Abdul Mir This workflow corresponds to n8n.io template #6538 — we link there as the canonical source.
This workflow follows the Agent → Documentdefaultdataloader 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": "c9437f3c-edbc-431c-be65-bc485d9fd6ad",
"name": "Set ID",
"type": "n8n-nodes-base.set",
"position": [
860,
760
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "e556566e-20a1-48b4-b01e-197a402b5a5f",
"name": "id",
"type": "string",
"value": "={{ $json.id }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "fc3b2696-d0c1-40e4-a13b-5d274b0b8c69",
"name": "Supabase Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"position": [
1600,
760
],
"parameters": {
"mode": "insert",
"options": {
"queryName": "match_documents"
},
"tableName": {
"__rl": true,
"mode": "list",
"value": "documents",
"cachedResultName": "documents"
}
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "71b61728-b87c-40f3-850b-81af6d544b75",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
1740,
980
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "=file_id",
"value": "={{ $('Set ID').item.json.id }}"
}
]
}
}
},
"typeVersion": 1
},
{
"id": "36fdd0a5-b95c-4fc3-9427-e67de0f3985f",
"name": "Recursive Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1840,
1140
],
"parameters": {
"options": {},
"chunkSize": 500,
"chunkOverlap": 100
},
"typeVersion": 1
},
{
"id": "66dd34df-763f-4497-bd73-b2dd78890eb4",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
1560,
980
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "3623a178-af67-4f07-b1d6-90ac07857f28",
"name": "New File",
"type": "n8n-nodes-base.googleDriveTrigger",
"position": [
560,
760
],
"parameters": {
"event": "fileCreated",
"options": {},
"pollTimes": {
"item": [
{}
]
},
"triggerOn": "specificFolder",
"folderToWatch": {
"__rl": true,
"mode": "list",
"value": "1UHQhCrwZg_ZEzBIKv4LR_RWtAyHbxZsg",
"cachedResultUrl": "https://drive.google.com/drive/folders/1UHQhCrwZg_ZEzBIKv4LR_RWtAyHbxZsg",
"cachedResultName": "Marketing Ladder Knowledge Base"
}
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "5a9c99b2-2876-4fd3-82e1-9212303151ae",
"name": "Download File",
"type": "n8n-nodes-base.googleDrive",
"position": [
1100,
760
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.id }}"
},
"options": {
"googleFileConversion": {
"conversion": {
"docsToFormat": "text/plain"
}
}
},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "2493e003-7c9e-4a98-8148-114abd2899ad",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
500,
560
],
"parameters": {
"color": 4,
"width": 820,
"height": 80,
"content": "# Upload New File into Knowledge Base\n\n"
},
"typeVersion": 1
},
{
"id": "3d7f646d-0de0-44da-8cab-568cfa3ead02",
"name": "Extract from File",
"type": "n8n-nodes-base.extractFromFile",
"position": [
1280,
760
],
"parameters": {
"options": {},
"operation": "text"
},
"typeVersion": 1
},
{
"id": "8b949a8f-5dee-4c48-86fa-dc87cdd83198",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
800,
680
],
"parameters": {
"color": 5,
"height": 260,
"content": "## Fix Formatting\n"
},
"typeVersion": 1
},
{
"id": "2ce675ef-7791-4fe4-86d4-0eeabd827531",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
1060,
680
],
"parameters": {
"color": 5,
"width": 420,
"height": 260,
"content": "## Extract File Text\n\n"
},
"typeVersion": 1
},
{
"id": "1d23677f-e268-4f66-8170-a5c28b4049b5",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
1500,
680
],
"parameters": {
"color": 5,
"width": 560,
"height": 580,
"content": "## Update Vector Database\n\n"
},
"typeVersion": 1
},
{
"id": "f29a335e-e6a5-4a75-8158-0c83e69e25bb",
"name": "File Updated",
"type": "n8n-nodes-base.googleDriveTrigger",
"position": [
560,
1500
],
"parameters": {
"event": "fileUpdated",
"options": {},
"pollTimes": {
"item": [
{}
]
},
"triggerOn": "specificFolder",
"folderToWatch": {
"__rl": true,
"mode": "list",
"value": "1UHQhCrwZg_ZEzBIKv4LR_RWtAyHbxZsg",
"cachedResultUrl": "https://drive.google.com/drive/folders/1UHQhCrwZg_ZEzBIKv4LR_RWtAyHbxZsg",
"cachedResultName": "Marketing Ladder Knowledge Base"
}
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "ae95c1ce-bcf7-47fb-a3e3-2b6c6d02aa9e",
"name": "Delete Row(s)",
"type": "n8n-nodes-base.supabase",
"position": [
840,
1500
],
"parameters": {
"tableId": "documents",
"operation": "delete",
"filterType": "string",
"filterString": "=metadata->>file_id=like.*{{ $json.id }}*"
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "c6f252c0-e81c-48f5-9a7b-6507b467c54d",
"name": "Get FIle ID",
"type": "n8n-nodes-base.set",
"position": [
1120,
1500
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "b4433ac7-0b70-4405-a564-f3f78f784470",
"name": "file_id",
"type": "string",
"value": "={{ $('File Updated').item.json.id }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "4d5bcbf0-fe14-4d24-81f5-72b84712c09d",
"name": "Reformat",
"type": "n8n-nodes-base.limit",
"position": [
1320,
1500
],
"parameters": {},
"typeVersion": 1
},
{
"id": "f55697b5-191d-4865-9970-3462abeb05ef",
"name": "Download File1",
"type": "n8n-nodes-base.googleDrive",
"position": [
1520,
1500
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $('Get FIle ID').item.json.file_id }}"
},
"options": {
"googleFileConversion": {
"conversion": {
"docsToFormat": "text/plain"
}
}
},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "4fcc245c-e57c-461e-ba04-18122933eacb",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
1280
],
"parameters": {
"color": 4,
"width": 640,
"height": 80,
"content": "# Update File in Knowledge Base \n"
},
"typeVersion": 1
},
{
"id": "78e0be5d-aa5b-49b3-8b52-2fb2db7dd8be",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
480,
1400
],
"parameters": {
"color": 5,
"width": 280,
"height": 260,
"content": "## Get File to Update\n \n"
},
"typeVersion": 1
},
{
"id": "35de9387-b80a-4274-aa57-622d85a60064",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
1040,
1400
],
"parameters": {
"color": 5,
"width": 400,
"height": 260,
"content": "## Fix Formatting\n"
},
"typeVersion": 1
},
{
"id": "8ffe865f-09ef-426d-9f5c-e7273a13441d",
"name": "Sticky Note9",
"type": "n8n-nodes-base.stickyNote",
"position": [
1460,
1400
],
"parameters": {
"color": 5,
"width": 420,
"height": 260,
"content": "## Extract File Text\n\n"
},
"typeVersion": 1
},
{
"id": "35aecaa8-b327-493f-8526-fbd019bc078d",
"name": "Sticky Note10",
"type": "n8n-nodes-base.stickyNote",
"position": [
1920,
1400
],
"parameters": {
"color": 5,
"width": 600,
"height": 580,
"content": "## Update Vector Database\n\n"
},
"typeVersion": 1
},
{
"id": "05d5c49a-8eee-4b90-9ec7-2ac6f20cd259",
"name": "Recursive Character Text Splitter1",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
2320,
1840
],
"parameters": {
"options": {},
"chunkSize": 300,
"chunkOverlap": 50
},
"typeVersion": 1
},
{
"id": "88c403af-3425-4be3-9cc9-c79196df5115",
"name": "Extract from File1",
"type": "n8n-nodes-base.extractFromFile",
"position": [
1700,
1500
],
"parameters": {
"options": {},
"operation": "text"
},
"typeVersion": 1
},
{
"id": "a4c44cc1-54c8-4d32-9d25-6b9b7bedb7a2",
"name": "Embeddings OpenAI1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
2040,
1700
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "1784fe6a-6b2e-4fc9-9e28-05284e5f9e15",
"name": "Default Data Loader1",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
2220,
1700
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "file_id",
"value": "={{ $('Reformat').item.json.file_id }}"
}
]
}
}
},
"typeVersion": 1
},
{
"id": "83950e53-fab5-4f58-af8d-11126c1bfb3f",
"name": "Supabase Vector Store1",
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"position": [
2060,
1500
],
"parameters": {
"mode": "insert",
"options": {
"queryName": "match_documents"
},
"tableName": {
"__rl": true,
"mode": "list",
"value": "documents",
"cachedResultName": "documents"
}
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "22c08877-6bb1-4cfa-acda-df2b5814afa0",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
500,
680
],
"parameters": {
"color": 5,
"width": 280,
"height": 260,
"content": "## Get New File \n"
},
"typeVersion": 1
},
{
"id": "d16c74c1-ccdb-4bc2-b607-c846b56b07d1",
"name": "Sticky Note11",
"type": "n8n-nodes-base.stickyNote",
"position": [
760,
1400
],
"parameters": {
"color": 5,
"width": 280,
"height": 260,
"content": "## Delete Rows\n \n"
},
"typeVersion": 1
},
{
"id": "7d163045-13c3-42d7-9c51-0045c3056a6e",
"name": "Transcribe",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
-1060,
840
],
"parameters": {
"options": {},
"resource": "audio",
"operation": "transcribe"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.6
},
{
"id": "14ac063c-0f77-4e3d-a603-7cf95d3701c4",
"name": "Text",
"type": "n8n-nodes-base.set",
"position": [
-1160,
1040
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "fe7ecc99-e1e8-4a5e-bdd6-6fce9757b234",
"name": "text",
"type": "string",
"value": "={{ $json.message.text }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "dccda445-c531-4009-bb3e-19b927d31d01",
"name": "Voice or Text",
"type": "n8n-nodes-base.switch",
"position": [
-1460,
980
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "voice",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "281588e5-cab1-47c7-b42a-f75b8e7b659e",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.voice.file_id }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "Text",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "8c844924-b2ed-48b0-935c-c66a8fd0c778",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.text }}",
"rightValue": ""
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "4ab95976-d1d8-438f-8112-99395823166c",
"name": "Response",
"type": "n8n-nodes-base.telegram",
"position": [
-20,
960
],
"parameters": {
"text": "={{ $json.output }}",
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"additionalFields": {
"appendAttribution": false
}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "e38d614d-09eb-4f42-9229-6b037ecdc264",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1520,
800
],
"parameters": {
"color": 5,
"width": 680,
"height": 460,
"content": "## Convert Message to Text\n\n"
},
"typeVersion": 1
},
{
"id": "136f7bd7-aa99-4460-b24f-30d65c932cb3",
"name": "RAG Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-640,
960
],
"parameters": {
"text": "={{ $json.text }}",
"options": {
"systemMessage": "=# Overview\nYou are a RAG assistant. Your job is to search for queries from a vector database and pass on the search results.\n\n# Tools\n**MarketingLadder** \n- This is the vector store that you must query to find answers. \n- Use the search findings from the vector store to create an answer to the input query.\n\n## Final Notes\n- If you can't find an answer from the database, then just say you couldn't find an answer. Never use your own knowledge. "
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "5e87da8f-4677-483e-b41c-a79ff11e2750",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-1700,
980
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "2b8470fb-2b8d-4490-8a40-c3479cb0865e",
"name": "Window Buffer Memory1",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-580,
1160
],
"parameters": {
"sessionKey": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "3e2e080a-62ab-4ab8-889d-d357d250d68d",
"name": "Download File2",
"type": "n8n-nodes-base.telegram",
"position": [
-1240,
840
],
"parameters": {
"fileId": "={{ $json.message.voice.file_id }}",
"resource": "file"
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "da9bebc8-452f-493f-aefc-81dcd789f355",
"name": "Supabase Vector Store3",
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"position": [
-620,
1340
],
"parameters": {
"options": {
"queryName": "match_documents"
},
"tableName": {
"__rl": true,
"mode": "list",
"value": "documents",
"cachedResultName": "documents"
}
},
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "0360fb6a-ac93-4e83-abb3-b19a5e614a76",
"name": "OpenAI Chat Model2",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-240,
1340
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "302c2316-d91e-4b57-80d1-8678bcdc718a",
"name": "Sticky Note12",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1800,
700
],
"parameters": {
"color": 4,
"width": 280,
"height": 80,
"content": "# RAG Chatbot\n"
},
"typeVersion": 1
},
{
"id": "9d0d4d0d-ec09-4f0f-bb14-bd6d5ea56c5a",
"name": "Embeddings OpenAI3",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-660,
1520
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "ea8349d1-8566-4f67-9e83-3a9b41f94d6b",
"name": "Sticky Note13",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1820,
920
],
"parameters": {
"color": 5,
"width": 280,
"height": 260,
"content": "## Get New Message\n"
},
"typeVersion": 1
},
{
"id": "d1a77833-3d99-4cc3-80a8-2d9b9c440175",
"name": "Sticky Note14",
"type": "n8n-nodes-base.stickyNote",
"position": [
-820,
800
],
"parameters": {
"color": 5,
"width": 720,
"height": 860,
"content": "## RAG System\n\n"
},
"typeVersion": 1
},
{
"id": "366a89d0-dd1d-4cd8-9de4-d7caa0433cab",
"name": "Sticky Note15",
"type": "n8n-nodes-base.stickyNote",
"position": [
-80,
900
],
"parameters": {
"color": 5,
"width": 320,
"height": 260,
"content": "## Send Output as Message\n"
},
"typeVersion": 1
},
{
"id": "11f88e16-7ef0-484f-b7d1-e74e0e639da3",
"name": "OpenAI Chat Model3",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-760,
1160
],
"parameters": {
"model": "gpt-4o",
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "5992f547-5327-4091-b4a8-37d6aec6b75e",
"name": "MarketingLadder",
"type": "@n8n/n8n-nodes-langchain.toolVectorStore",
"position": [
-440,
1160
],
"parameters": {
"name": "MarketingLadder",
"description": "This vector store holds information about Marketing Ladder agency"
},
"typeVersion": 1
},
{
"id": "10baf4fe-5497-4fcc-b624-155b56d17dbe",
"name": "Sticky Note16",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2320,
1900
],
"parameters": {
"color": 5,
"width": 440,
"height": 240,
"content": "## Hey, I'm Abdul \ud83d\udc4b\n### I build growth systems for consultants & agencies. If you want to work together or need help automating your business, check out my website: \n### **https://www.builtbyabdul.com/**\n### Or email me at **abdul@buildabdul.com**\n### Have a lovely day ;)`"
},
"typeVersion": 1
},
{
"id": "98e8b14c-ea04-4e08-9c3f-3e1510197e03",
"name": "Sticky Note17",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2660,
420
],
"parameters": {
"width": 780,
"height": 1420,
"content": "# Company RAG Knowledge Base Agent\n## Overview\nTurn your docs into an AI-powered internal or public-facing assistant. This chatbot workflow uses RAG (Retrieval-Augmented Generation) with Supabase vector search to answer employee or customer questions based on your company documents\u2014automatically updated via Google Drive.\n\nWhether it\u2019s deployed in Telegram or embedded on your website, this agent supports voice and text input, transcribes voice messages, pulls relevant context from your internal files, and responds with a helpful, AI-generated answer. Two additional workflows listen for file changes in a shared Google Drive folder, convert them into embeddings using OpenAI, and sync them with your Supabase vector DB\u2014so your knowledge base is always up to date.\n\n### Who\u2019s it for\n- Startups building an internal ops or HR assistant \n- SaaS companies deploying help bots on their websites \n- Customer support teams reducing repetitive questions \n- Knowledge-driven teams needing internal AI assistants \n\n### How it works\n- Triggered via Telegram bot (or easily swapped for website chatbot or \u201con chat message\u201d) \n- If user sends a voice message, it\u2019s transcribed to text using OpenAI Whisper \n- Input is passed to a RAG agent that:\n - Searches a Supabase vector store for relevant docs \n - Pulls context from matching chunks using OpenAI embeddings \n - Responds with an LLM-powered answer \n- The response is sent back as a Telegram message \n- Two separate workflows:\n - **New File Workflow**: Listens for file uploads in Google Drive, extracts and splits text, then sends to Supabase with embeddings \n - **Update File Workflow**: Detects file edits, deletes old rows, and updates embeddings for the revised file \n\n### Example use case\n> You upload your internal policy docs and client FAQs into a Google Drive folder. \n> \n> Employees or customers can now ask: \n> - \u201cWhat\u2019s the refund policy for annual plans?\u201d \n> - \u201cHow do I request a day off?\u201d \n> - \u201cWhat tools are approved for use by the engineering team?\u201d \n> \n> The chatbot instantly pulls up the right section and responds with a smart, confident answer.\n\n### How to set up\n1. Connect a Telegram bot or use n8n\u2019s webchat / chatbot widget \n2. Hook up OpenAI for transcription, embeddings, and completion \n3. Set up a Supabase project and connect it as a vector store \n4. Upload your internal docs to Google Drive \n5. Deploy the \u201cAdd File\u201d and \u201cUpdate File\u201d automations to manage embedding sync \n6. Customize the chatbot\u2019s tone and personality with prompt tweaks \n\n### Requirements\n- Telegram bot (or n8n Chat widget) \n- Google Drive integration \n- Supabase with pgvector or similar enabled \n- OpenAI API key (Whisper, Embeddings, ChatGPT) \n- Two folders: one for raw documents and one for tracking updates \n\n### How to customize\n- Swap Supabase for Pinecone, Weaviate, or Qdrant \n- Replace Telegram with web chat, Slack, Intercom, or Discord \n- Add logic to handle fallback answers or escalate to human \n- Embed the chat widget on your site for public customer use \n- Add filters (e.g. department, date, author) to narrow down context\n"
},
"typeVersion": 1
}
],
"connections": {
"Text": {
"main": [
[
{
"node": "RAG Agent",
"type": "main",
"index": 0
}
]
]
},
"Set ID": {
"main": [
[
{
"node": "Download File",
"type": "main",
"index": 0
}
]
]
},
"New File": {
"main": [
[
{
"node": "Set ID",
"type": "main",
"index": 0
}
]
]
},
"Reformat": {
"main": [
[
{
"node": "Download File1",
"type": "main",
"index": 0
}
]
]
},
"RAG Agent": {
"main": [
[
{
"node": "Response",
"type": "main",
"index": 0
}
]
]
},
"Transcribe": {
"main": [
[
{
"node": "RAG Agent",
"type": "main",
"index": 0
}
]
]
},
"Get FIle ID": {
"main": [
[
{
"node": "Reformat",
"type": "main",
"index": 0
}
]
]
},
"File Updated": {
"main": [
[
{
"node": "Delete Row(s)",
"type": "main",
"index": 0
}
]
]
},
"Delete Row(s)": {
"main": [
[
{
"node": "Get FIle ID",
"type": "main",
"index": 0
}
]
]
},
"Download File": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"Voice or Text": {
"main": [
[
{
"node": "Download File2",
"type": "main",
"index": 0
}
],
[
{
"node": "Text",
"type": "main",
"index": 0
}
]
]
},
"Download File1": {
"main": [
[
{
"node": "Extract from File1",
"type": "main",
"index": 0
}
]
]
},
"Download File2": {
"main": [
[
{
"node": "Transcribe",
"type": "main",
"index": 0
}
]
]
},
"MarketingLadder": {
"ai_tool": [
[
{
"node": "RAG Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "Voice or Text",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Supabase Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI1": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Embeddings OpenAI3": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store3",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Extract from File1": {
"main": [
[
{
"node": "Supabase Vector Store1",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model2": {
"ai_languageModel": [
[
{
"node": "MarketingLadder",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model3": {
"ai_languageModel": [
[
{
"node": "RAG Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Supabase Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Default Data Loader1": {
"ai_document": [
[
{
"node": "Supabase Vector Store1",
"type": "ai_document",
"index": 0
}
]
]
},
"Window Buffer Memory1": {
"ai_memory": [
[
{
"node": "RAG Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Supabase Vector Store3": {
"ai_vectorStore": [
[
{
"node": "MarketingLadder",
"type": "ai_vectorStore",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Recursive Character Text Splitter1": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader1",
"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.
googleDriveOAuth2ApiopenAiApisupabaseApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Turn your docs into an AI-powered internal or public-facing assistant. This chatbot workflow uses RAG (Retrieval-Augmented Generation) with Supabase vector search to answer employee or customer questions based on your company documents—automatically updated via Google Drive.
Source: https://n8n.io/workflows/6538/ — 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.
A lightweight, self-hosted AI assistant built entirely in n8n. Multi-channel messaging (Telegram, WhatsApp, Gmail), persistent memory, task management, and autonomous work — all in a single visual wor
Telegram Trigger, OpenRouter Chat, Data Table +20
Your AI workforce is ready. Are you?
Google Sheets Tool, Mcp Trigger, Google Drive +29
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
Telegram Trigger, Telegram, OpenAI +19
This intelligent chatbot leverages cutting-edge financial APIs and AI-driven analysis to deliver comprehensive stock research reports. Get instant access to professional-grade investment analysis that
Tool Think, Supabase Vector Store, OpenAI Embeddings +15
RAG_Ingest. Uses httpRequest, vectorStoreSupabase, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter. Event-driven trigger; 73 nodes.
HTTP Request, Supabase Vector Store, Document Default Data Loader +4