This workflow follows the Chainretrievalqa → Retrievervectorstore recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "01730710-e299-4e66-93e9-6079fdf9b8b7",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
2120,
0
],
"parameters": {
"color": 6,
"width": 903.0896125323785,
"height": 733.5099670584011,
"content": "## Step 2: Setup the Q&A \n### The incoming message from the webhook is queried from the Supabase Vector Store. The response is provided in the response webhook. "
},
"typeVersion": 1
},
{
"id": "66aed89e-fd72-4067-82bf-d480be27e5d6",
"name": "When clicking \"Execute Workflow\"",
"type": "n8n-nodes-base.manualTrigger",
"position": [
840,
140
],
"parameters": {},
"typeVersion": 1
},
{
"id": "9dc8f2a7-eeff-4a35-be52-05c42b71eee4",
"name": "Google Drive",
"type": "n8n-nodes-base.googleDrive",
"position": [
1140,
140
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "list",
"value": "1LZezppYrWpMStr4qJXtoIX-Dwzvgehll",
"cachedResultUrl": "https://drive.google.com/file/d/1LZezppYrWpMStr4qJXtoIX-Dwzvgehll/view?usp=drivesdk",
"cachedResultName": "crowdstrike.pdf"
},
"options": {},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "1dd3d3fd-6c2e-4e23-9c82-b0d07b199de3",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
1100,
0
],
"parameters": {
"color": 6,
"width": 772.0680602743597,
"height": 732.3675002130781,
"content": "## Step 1: Upserting the PDF\n### Fetch file from Google Drive, split it into chunks and insert into Supabase index\n\n"
},
"typeVersion": 1
},
{
"id": "4796124f-bc12-4353-b7ea-ec8cd7653e68",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
0
],
"parameters": {
"color": 6,
"width": 710.9124489067698,
"height": 726.4452519516944,
"content": "## Start here: Step-by Step Youtube Tutorial :star:\n\n[](https://www.youtube.com/watch?v=pMvizUx5n1g)\n"
},
"typeVersion": 1
},
{
"id": "1e2ecc88-c8c7-4687-a2a1-b20b0da9b772",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
1400,
320
],
"parameters": {
"options": {
"splitPages": true
},
"dataType": "binary"
},
"typeVersion": 1
},
{
"id": "6dd8545d-df8c-49ff-acf6-f8c150723ee8",
"name": "Recursive Character Text Splitter1",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1400,
460
],
"parameters": {
"options": {},
"chunkSize": 3000,
"chunkOverlap": 200
},
"typeVersion": 1
},
{
"id": "6899e2d6-965a-40cd-a34f-a61de8fd32ef",
"name": "Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
1480,
140
],
"parameters": {
"mode": "insert",
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "crowd"
}
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "6136c6fb-3d20-44a7-ab00-6c5671bafa10",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"disabled": true,
"position": [
2180,
120
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "c970f654-4c79-4637-bec0-73f79a01ab59",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"position": [
2180,
320
],
"parameters": {
"path": "19f5499a-3083-4783-93a0-e8ed76a9f742",
"options": {},
"httpMethod": "POST",
"responseMode": "responseNode"
},
"typeVersion": 2
},
{
"id": "e05e9046-de17-4ca1-b1ac-2502ee123e5f",
"name": "Retrieval QA Chain",
"type": "@n8n/n8n-nodes-langchain.chainRetrievalQa",
"position": [
2420,
120
],
"parameters": {
"text": "={{ $json.chatInput || $json.body.input }}",
"options": {},
"promptType": "define"
},
"typeVersion": 1.5
},
{
"id": "ecf0d248-a8a9-45ed-8786-8864547f79b6",
"name": "Vector Store Retriever",
"type": "@n8n/n8n-nodes-langchain.retrieverVectorStore",
"position": [
2580,
320
],
"parameters": {
"topK": 5
},
"typeVersion": 1
},
{
"id": "4fb1d8ac-bc6f-4f99-965f-7d38ea0680e0",
"name": "Qdrant Vector Store1",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
2540,
460
],
"parameters": {
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "={{ $json.body.company }}"
}
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "66868422-39c9-4e76-99b9-a77bb613b248",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
2420,
340
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "f290f809-3b4e-42e3-bfb5-d505566d9275",
"name": "Embeddings OpenAI1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
2520,
580
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "c360f7b3-2ae4-4ebd-85ca-f64c3966e65d",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
1700,
320
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "9223d119-b5a7-40d4-b8da-f85951b52bde",
"name": "Respond to Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
2840,
120
],
"parameters": {
"options": {},
"respondWith": "text",
"responseBody": "={{ $json.response.text }}"
},
"typeVersion": 1.1
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "Retrieval QA Chain",
"type": "main",
"index": 0
}
]
]
},
"Google Drive": {
"main": [
[
{
"node": "Qdrant Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Retrieval QA Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings OpenAI1": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Retrieval QA Chain": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Qdrant Vector Store1": {
"ai_vectorStore": [
[
{
"node": "Vector Store Retriever",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Vector Store Retriever": {
"ai_retriever": [
[
{
"node": "Retrieval QA Chain",
"type": "ai_retriever",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Retrieval QA Chain",
"type": "main",
"index": 0
}
]
]
},
"When clicking \"Execute Workflow\"": {
"main": [
[
{
"node": "Google Drive",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter1": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
googleDriveOAuth2ApiopenAiApiqdrantApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow enables seamless retrieval of information from your Google Drive documents by processing queries through an AI-powered system, delivering accurate answers without manual searching. It's ideal for knowledge workers, researchers, or teams managing extensive files who need quick insights from stored content. The key step involves splitting documents into chunks, embedding them into a Qdrant vector store, and using a retrieval chain to generate context-aware responses via a chat interface.
Use this when handling frequent queries on large document sets in Google Drive, such as summarising reports or extracting facts for client consultations. Avoid it for real-time data sources or non-text files like images, where specialised tools perform better. Common variations include swapping Qdrant for another vector store or adding filters for multi-folder access.
About this workflow
Webhook Respondtowebhook. Uses stickyNote, manualTrigger, googleDrive, documentDefaultDataLoader. Event-driven trigger; 17 nodes.
Source: https://github.com/Zie619/n8n-workflows — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This comprehensive workflow bundle is designed as a powerful starter kit, enabling you to build a multi-functional AI assistant on Telegram. It seamlessly integrates AI-powered voice interactions, an
Agent IA Projet Client. Uses executeWorkflowTrigger, lmChatOpenAi, toolWorkflow, vectorStoreQdrant. Event-driven trigger; 79 nodes.
Chat with docs - 5minAI New version. Uses httpRequest, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Event-driven trigger; 62 nodes.
I prepared a detailed guide that illustrates the entire process of building an AI agent using Supabase and Google Drive within N8N workflows.
RAG AI Agent Template V5. Uses lmChatOpenAi, documentDefaultDataLoader, embeddingsOpenAi, googleDrive. Event-driven trigger; 56 nodes.