This workflow follows the Documentdefaultdataloader → Google Drive 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 →
{
"nodes": [
{
"parameters": {
"content": "## \ud83d\ude80 Ingestion Phase (Data Processing)\n**Goal:** Pull files, read content, and store as vector embeddings.\n\n\ud83d\udc68\u200d\ud83d\udcbb **Designed by:** Yousef El-Sherbiny\n\ud83c\udf10 **Contact:** https://yousefautomates.pages.dev\n\n\ud83d\udcda **What is RAG?**\nRetrieval-Augmented Generation combines document retrieval with AI generation for accurate, context-aware responses.",
"height": 280,
"width": 420,
"color": 7
},
"type": "n8n-nodes-base.stickyNote",
"position": [
-144,
-256
],
"typeVersion": 1,
"id": "b6beb3c7-304f-497c-8270-6084b75f03c1",
"name": "Sticky Note"
},
{
"parameters": {
"content": "\u26a0\ufe0f **Important Notice:**\nThis workflow is **for educational purposes only** to simplify RAG concepts for beginners.\n\n\ud83d\udee0\ufe0f **Needs Enhancement:** To be production-ready, additional improvements are required (will be covered in advanced tutorials).\n\n\u2705 **Current Status:** Fully functional for learning RAG fundamentals and basic implementation.\n\n\ud83d\udd10 **Security Note:** Ensure your credentials are properly configured for Google Drive, Supabase, and HuggingFace.",
"height": 284,
"width": 420,
"color": 6
},
"type": "n8n-nodes-base.stickyNote",
"position": [
-208,
80
],
"typeVersion": 1,
"id": "e87fd178-b9fc-4e1e-a973-4c34e115878d",
"name": "Sticky Note1"
},
{
"parameters": {
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
},
"triggerOn": "specificFolder",
"folderToWatch": {
"__rl": true,
"value": "19EIou_ZCabdAaYU39qUy9_jqt5wqcmG6",
"mode": "list",
"cachedResultName": "RAG 2",
"cachedResultUrl": "https://drive.google.com/drive/folders/19EIou_ZCabdAaYU39qUy9_jqt5wqcmG6"
},
"event": "fileCreated",
"options": {}
},
"type": "n8n-nodes-base.googleDriveTrigger",
"typeVersion": 1,
"position": [
-160,
416
],
"id": "f17dfe27-5b95-4777-bccd-0789d25f98f4",
"name": "Google Drive Trigger",
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "download",
"fileId": {
"__rl": true,
"value": "={{ $json.id }}",
"mode": "id"
},
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
96,
416
],
"id": "09dbae3c-a380-47f7-bd65-23e12c74816d",
"name": "Download File",
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "pdf",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1.1,
"position": [
336,
416
],
"id": "12ff235f-fbdf-4f2f-ae05-cda6170f60fc",
"name": "Extract Text from PDF"
},
{
"parameters": {
"mode": "insert",
"tableName": {
"__rl": true,
"value": "documents",
"mode": "list",
"cachedResultName": "documents"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"typeVersion": 1.3,
"position": [
576,
416
],
"id": "3167ff1b-79d5-4658-98c1-bfbd00e124aa",
"name": "Supabase Vector Store",
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"textSplittingMode": "custom",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1.1,
"position": [
800,
560
],
"id": "5351f9bc-df0b-4802-9c43-94b24b25385a",
"name": "Document Loader"
},
{
"parameters": {
"chunkSize": 400,
"chunkOverlap": 50,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"typeVersion": 1,
"position": [
928,
720
],
"id": "b3333c0b-de6c-405e-88bc-cf159bee2990",
"name": "Text Splitter"
},
{
"parameters": {
"modelName": "intfloat/multilingual-e5-large",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.embeddingsHuggingFaceInference",
"typeVersion": 1,
"position": [
416,
768
],
"id": "c992150d-471a-498c-8332-905f1716d81b",
"name": "Embedding Model (HuggingFace)",
"credentials": {
"huggingFaceApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"content": "### 1\ufe0f\u20e3 File Monitoring & Download\n**Function:** Monitors a Google Drive folder for new files.\n\n**Process:**\n- Checks every minute for new uploads\n- Triggers automatically when a file is added\n- Downloads the file for processing\n\n**Supported:** PDF files (can be extended to other formats)",
"height": 296,
"width": 280,
"color": 4
},
"type": "n8n-nodes-base.stickyNote",
"position": [
-144,
592
],
"typeVersion": 1,
"id": "9b89f558-9ebd-45bc-b9f2-76d099b6a8a9",
"name": "Sticky Note2"
},
{
"parameters": {
"content": "### 2\ufe0f\u20e3 Text Extraction\n**Function:** Converts PDF files into readable text.\n\n**Process:**\n- Extracts all text content from PDF\n- Maintains document structure\n- Prepares data for AI processing\n\n**Output:** Raw text ready for chunking",
"height": 260,
"width": 260,
"color": 3
},
"type": "n8n-nodes-base.stickyNote",
"position": [
272,
96
],
"typeVersion": 1,
"id": "a98276e8-ebae-4f91-9d06-e77a8e55d902",
"name": "Sticky Note3"
},
{
"parameters": {
"content": "### 3\ufe0f\u20e3 Vector Storage\n**Function:** Converts text to embeddings and stores in database.\n\n**Process:**\n- Text is split into 400-character chunks (50 char overlap)\n- Each chunk is converted to a vector embedding\n- Vectors are stored in Supabase for semantic search\n\n**Why Vectors?** Enables AI to find relevant content based on meaning, not just keywords.",
"height": 316,
"width": 340,
"color": 5
},
"type": "n8n-nodes-base.stickyNote",
"position": [
608,
32
],
"typeVersion": 1,
"id": "ad02a70e-7653-46c1-8288-b1e1bf09d357",
"name": "Sticky Note4"
},
{
"parameters": {
"content": "### \ud83d\udd27 Configuration Notes\n\n**Text Splitter:**\n- Chunk Size: 400 chars (balanced for context)\n- Overlap: 50 chars (prevents context loss)\n\n**Embedding Model:**\n- intfloat/multilingual-e5-large\n- Supports multiple languages including Arabic\n\n**Customization:** Adjust chunk size based on your document type and use case.",
"height": 332,
"width": 300,
"color": 2
},
"type": "n8n-nodes-base.stickyNote",
"position": [
528,
688
],
"typeVersion": 1,
"id": "a955e02c-cc92-40ea-8845-a88c3b5fce83",
"name": "Sticky Note5"
},
{
"parameters": {
"content": "### \ud83d\udcca Workflow Summary\n\n**Input:** PDF files uploaded to Google Drive\n**Output:** Vector embeddings stored in Supabase\n**Next Step:** Part 2 - Retrieval & Query\n\n**Prerequisites:**\n\u2705 Google Drive API access\n\u2705 Supabase database with pgvector\n\u2705 HuggingFace API key",
"height": 232,
"width": 320
},
"type": "n8n-nodes-base.stickyNote",
"position": [
304,
-256
],
"typeVersion": 1,
"id": "29361c05-cd8d-4079-81a1-374e7a845a68",
"name": "Sticky Note6"
},
{
"parameters": {
"content": "## \ud83c\udfa5 Resources & Documentation\n\n### \ud83d\udcf9 Video Tutorial\n**Watch the complete workflow build process:**\n\n\ud83d\udd17 **YouTube:** https://youtu.be/a2unzl4mNtA\n\n**What's covered:**\n\u2705 RAG System fundamentals\n\u2705 Step-by-step implementation\n\u2705 Best practices & optimization\n\n---\n\n### \ud83d\udcbe SQL Database Setup\n**Supabase database configuration code:**\n\n\ud83d\udd17 **GitHub Gist:** https://gist.github.com/YousefAutomates/25962e215fc54a8aa9c0231adc770078\n\n**Setup Required:**\n\u2022 Create Supabase project\n\u2022 Enable pgvector extension\n\u2022 Run the SQL script to create tables\n\u2022 Configure credentials in n8n\n\n\ud83d\udca1 **Important:** Execute the SQL script before running this workflow!",
"height": 720,
"width": 544
},
"type": "n8n-nodes-base.stickyNote",
"position": [
1120,
-256
],
"typeVersion": 1,
"id": "40af84e8-0fce-4a26-8642-bb816202f3b8",
"name": "Sticky Note7"
}
],
"connections": {
"Google Drive Trigger": {
"main": [
[
{
"node": "Download File",
"type": "main",
"index": 0
}
]
]
},
"Download File": {
"main": [
[
{
"node": "Extract Text from PDF",
"type": "main",
"index": 0
}
]
]
},
"Extract Text from PDF": {
"main": [
[
{
"node": "Supabase Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Document Loader": {
"ai_document": [
[
{
"node": "Supabase Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Document Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Embedding Model (HuggingFace)": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store",
"type": "ai_embedding",
"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.
googleDriveOAuth2ApihuggingFaceApisupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
N8N-Rag-Ingestion-Workflow. Uses googleDriveTrigger, googleDrive, vectorStoreSupabase, documentDefaultDataLoader. Event-driven trigger; 15 nodes.
Source: https://gist.github.com/YousefAutomates/ff9c006a0d377d58c704e444064accd1 — 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.
RAG_Ingest. Uses httpRequest, vectorStoreSupabase, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter. Event-driven trigger; 73 nodes.
HTTP Request, Supabase Vector Store, Document Default Data Loader +4
Chat with docs - 5minAI New version. Uses httpRequest, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Event-driven trigger; 62 nodes.
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +10
I prepared a detailed guide that illustrates the entire process of building an AI agent using Supabase and Google Drive within N8N workflows.
HTTP Request, Document Default Data Loader, Text Splitter Recursive Character Text Splitter +10
Auto repost job with RAG is a workflow designed to automatically extract, process, and publish job listings from monitored sources using Google Drive, OpenAI, Supabase, and WordPress. This integration
Google Drive, Supabase Vector Store, OpenAI Embeddings +12
Automatically extract job listings from any website URL, format them with AI, and publish directly to WordPress. Just send a URL via Telegram, and watch as the workflow scrapes the job details, enhanc
Google Drive, Supabase Vector Store, OpenAI Embeddings +8