This workflow follows the Agent → Chat Trigger 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": "I2A2",
"nodes": [
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
-680,
120
],
"id": "61ea9c53-687d-4b5c-b61c-99dff03e5926",
"name": "When clicking \u2018Test workflow\u2019"
},
{
"parameters": {},
"type": "n8n-nodes-base.compression",
"typeVersion": 1.1,
"position": [
-220,
120
],
"id": "285a9902-96fb-462d-8826-2aeb5aa49beb",
"name": "Compression"
},
{
"parameters": {
"binaryPropertyName": "file_0",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
40,
20
],
"id": "7b8dd245-9d89-4d55-b8b3-26c705e8005a",
"name": "Extract from File"
},
{
"parameters": {
"binaryPropertyName": "file_1",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
40,
260
],
"id": "e31824d8-3ad9-4e0e-92e3-cf9c2378bfbd",
"name": "Extract from File1"
},
{
"parameters": {
"public": true,
"initialMessages": "Ol\u00e1! \ud83d\udc4b\nAqui voc\u00ea pode consultar rapidamente informa\u00e7\u00f5es sobre notas fiscais. Pergunte, por exemplo:\n\nQuantas notas fiscais foram emitidas em determinado per\u00edodo? \ud83d\udcc5\n\nQual o valor total das notas fiscais para um cliente espec\u00edfico? \ud83d\udcb0\n\nEm quais estados as notas fiscais foram emitidas? \ud83d\uddfa\ufe0f\n\nQuais produtos foram vendidos em uma cidade? \ud83c\udfd9\ufe0f",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
-600,
540
],
"id": "5ffa8c5e-b7ac-4bd3-a8aa-2fbdeea85d8b",
"name": "When chat message received",
"notesInFlow": false
},
{
"parameters": {
"promptType": "define",
"text": "=You are an SQL agent and you are developing queries to execute on a PostgreSQL database.\nYou will receive a user question, and your answer must be exclusively the ready-to-run SQL query, with no additional text, explanation, or comments.\nDo not add titles, instructions, examples, or any words before or after the query.\nJust return the SQL query ready for use, nothing else.\n\nThe database consists of one table:\n\nTable notas_fiscais with the following columns:\n\nchave_de_acesso,modelo,serie,numero,natureza_da_operacao,data_emissao,evento_mais_recente,data_hora_evento_mais_recente,cpf_cnpj_emitente,razao_social_emitente,inscricao_estadual_emitente,uf_emitente,municipio_emitente,cnpj_destinatario,nome_destinatario,uf_destinatario,indicador_ie_destinatario,destino_da_operacao,consumidor_final,presenca_do_comprador,valor_nota_fiscal,descricao_do_produto,codigo_ncm_sh,ncm_sh_tipo_de_produto,cfop,quantidade,unidade,valor_unitario,valor_total\n\nImportant Table Rules\n\nEach row in this table represents a single item of a nota fiscal (invoice).\n\nA nota fiscal can have multiple items; all items belonging to the same nota fiscal share the same value in the \"chave_de_acesso\" column.\n\nEach nota fiscal (invoice) is uniquely identified by the value in the \"chave_de_acesso\" column.\n\nIf there are duplicate \"chave_de_acesso\" values, they refer to items of the same nota fiscal.\n\nWhen calculating totals or counts related to invoices (not items), always use DISTINCT \"chave_de_acesso\" to avoid duplicates.\n\nNote: The columns \"valor_total\" and \"valor_unitario\" represent monetary values.\n\nMandatory Criteria\n\nThe output must be ONLY the complete SQL query.\n\nDo not add any comments, explanations, markdown, or extra formatting.\n\nUse COUNT(), SUM(), or AVG() when applicable.\n\nAlways use double quotes for column names (e.g., \"uf_emitente\") and single quotes for literal values (e.g., 'SP').\n\nTable names must not be quoted (e.g., notas_fiscais).\n\nThe query must be a single SQL statement, ready for execution.\n\nWhat NOT to do:\n\nDo not add any text before or after the query.\n\nDo not use markdown formatting.\n\nDo not include comments or explanations.\n\nDo not use backticks or any other quotation marks for the query.\n\nDo not use table names with spaces; always use notas_fiscais.\n\nExamples:\nQuestion: What is the total number of invoices?\nAnswer: SELECT COUNT(DISTINCT \"chave_de_acesso\") FROM notas_fiscais;\n\nQuestion: How many distinct UF?\nAnswer: SELECT COUNT(DISTINCT \"uf_emitente\") FROM notas_fiscais;\n\nUser question: {{ $json.chatInput }}"
},
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"typeVersion": 1.6,
"position": [
-400,
540
],
"id": "7df91f39-0908-4136-b4b3-d7c3c1ffc8d9",
"name": "Basic LLM Chain",
"alwaysOutputData": false
},
{
"parameters": {
"modelName": "models/gemini-2.0-flash-001",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1,
"position": [
-380,
760
],
"id": "e27d6e84-3fde-4803-b6ab-c5c14cf00c3d",
"name": "Google Gemini Chat Model1",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"promptType": "define",
"text": "=Voc\u00ea \u00e9 um assistende de SQL.\n\nVoc\u00ea recebe perguntas e faz consultas no banco de dados postgresql para responder da melhor forma o usu\u00e1rio.\n\nAqui est\u00e1 a query a ser executada:{{ $json.resultado }}\n\nEssa foi a pergunta do usu\u00e1rio: {{ $('When chat message received').item.json.chatInput }}. \n\nMem\u00f3ria:\nVoc\u00ea possui uma mem\u00f3ria para consultar e responder melhor o usu\u00e1rio.\n\nAo fazer a consulta, responda de forma gentil o usu\u00e1rio.",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.9,
"position": [
220,
540
],
"id": "f36a0cda-64d5-4a7a-ba97-8ba50ef812b6",
"name": "AI Agent1"
},
{
"parameters": {
"modelName": "models/gemini-2.0-flash",
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"typeVersion": 1,
"position": [
180,
720
],
"id": "179f9ff0-4c7b-41cb-86b0-683d5e24170e",
"name": "Google Gemini Chat Model3",
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"tableId": "notas_fiscais",
"fieldsUi": {
"fieldValues": [
{
"fieldId": "chave_de_acesso",
"fieldValue": "={{ $json['CHAVE DE ACESSO'] }}"
},
{
"fieldId": "modelo",
"fieldValue": "={{ $json.MODELO }}"
},
{
"fieldId": "serie",
"fieldValue": "={{ $json['S\u00c9RIE'] }}"
},
{
"fieldId": "numero",
"fieldValue": "={{ $json['N\u00daMERO'] }}"
},
{
"fieldId": "natureza_da_operacao",
"fieldValue": "={{ $json['NATUREZA DA OPERA\u00c7\u00c3O'] }}"
},
{
"fieldId": "data_emissao",
"fieldValue": "={{ $json['DATA EMISS\u00c3O'] }}"
},
{
"fieldId": "evento_mais_recente",
"fieldValue": "={{ $json['EVENTO MAIS RECENTE'] }}"
},
{
"fieldId": "data_hora_evento_mais_recente",
"fieldValue": "={{ $json['DATA/HORA EVENTO MAIS RECENTE'] }}"
},
{
"fieldId": "cpf_cnpj_emitente",
"fieldValue": "={{ $json['CPF/CNPJ Emitente'] }}"
},
{
"fieldId": "razao_social_emitente",
"fieldValue": "={{ $json['RAZ\u00c3O SOCIAL EMITENTE'] }}"
},
{
"fieldId": "inscricao_estadual_emitente",
"fieldValue": "={{ $json['INSCRI\u00c7\u00c3O ESTADUAL EMITENTE'] }}"
},
{
"fieldId": "uf_emitente",
"fieldValue": "={{ $json['UF EMITENTE'] }}"
},
{
"fieldId": "municipio_emitente",
"fieldValue": "={{ $json['MUNIC\u00cdPIO EMITENTE'] }}"
},
{
"fieldId": "cnpj_destinatario",
"fieldValue": "={{ $json['CNPJ DESTINAT\u00c1RIO'] }}"
},
{
"fieldId": "nome_destinatario",
"fieldValue": "={{ $json['NOME DESTINAT\u00c1RIO'] }}"
},
{
"fieldId": "uf_destinatario",
"fieldValue": "={{ $json['UF DESTINAT\u00c1RIO'] }}"
},
{
"fieldId": "indicador_ie_destinatario",
"fieldValue": "={{ $json['INDICADOR IE DESTINAT\u00c1RIO'] }}"
},
{
"fieldId": "destino_da_operacao",
"fieldValue": "={{ $json['DESTINO DA OPERA\u00c7\u00c3O'] }}"
},
{
"fieldId": "consumidor_final",
"fieldValue": "={{ $json['CONSUMIDOR FINAL'] }}"
},
{
"fieldId": "presenca_do_comprador",
"fieldValue": "={{ $json['PRESEN\u00c7A DO COMPRADOR'] }}"
},
{
"fieldId": "valor_nota_fiscal",
"fieldValue": "={{ $json['VALOR NOTA FISCAL'] }}"
},
{
"fieldId": "numero_produto",
"fieldValue": "={{ $json['N\u00daMERO PRODUTO'] }}"
},
{
"fieldId": "descricao_do_produto",
"fieldValue": "={{ $json['DESCRI\u00c7\u00c3O DO PRODUTO/SERVI\u00c7O'] }}"
},
{
"fieldId": "codigo_ncm_sh",
"fieldValue": "={{ $json['C\u00d3DIGO NCM/SH'] }}"
},
{
"fieldId": "ncm_sh_tipo_de_produto",
"fieldValue": "={{ $json['NCM/SH (TIPO DE PRODUTO)'] }}"
},
{
"fieldId": "cfop",
"fieldValue": "={{ $json.CFOP }}"
},
{
"fieldId": "quantidade",
"fieldValue": "={{ $json.QUANTIDADE }}"
},
{
"fieldId": "unidade",
"fieldValue": "={{ $json.UNIDADE }}"
},
{
"fieldId": "valor_unitario",
"fieldValue": "={{ $json['VALOR UNIT\u00c1RIO'] }}"
},
{
"fieldId": "valor_total",
"fieldValue": "={{ $json['VALOR TOTAL'] }}"
}
]
}
},
"type": "n8n-nodes-base.supabase",
"typeVersion": 1,
"position": [
520,
120
],
"id": "81507c81-e9ba-4f41-9cba-7bef88ab7780",
"name": "Create a row",
"credentials": {
"supabaseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "executeQuery",
"query": "{{ $json.resultado }}\n",
"options": {}
},
"type": "n8n-nodes-base.postgresTool",
"typeVersion": 2.6,
"position": [
500,
720
],
"id": "bf329034-bf32-4545-b94c-98255e792f2f",
"name": "Execute a SQL query in Postgres",
"credentials": {
"postgres": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"jsCode": "let texto = $input.first().json.text;\n// Remova os backticks e \"sql\"\ntexto = texto.replace(/```/g, \"\").replace(/sql/g, \"\");\nreturn [{ resultado: texto }];"
},
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
0,
540
],
"id": "a56982f1-b55d-415c-957c-3617785ee729",
"name": "Code"
},
{
"parameters": {
"operation": "download",
"fileId": {
"__rl": true,
"value": "1WSSDtezq2jf-Bi4OenJwYbhITSutFALD",
"mode": "list",
"cachedResultName": "202401_NFs.zip",
"cachedResultUrl": "https://drive.google.com/file/d/1WSSDtezq2jf-Bi4OenJwYbhITSutFALD/view?usp=drivesdk"
},
"options": {}
},
"type": "n8n-nodes-base.googleDrive",
"typeVersion": 3,
"position": [
-460,
120
],
"id": "a65aebe2-4179-42d5-90cf-c4e3f9a6c538",
"name": "Download file",
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"mode": "combine",
"fieldsToMatchString": "['CHAVE DE ACESSO']",
"options": {}
},
"type": "n8n-nodes-base.merge",
"typeVersion": 3.2,
"position": [
280,
120
],
"id": "c297b7b6-74dd-43ed-ac61-bddec3e8b81f",
"name": "Merge"
},
{
"parameters": {
"sessionIdType": "customKey",
"sessionKey": "={{ $('When chat message received').item.json.sessionId }}",
"contextWindowLength": 10
},
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"typeVersion": 1.3,
"position": [
340,
740
],
"id": "7cc7570b-bfe9-456c-9e65-e67be04e0f88",
"name": "Simple Memory"
}
],
"connections": {
"When clicking \u2018Test workflow\u2019": {
"main": [
[
{
"node": "Download file",
"type": "main",
"index": 0
}
]
]
},
"Compression": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
},
{
"node": "Extract from File1",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Extract from File1": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Google Gemini Chat Model1": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Google Gemini Chat Model3": {
"ai_languageModel": [
[
{
"node": "AI Agent1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Execute a SQL query in Postgres": {
"ai_tool": [
[
{
"node": "AI Agent1",
"type": "ai_tool",
"index": 0
}
]
]
},
"Code": {
"main": [
[
{
"node": "AI Agent1",
"type": "main",
"index": 0
}
]
]
},
"Download file": {
"main": [
[
{
"node": "Compression",
"type": "main",
"index": 0
}
]
]
},
"Merge": {
"main": [
[
{
"node": "Create a row",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent1",
"type": "ai_memory",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "5b0113a4-1e1f-4c85-9dc3-1587214cbc36",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "1vTsK7MnLqlHpmiS",
"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.
googlePalmApigoogleSheetsOAuth2Api
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
I2A2. Uses agent, lmChatGoogleGemini, chatTrigger, executeWorkflowTrigger. Chat trigger; 16 nodes.
Source: https://github.com/IntelligenceI2A2/2025-Agentes/blob/7bdfa7c37fdfc8fd786c6cf12000ac792d4cac2f/Desafio02/chat_n8n/I2A2.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.
This Chatbot automates the process of discovering job openings and generating tailored job application emails.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
Job Application PredictLeads & ScrapeGraph AI. Uses chatTrigger, lmChatOpenAi, mcpClientTool, memoryBufferWindow. Chat trigger; 32 nodes.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
Job Application PredictLeads & ScrapeGraph AI. Uses chatTrigger, lmChatOpenAi, mcpClientTool, memoryBufferWindow. Chat trigger; 32 nodes.
Chat Trigger, OpenAI Chat, Mcp Client Tool +12
My Automations. Uses chatTrigger, agent, memoryBufferWindow, toolHttpRequest. Chat trigger; 17 nodes.
Chat Trigger, Agent, Memory Buffer Window +6
This workflow is an AI-powered Dental Appointment Assistant that automates appointment booking, rescheduling, and cancellations through Telegram or a Webhook. It uses intelligent agents to understand
Memory Buffer Window, Output Parser Structured, Mcp Client Tool +12