🧬 RAG & KnowledgeIntermediate🧠 AI-powered🧬 RAG

Google Drive Files Workflow

A 26-step rag & knowledge automation, triggered by chat, connecting Google Drive, OpenAI Embeddings, HTTP / REST API, OpenAI (LLM), with built-in AI reasoning.

⬇ Download workflow JSON
💡

What this does for your business

In plain terms: this turns your documents into a smart Q&A brain. It reads and remembers your content, then answers questions accurately using Google Drive, OpenAI Embeddings, OpenAI (LLM) — great for support and internal knowledge.

26
Nodes
4
Integrations
24
Connections
Chat
Trigger

🚀 Deploy this workflow

Deploy this automation in minutes

Log in and we'll walk you through every key step by step, then deploy it for you.

Get started free Log in

🏗️ Architecture diagram

The real node graph exported from n8n — triggers (green), AI nodes (violet), services and logic — laid out as they run.

File CreatedgoogleDriveTriggerFile UpdatedgoogleDriveTrigger🗂️Download filegoogleDriveSwitch- By TypeswitchExtract from FileextractFromFileQdrant Vector StorevectorStoreQdrant🧬Embeddings OpenAIembeddingsOpenAi🌐Qdrant – Create Colle…httpRequestDefault Data LoaderdocumentDefaultData…Doc ShapesetWhen chat message rec…chatTrigger🌐Create the - Qdrant I…httpRequest🧠AI AgentagentQdrant Vector Store1vectorStoreQdrant🧬Embeddings OpenAI2embeddingsOpenAi🧠OpenAI Chat ModellmChatOpenAi🧠Simple MemorymemoryBufferWindowExtract Document TextextractFromFileTXT – Pull TextcodeTXT – Add MetadatacodePDF – Pull TextcodePDF – Add MetadatacodeLoop Over ItemssplitInBatchesFinishednoOpRecursive Character T…textSplitterRecursi…🧠ThinktoolThink

⚙️ How it works

  1. File Created · googleDriveTrigger
  2. File Updated · googleDriveTrigger
  3. Embeddings OpenAI · embeddingsOpenAi
  4. Qdrant – Create Collection · httpRequest
  5. When chat message received · chatTrigger
  6. Create the - Qdrant Index · httpRequest
  7. Embeddings OpenAI2 · embeddingsOpenAi
  8. OpenAI Chat Model · lmChatOpenAi
  9. Simple Memory · memoryBufferWindow
  10. Recursive Character Text Splitter · textSplitterRecursiveCharacterTextSplitter
  11. Think · toolThink
  12. Loop Over Items · splitInBatches
  13. Qdrant Vector Store · vectorStoreQdrant
  14. AI Agent · agent

💼 Business analysis

🎯

Business use case

Builds a retrieval-augmented knowledge system: content is embedded into a vector store and served back as grounded, citeable answers. Ideal for support deflection, internal knowledge bases, and AI assistants that must stay factual.

📈

Market need

Generic chatbots hallucinate; companies need answers grounded in their own documents. RAG is the proven pattern, and a working pipeline is scarce and valuable.

💰

Market value

RAG assistant implementations typically run $5,000–$20,000 bespoke. Packaged, it underpins support-deflection tools that sell for $99–$999/mo.

🧩 Integrations & stack

🗂️Google Drive🧬OpenAI Embeddings🌐HTTP / REST API🧠OpenAI (LLM)
Node typesgoogleDriveTrigger, googleDrive, switch, extractFromFile, vectorStoreQdrant, embeddingsOpenAi, httpRequest, documentDefaultDataLoader, set, chatTrigger, agent, lmChatOpenAi, memoryBufferWindow, code, splitInBatches, noOp, textSplitterRecursiveCharacterTextSplitter, toolThinkWorkflow ID4k4ZWc76x1nF67KT
⬇ Download workflow JSON ← Back to library