Chat with Google Drive documents using Pinecone and OpenAI RAG
Needs changesWhat this workflow does
This AI workflow has 30 nodes and runs manually, when you click “Execute workflow” (plus 3 other triggers). Along the way it connects Pinecone Vector Store, Vector Store Question Answer, Google Drive and OpenAI Chat Model and 2 more. It also calls open-ai-3072-71cwk85.svc.aped-4627-b74a.pinecone.io over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 3 other triggers).
- Pinecone – Delete All Vectors (HTTP Request): calls open-ai-3072-71cwk85.svc.aped-4627-b74a.pinecone.io (POST)
- Filter: keeps only the items that match a condition
- Filter: keeps only the items that match a condition
- Documents finder (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (Vector Store Tool); memory: Window Buffer Memory
- Search files and folders (Google Drive): work with file folder
- If: checks a condition and branches into true / false
- If: checks a condition and branches into true / false
- Loop Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Download File From Google Drive (Google Drive): download
- Send a message (Gmail): uses Gmail
…plus 4 more steps. See the full node list below.
Services it uses
HTTP calls to: open-ai-3072-71cwk85.svc.aped-4627-b74a.pinecone.io
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Documents finder (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Documents finder (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (18)
- Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - Google Drive
n8n-nodes-base.googleDrive - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Manual Trigger
n8n-nodes-base.manualTrigger - Wait
n8n-nodes-base.wait - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Gmail
n8n-nodes-base.gmail - HTTP Request
n8n-nodes-base.httpRequest - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - AI Agent
@n8n/n8n-nodes-langchain.agent - Filter
n8n-nodes-base.filter - If
n8n-nodes-base.if
From the author
Google Drive → Pinecone RAG Chatbot (Auto-Sync & Query) This n8n workflow implements a fully automated Retrieval-Augmented Generation (RAG) pipeline powered by Google Drive, OpenAI embeddings, and Pinecone. It continuously keeps a vector database in sync with…