Process documents with recursive chunking using Google Drive, OpenAI & Gemini RAG

by Mohsin Ali · 3,431 views · created 2025-07-01 · Internal Wiki, AI RAG

What this workflow does

This AI workflow has 23 nodes and runs on Google Drive events (file created) (plus 1 other trigger). Along the way it connects Google Drive, OpenAI Chat Model, Embeddings OpenAI and Supabase Vector Store and 3 more. It also calls etvncxazsxflierkgyge.supabase.co over HTTP.

How it runs

Trigger: On Google Drive events (file created) (plus 1 other trigger).

1. Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
2. OpenAI: analyze (image)
3. File info (Edit Fields (Set)): sets 4 fields: File_id, File_Type, File_url…
4. AI Agent: runs an AI agent, with model: Google Gemini Chat Model; 1 tool (SupaBase Query)
5. Google Drive: download
6. Switch: routes items into 2 branches
7. Extract from PDF (Extract from File): extracts data from a file (pdf)
8. Extract from TEXT (Extract from File): extracts data from a file (text)
9. PDF to DATA (Edit Fields (Set)): sets or maps fields
10. Document Data (Edit Fields (Set)): sets or maps fields

…plus 5 more steps. See the full node list below.

Services it uses

Google DriveOpenAI Chat ModelEmbeddings OpenAISupabase Vector StoreGoogle Gemini Chat ModelOpenAIHTTP Request

HTTP calls to: etvncxazsxflierkgyge.supabase.co

Before you upgrade to n8n 3.0

Nodes used (20)

• Google Drive Triggern8n-nodes-base.googleDriveTrigger
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Google Driven8n-nodes-base.googleDrive
• Switchn8n-nodes-base.switch
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Summarizen8n-nodes-base.summarize
• Embeddings OpenAI@n8n/n8n-nodes-langchain.embeddingsOpenAi
• Supabase Vector Store@n8n/n8n-nodes-langchain.vectorStoreSupabase
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Character Text Splitter@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter
• AI Agent@n8n/n8n-nodes-langchain.agent
• Manual Triggern8n-nodes-base.manualTrigger
• Google Gemini Chat Model@n8n/n8n-nodes-langchain.lmChatGoogleGemini
• OpenAI@n8n/n8n-nodes-langchain.openAi
• Edit Fields (Set)n8n-nodes-base.set
• Extract from Filen8n-nodes-base.extractFromFile
• Coden8n-nodes-base.code
• Split Outn8n-nodes-base.splitOut
• Http Request Tooln8n-nodes-base.httpRequestTool

From the author

1. Document Ingestion & Processing Google Drive Trigger monitors for new files → Loop Over Items processes each file → File Info extracts metadata → Google Drive downloads the actual content → Switch routes to appropriate extractors (PDF or TEXT) based on…

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