This workflow follows the Chainllm → 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 →
{
"name": "vector_manager",
"nodes": [
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
-224,
496
],
"id": "05f23abc-6f60-4a0d-a88e-8c31edb3e184",
"name": "When clicking \u2018Execute workflow\u2019"
},
{
"parameters": {
"operation": "get",
"dataTableId": {
"__rl": true,
"value": "vNdtv6ffWxydZcwX",
"mode": "list",
"cachedResultName": "concierge_sources",
"cachedResultUrl": "/projects/uabU37OVTmcWS1JM/datatables/vNdtv6ffWxydZcwX"
},
"filters": {
"conditions": [
{
"keyName": "status",
"keyValue": "notindexed"
}
]
},
"returnAll": true
},
"type": "n8n-nodes-base.dataTable",
"typeVersion": 1.1,
"position": [
0,
496
],
"id": "b9b53a8e-411e-4384-b95a-8ff72a000001",
"name": "concierge_sources"
},
{
"parameters": {
"operation": "update",
"dataTableId": {
"__rl": true,
"value": "vNdtv6ffWxydZcwX",
"mode": "list",
"cachedResultName": "concierge_sources",
"cachedResultUrl": "/projects/uabU37OVTmcWS1JM/datatables/vNdtv6ffWxydZcwX"
},
"filters": {
"conditions": [
{
"keyName": "url",
"keyValue": "={{ $('iteration').isExecuted ? $('iteration').item.json.url : $('get_page').item.json.url }}"
}
]
},
"columns": {
"mappingMode": "defineBelow",
"value": {
"status": "indexed",
"text": "={{ $('Basic LLM Chain').item.json.text }}"
},
"matchingColumns": [],
"schema": [
{
"id": "url",
"displayName": "url",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": true
},
{
"id": "type",
"displayName": "type",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": true
},
{
"id": "status",
"displayName": "status",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "text",
"displayName": "text",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
}
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"type": "n8n-nodes-base.dataTable",
"typeVersion": 1.1,
"position": [
1744,
320
],
"id": "d8ac0c50-68cb-49e5-932d-55cef6c0fcf9",
"name": "update data"
},
{
"parameters": {
"options": {}
},
"type": "n8n-nodes-base.splitInBatches",
"typeVersion": 3,
"position": [
224,
496
],
"id": "89317d3e-be51-4802-8058-36fab6155c53",
"name": "iteration"
},
{
"parameters": {},
"type": "n8n-nodes-base.wait",
"typeVersion": 1.1,
"position": [
1968,
496
],
"id": "379e6597-4392-428f-9e9e-16e3bf20978f",
"name": "5s"
},
{
"parameters": {
"promptType": "define",
"text": "=Tu es un extracteur de contenu. Ta t\u00e2che est de nettoyer et restructurer le contenu brut d'une page web, extrait automatiquement, pour qu'il devienne une base de connaissance exploitable par un agent conversationnel.\n\nR\u00c8GLES STRICTES :\n\n1. Ne jamais inventer, r\u00e9sumer, reformuler ou interpr\u00e9ter l'information. Le texte de sortie doit rester fid\u00e8le mot pour mot au contenu source pour tout ce qui est conserv\u00e9. Tu restructures et tu nettoies, tu ne r\u00e9\u00e9cris pas.\n\n2. Retire syst\u00e9matiquement :\n - Menus de navigation, liens de header/footer\n - Scripts, code JavaScript, JSON de configuration technique, balises de routing\n - Badges d'interface, compteurs, statistiques de statut syst\u00e8me (ex: \"Uptime: 99.98%\", \"Tasks: 1,248\")\n - \u00c9l\u00e9ments r\u00e9p\u00e9t\u00e9s plusieurs fois dans le texte (souvent des artefacts de composants dupliqu\u00e9s dans le rendu)\n - Call-to-action g\u00e9n\u00e9riques sans contenu informatif (\"S'abonner\", \"R\u00e9server mon audit\" isol\u00e9s sans contexte)\n - Mentions l\u00e9gales, copyright, liens r\u00e9seaux sociaux\n\n3. Conserve int\u00e9gralement :\n - Toute description de service, tarif, m\u00e9thodologie, processus\n - Tout texte biographique ou de positionnement\n - Titres d'articles de blog et leurs r\u00e9sum\u00e9s/accroches si pr\u00e9sents\n - Toute donn\u00e9e chiffr\u00e9e qui n'est pas un artefact d'interface (ex: \"1500\u20ac HT\", \"40h/mois\" sont \u00e0 garder, \"Uptime: 99.98%\" est \u00e0 jeter)\n\n4. Si un passage est ambigu (tu ne sais pas s'il s'agit de contenu r\u00e9el ou de bruit d'interface), conserve-le plut\u00f4t que de le supprimer. Un faux positif dans le nettoyage est pire qu'un peu de bruit r\u00e9siduel.\n\n5. Structure la sortie en texte clair, paragraphes coh\u00e9rents, sans markdown de mise en forme complexe (pas de tableaux, pas de liens). Des titres simples en majuscules ou entre ## sont accept\u00e9s pour s\u00e9parer les sections th\u00e9matiques si la page en contient plusieurs (ex: plusieurs services sur une m\u00eame page).\n\n6. Ne commente jamais ton propre travail. Ne dis jamais \"voici le contenu nettoy\u00e9\" ou \u00e9quivalent. Retourne uniquement le texte final.\n\nURL source de la page : {{ $('iteration').isExecuted ? $('iteration').item.json.url : $('get_page').item.json.url }}\n\nContenu brut \u00e0 traiter :\n{{ $json.data }}",
"batching": {}
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.9,
"position": [
896,
64
],
"id": "929e4df5-8b6d-4236-9208-6a4870b76dca",
"name": "Basic LLM Chain",
"retryOnFail": true,
"maxTries": 5,
"waitBetweenTries": 1500
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1.1,
"position": [
976,
288
],
"id": "709b9c00-5d47-4f4e-8455-5302c1f98b74",
"name": "Google Gemini Chat Model",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"url": "=https://r.jina.ai/{{ $json.url ?? $('get_page').item.json.url }}",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.4,
"position": [
672,
176
],
"id": "3a4a7979-a0d8-4a02-aeb2-799b3be34371",
"name": "jina.ai"
},
{
"parameters": {
"mode": "insert",
"tableName": {
"__rl": true,
"value": "concierge_documents",
"mode": "list",
"cachedResultName": "concierge_documents"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStoreSupabase",
"typeVersion": 1.3,
"position": [
1280,
320
],
"id": "f286391c-9297-419d-a582-d6be185e5e38",
"name": "Supabase Vector Store",
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"textSplittingMode": "custom",
"options": {
"metadata": {
"metadataValues": [
{
"name": "type",
"value": "={{ $('iteration').isExecuted ? $('iteration').item.json.type : $('get_page').item.json.type }}"
},
{
"name": "url",
"value": "={{ $('iteration').isExecuted ? $('iteration').item.json.url : $('get_page').item.json.url }}"
}
]
}
}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1.1,
"position": [
1376,
544
],
"id": "493f9c43-f1f0-430d-b0a1-f39c1755f963",
"name": "Default Data Loader"
},
{
"parameters": {
"chunkSize": 800,
"chunkOverlap": 120,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"typeVersion": 1,
"position": [
1456,
752
],
"id": "31ae6325-17d8-4164-b771-bc06d99094cf",
"name": "Recursive Character Text Splitter"
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"typeVersion": 1,
"position": [
1248,
544
],
"id": "44a823d3-9fa0-444b-9ce9-1cc59d061e71",
"name": "Embeddings Google Gemini",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"dataTableId": {
"__rl": true,
"value": "vNdtv6ffWxydZcwX",
"mode": "list",
"cachedResultName": "concierge_sources",
"cachedResultUrl": "/projects/uabU37OVTmcWS1JM/datatables/vNdtv6ffWxydZcwX"
},
"columns": {
"mappingMode": "defineBelow",
"value": {
"status": "notindexed",
"url": "={{ $('form trigger').item.json.Url }}",
"type": "={{ $('form trigger').item.json.Type }}"
},
"matchingColumns": [],
"schema": [
{
"id": "url",
"displayName": "url",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "type",
"displayName": "type",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "status",
"displayName": "status",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": false
},
{
"id": "text",
"displayName": "text",
"required": false,
"defaultMatch": false,
"display": true,
"type": "string",
"readOnly": false,
"removed": true
}
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": {}
},
"type": "n8n-nodes-base.dataTable",
"typeVersion": 1.1,
"position": [
96,
336
],
"id": "752d9d7d-96c1-42e6-84c5-2b76f9f50f86",
"name": "Insert row"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 3
},
"conditions": [
{
"id": "9d716f2d-de51-4952-8963-07dccfe74dab",
"leftValue": "={{ Object.keys($json).length }}",
"rightValue": 0,
"operator": {
"type": "number",
"operation": "gt"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.3,
"position": [
-64,
224
],
"id": "2550d7cc-aa73-4f9e-bb20-c36d33f936e0",
"name": "page exists ?"
},
{
"parameters": {
"formTitle": "Concierge",
"formDescription": "Ajouter ou mettre \u00e0 jour une page",
"formFields": {
"values": [
{
"fieldLabel": "Url",
"requiredField": true
},
{
"fieldLabel": "Type",
"fieldType": "dropdown",
"fieldOptions": {
"values": [
{
"option": "page"
},
{
"option": "service"
},
{
"option": "article"
}
]
},
"requiredField": true
}
]
},
"options": {}
},
"type": "n8n-nodes-base.formTrigger",
"typeVersion": 2.6,
"position": [
-480,
224
],
"id": "9fdf0c28-852b-4454-bc98-9ce29df8f57f",
"name": "form trigger"
},
{
"parameters": {
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 3
},
"conditions": [
{
"id": "260041bd-7d23-4ce5-aa52-3938d10165ec",
"leftValue": "={{ Object.keys($json).length }}",
"rightValue": 0,
"operator": {
"type": "number",
"operation": "gt"
}
}
],
"combinator": "and"
},
"options": {}
},
"type": "n8n-nodes-base.if",
"typeVersion": 2.3,
"position": [
240,
304
],
"id": "97c506c4-515a-4193-95bb-e52f2623a5f4",
"name": "inserted ?"
},
{
"parameters": {
"rules": {
"values": [
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 3
},
"conditions": [
{
"leftValue": "={{ (!$json.text || $json.text === \"\") && $('concierge_sources').isExecuted }}",
"rightValue": "",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"id": "89d15956-38ce-4a94-b7eb-f357743193c3"
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "no content"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 3
},
"conditions": [
{
"id": "16ca5bc7-03a1-4f4c-9086-1d12e6510e11",
"leftValue": "={{ ($json.text && $json.text !== \"\") && $('concierge_sources').isExecuted }}",
"rightValue": "",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "content"
},
{
"conditions": {
"options": {
"caseSensitive": true,
"leftValue": "",
"typeValidation": "strict",
"version": 3
},
"conditions": [
{
"id": "8767e7cc-8950-4fd2-83e3-d5d510afe721",
"leftValue": "={{ $('concierge_sources').isExecuted }}",
"rightValue": "",
"operator": {
"type": "boolean",
"operation": "false",
"singleValue": true
}
}
],
"combinator": "and"
},
"renameOutput": true,
"outputKey": "no iteraction"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.switch",
"typeVersion": 3.4,
"position": [
448,
320
],
"id": "aa1da40a-aa18-46d8-ac68-0699e20b80f2",
"name": "Switch"
},
{
"parameters": {
"operation": "get",
"dataTableId": {
"__rl": true,
"value": "vNdtv6ffWxydZcwX",
"mode": "list",
"cachedResultName": "concierge_sources",
"cachedResultUrl": "/projects/uabU37OVTmcWS1JM/datatables/vNdtv6ffWxydZcwX"
},
"filters": {
"conditions": [
{
"keyName": "url",
"keyValue": "={{ $json.Url }}"
}
]
}
},
"type": "n8n-nodes-base.dataTable",
"typeVersion": 1.1,
"position": [
-272,
224
],
"id": "a4e15fea-3c7f-439d-935c-a84cd4ebbd0e",
"name": "get_page",
"alwaysOutputData": true
},
{
"parameters": {
"method": "DELETE",
"url": "=https://YOUR_PROJECT_REF.supabase.co/rest/v1/concierge_documents?metadata->>url=eq.{{ encodeURIComponent($json.url) }}",
"authentication": "predefinedCredentialType",
"nodeCredentialType": "supabaseApi",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.4,
"position": [
128,
64
],
"id": "7ecea7ed-c340-4912-9eb3-03ffdb4d740f",
"name": "delete_vector",
"alwaysOutputData": false,
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"assignments": {
"assignments": [
{
"id": "eec32d71-9839-4827-a3fe-efd6de831604",
"name": "text",
"value": "={{ $json.text }}",
"type": "string"
}
]
},
"options": {}
},
"type": "n8n-nodes-base.set",
"typeVersion": 3.4,
"position": [
960,
464
],
"id": "ff31fb63-e5bf-44a3-896c-489eb15a7506",
"name": "normalizer"
}
],
"connections": {
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "concierge_sources",
"type": "main",
"index": 0
}
]
]
},
"concierge_sources": {
"main": [
[
{
"node": "iteration",
"type": "main",
"index": 0
}
]
]
},
"update data": {
"main": [
[
{
"node": "5s",
"type": "main",
"index": 0
}
]
]
},
"iteration": {
"main": [
[],
[
{
"node": "Switch",
"type": "main",
"index": 0
}
]
]
},
"5s": {
"main": [
[
{
"node": "iteration",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Supabase Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"jina.ai": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Supabase Vector Store": {
"main": [
[
{
"node": "update data",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Supabase Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Embeddings Google Gemini": {
"ai_embedding": [
[
{
"node": "Supabase Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Insert row": {
"main": [
[
{
"node": "inserted ?",
"type": "main",
"index": 0
}
]
]
},
"page exists ?": {
"main": [
[
{
"node": "delete_vector",
"type": "main",
"index": 0
},
{
"node": "jina.ai",
"type": "main",
"index": 0
}
],
[
{
"node": "Insert row",
"type": "main",
"index": 0
}
]
]
},
"form trigger": {
"main": [
[
{
"node": "get_page",
"type": "main",
"index": 0
}
]
]
},
"inserted ?": {
"main": [
[
{
"node": "jina.ai",
"type": "main",
"index": 0
}
]
]
},
"Switch": {
"main": [
[
{
"node": "jina.ai",
"type": "main",
"index": 0
}
],
[
{
"node": "normalizer",
"type": "main",
"index": 0
}
],
[]
]
},
"get_page": {
"main": [
[
{
"node": "page exists ?",
"type": "main",
"index": 0
}
]
]
},
"delete_vector": {
"main": [
[]
]
},
"normalizer": {
"main": [
[
{
"node": "Supabase Vector Store",
"type": "main",
"index": 0
}
]
]
}
},
"active": false,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate",
"availableInMCP": false
},
"versionId": "903cd086-5a6c-43a1-8f3d-71fc3551a92a",
"meta": {
"templateCredsSetupCompleted": true
},
"nodeGroups": [],
"id": "YOUR_CREDENTIAL_ID",
"tags": []
}
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.
googlePalmApisupabaseApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
vector_manager. Uses dataTable, chainLlm, lmChatGoogleGemini, httpRequest. Event-driven trigger; 20 nodes.
Source: https://github.com/tolproductlab/tpl-concierge/blob/main/workflows/vector_manager.json — 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.
n8n telegram RAG. Uses lmChatGoogleGemini, embeddingsGoogleGemini, memoryManager, vectorStoreSupabase. Event-driven trigger; 32 nodes.
Google Gemini Chat, Google Gemini Embeddings, Memory Manager +10
This template is designed for podcasters, researchers, educators, product teams, and support teams who work with audio content and want to turn it into searchable knowledge. It is especially useful fo
Form Trigger, HTTP Request, Pinecone Vector Store +8
Create AI-Ready Vector Datasets for LLMs with Bright Data, Gemini & Pinecone. Uses manualTrigger, agent, vectorStorePinecone, embeddingsGoogleGemini. Event-driven trigger; 21 nodes.
Agent, Pinecone Vector Store, Google Gemini Embeddings +7
This workflow enables automated, scalable collection of high-quality, AI-ready data from websites using Bright Data’s Web Unlocker, with a focus on preparing that data for LLM training. Leveraging LLM
Agent, Pinecone Vector Store, Google Gemini Embeddings +7
Convert any website into a searchable vector database for AI chatbots. Submit a URL, choose scraping scope, and this workflow handles everything: scraping, cleaning, chunking, embedding, and storing i
Supabase Vector Store, Google Gemini Embeddings, Text Splitter Recursive Character Text Splitter +3