calls to: qdranturl

Before you upgrade to n8n 3.0

Nodes used (17)

• 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
• 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
• Mergen8n-nodes-base.merge
• Aggregaten8n-nodes-base.aggregate
• Google Driven8n-nodes-base.googleDrive
• Edit Fields (Set)n8n-nodes-base.set
• Coden8n-nodes-base.code

From the author

This workflow implements a Retrieval-Augmented Generation (RAG) system that: Stores vectorized documents in Qdrant, Retrieves relevant content based on user input, Generates AI answers using Google Gemini, Automatically cites the document sources (from Google…

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