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 →
{
"name": "TRBL_IA",
"nodes": [
{
"parameters": {
"httpMethod": "POST",
"path": "ia",
"responseMode": "responseNode",
"options": {}
},
"type": "n8n-nodes-base.webhook",
"typeVersion": 2.1,
"position": [
-720,
96
],
"id": "a03f970d-8f2a-4e7f-9fd4-bf05e0922322",
"name": "Webhook"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.body.pergunta }}",
"options": {
"systemMessage": "<System>\nVoc\u00ea \u00e9 um assistente de um site de receitas culin\u00e1rias.\nSEMPRE consulte a ferramenta de busca antes de responder qualquer pergunta.\nNunca responda sem antes buscar no banco de dados.\nCaso n\u00e3o ache informa\u00e7\u00f5es no banco, procure em outros meios como a internet.\nN\u00e3o responda perguntas fora do tema de receitas.\nA sa\u00edda deve ser apenas texto simples sem nenhum comando de texto.\n</System>"
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 3.1,
"position": [
-512,
96
],
"id": "eced64ec-6eb9-4914-a954-76f1a2fd1016",
"name": "AI Agent",
"executeOnce": false,
"retryOnFail": true
},
{
"parameters": {
"modelName": "models/gemini-2.5-flash",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1.1,
"position": [
-512,
320
],
"id": "9fd61814-c1ff-424a-b246-3659de7f1b0e",
"name": "Google Gemini Chat Model",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"notes": "responda somente com: banana"
},
{
"parameters": {
"respondWith": "json",
"responseBody": "={\n \"resposta\": {{ $json.output.toJsonString()}}\n}",
"options": {}
},
"type": "n8n-nodes-base.respondToWebhook",
"typeVersion": 1.5,
"position": [
-176,
96
],
"id": "28f40afe-ec47-481c-8de0-14ed8e6593c4",
"name": "Respond to Webhook"
},
{
"parameters": {
"url": "https://api-receitas-pi.vercel.app/receitas/todas?page=0&limit=93",
"options": {}
},
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.4,
"position": [
96,
96
],
"id": "bae6d346-8b2d-4270-9c08-b9e7217e978d",
"name": "HTTP Request"
},
{
"parameters": {
"mode": "insert",
"tableName": "vetores",
"embeddingBatchSize": 93,
"options": {
"columnNames": {
"values": {}
}
}
},
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"typeVersion": 1.3,
"position": [
496,
96
],
"id": "11dbff1e-6315-4592-9960-af2727094317",
"name": "Postgres PGVector Store1",
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "retrieve-as-tool",
"toolDescription": "System: voc\u00ea \u00e9 um assistente chatbot de um site de receitas culinarias, voc\u00ea n\u00e3o pode responder mensagens que fujam do prop\u00f3sito do site. Respostas que respondam sem deixar d\u00favidas e de facil intui\u00e7\u00e3o s\u00e3o melhores.",
"tableName": "vetores",
"topK": 20,
"includeDocumentMetadata": false,
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"typeVersion": 1.3,
"position": [
-448,
448
],
"id": "17c5687e-2ad9-4e8b-9ee6-a2898302ff5d",
"name": "Postgres PGVector Store",
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {},
"type": "@n8n/n8n-nodes-langchain.embeddingsGoogleGemini",
"typeVersion": 1,
"position": [
-288,
608
],
"id": "89b4b646-13cc-4638-959f-ba2d87d6daef",
"name": "Embeddings Google Gemini",
"executeOnce": true,
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "const response = $input.first().json.items;\n\nreturn response\n .filter(r => r.receita && r.tipo && r.ingredientes && r.modo_preparo)\n .map(r => ({\n json: {\n text: [\n `Receita: ${r.receita}`,\n `Tipo: ${r.tipo}`,\n `Ingredientes: ${r.ingredientes}`,\n `Modo de Preparo: ${r.modo_preparo}`\n ].join('\\n'),\n }\n }));"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
304,
96
],
"id": "035e9794-0c19-452c-91ec-cfb63f84b613",
"name": "Code in JavaScript"
},
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"typeVersion": 1.1,
"position": [
544,
304
],
"id": "96c85828-8afb-4e6a-8795-45ac9daa083f",
"name": "Default Data Loader"
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "Respond to Webhook",
"type": "main",
"index": 0
}
]
]
},
"HTTP Request": {
"main": [
[
{
"node": "Code in JavaScript",
"type": "main",
"index": 0
}
]
]
},
"Postgres PGVector Store": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Embeddings Google Gemini": {
"ai_embedding": [
[
{
"node": "Postgres PGVector Store1",
"type": "ai_embedding",
"index": 0
},
{
"node": "Postgres PGVector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Code in JavaScript": {
"main": [
[
{
"node": "Postgres PGVector Store1",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Postgres PGVector Store1",
"type": "ai_document",
"index": 0
}
]
]
},
"Postgres PGVector Store1": {
"main": [
[]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1",
"binaryMode": "separate",
"availableInMCP": false
},
"versionId": "0ae24aa8-ce2b-4803-a973-2a6aa33e57c2",
"meta": {
"templateCredsSetupCompleted": true
},
"nodeGroups": [],
"id": "q8PFuXxbp138vpVm",
"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.
googlePalmApipostgres
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
TRBL_IA. Uses agent, lmChatGoogleGemini, httpRequest, vectorStorePGVector. Webhook trigger; 10 nodes.
Source: https://github.com/CarEduCar/Serratec_GP2_React_P2/blob/fd3630b4282def6a6d95b0f7293a2c0d47a0c2a6/n8n/n8n_saborrei_IA.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.
Camila IA. Uses postgres, crypto, redis, agent. Webhook trigger; 92 nodes.
This workflow ingests FAQs from Google Sheets into a Supabase vector table using Google Gemini embeddings, then serves a webhook-based support chatbot that answers only from that FAQ knowledge base an
Rag Workflow. Uses googleDrive, vectorStorePinecone, embeddingsGoogleGemini, documentDefaultDataLoader. Webhook trigger; 17 nodes.
This workflow acts as a 24/7 sales agent, engaging leads across WhatsApp, Instagram, Facebook, Telegram, and your website. It intelligently transcribes audio messages, answers questions using a knowle
My Workflow. Uses outputParserStructured, httpRequest, lmChatGoogleGemini, chainLlm. Scheduled trigger; 82 nodes.