This workflow follows the Chat Trigger → OpenAI 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 →
{
"updatedAt": "2025-11-28T17:51:13.920Z",
"createdAt": "2025-11-28T17:36:31.254Z",
"id": "QFvLylMg9TswRZTe",
"name": "PDF Summarizer",
"active": true,
"isArchived": false,
"nodes": [
{
"parameters": {
"public": true,
"options": {
"allowFileUploads": true
}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.3,
"position": [
0,
0
],
"id": "773cd981-5815-4159-9a21-7f317875be32",
"name": "When chat message received"
},
{
"parameters": {
"modelId": {
"__rl": true,
"value": "gpt-4.1-mini-2025-04-14",
"mode": "list",
"cachedResultName": "GPT-4.1-MINI-2025-04-14"
},
"messages": {
"values": [
{
"content": "=PDF: {{ $json.text }}"
},
{
"content": "=Objetivo:\nVoc\u00ea receber\u00e1 um arquivo PDF. Sua tarefa \u00e9:\n\nProduzir um resumo detalhado, entre 1500 e 2000 palavras, destacando os pontos mais importantes para estudo.\nEm seguida, criar um quiz com 10 quest\u00f5es de m\u00faltipla escolha (A, B, C, D), cada uma com:\nEnunciado claro e objetivo.\nQuatro alternativas plaus\u00edveis (A\u2013D).\nIndica\u00e7\u00e3o expl\u00edcita da resposta correta.\nUm coment\u00e1rio explicativo curto citando trechos ou ideias-chave do conte\u00fado para justificar a resposta.\nInstru\u00e7\u00f5es detalhadas:\n\nLinguagem: portugu\u00eas claro, formal, com precis\u00e3o conceitual.\nP\u00fablico-alvo: estudantes que ir\u00e3o revisar o conte\u00fado para provas.\nConsist\u00eancia: garanta que cada quest\u00e3o se baseie diretamente no conte\u00fado do arquivo PDF, evitando infer\u00eancias externas.\nCobertura: o resumo deve contemplar defini\u00e7\u00e3o dos conceitos centrais, argumentos principais, evid\u00eancias, exemplos relevantes, implica\u00e7\u00f5es pr\u00e1ticas, controv\u00e9rsias/limita\u00e7\u00f5es, e rela\u00e7\u00f5es entre os t\u00f3picos.\nOrganiza\u00e7\u00e3o:\nT\u00edtulo do resumo.\nSe\u00e7\u00f5es com subt\u00edtulos descritivos.\nLista dos principais termos e defini\u00e7\u00f5es (bullet points) ao final do resumo.\nQuiz ap\u00f3s o resumo, em se\u00e7\u00e3o separada.\nEstilo do resumo:\nAbertura com vis\u00e3o geral do tema e objetivo do arquivo PDF.\nDesenvolvimento com encadeamento l\u00f3gico e coes\u00e3o.\n\u00canfase nos pontos mais importantes para estudo (fa\u00e7a uma se\u00e7\u00e3o \u201cPontos-chave para revis\u00e3o\u201d com bullets).\nConclus\u00e3o sintetizando aprendizados e poss\u00edveis aplica\u00e7\u00f5es.\nCita\u00e7\u00f5es: quando fizer refer\u00eancia a partes espec\u00edficas, cite brevemente entre aspas (\u201c...\u201d) ou com indica\u00e7\u00e3o de se\u00e7\u00e3o/minutagem se fornecida.\nExtens\u00e3o: entre 1500 e 2000 palavras (n\u00e3o menos que 1500 e n\u00e3o mais que 2000).\nQuiz:\nVarie os tipos de quest\u00e3o: defini\u00e7\u00e3o, aplica\u00e7\u00e3o, interpreta\u00e7\u00e3o de cita\u00e7\u00e3o, rela\u00e7\u00e3o de causa/efeito, verdadeiro/falso convertido em m\u00faltipla escolha.\nEm pelo menos 2 quest\u00f5es, use trechos literais do arquivo PDF para perguntar \u201cA que conceito/parte se refere a seguinte passagem: \u2018\u2026\u2019\u201d.\nEvite alternativas \u00f3bvias; todas devem ser veross\u00edmeis.\nAp\u00f3s cada quest\u00e3o, indique:\nResposta: [A/B/C/D]\nComent\u00e1rio: uma breve justificativa, citando a passagem ou a ideia correspondente.\nFormata\u00e7\u00e3o de sa\u00edda:\nUse cabe\u00e7alhos e listas para tornar o material escane\u00e1vel.\nMantenha portugu\u00eas do Brasil.\nN\u00e3o inclua conte\u00fado n\u00e3o presente no arquivo PDF.\nEntrada fornecida:\n\nArquivo PDF: {{ $json.text }}.\nModelo de sa\u00edda (exemplo de estrutura):\n\nResumo (1500\u20132000 palavras)\nT\u00edtulo\nIntrodu\u00e7\u00e3o (contexto e objetivo)\nSe\u00e7\u00f5es tem\u00e1ticas (2\u20135 se\u00e7\u00f5es, com subt\u00edtulos)\nPontos-chave para revis\u00e3o (bullet points)\nTermos e defini\u00e7\u00f5es (bullet points)\nConclus\u00e3o\nQuiz (10 quest\u00f5es)\nQuest\u00e3o 1: [enunciado]\nA) [alternativa]\nB) [alternativa]\nC) [alternativa]\nD) [alternativa]\nResposta: [letra]\nComent\u00e1rio: [justificativa curta citando trecho/ideia]\n\nQuest\u00e3o 2: \u2026\n\n\u2026\n\nQuest\u00e3o 10: \u2026\n\nCrit\u00e9rios de qualidade:\n\nFidelidade total ao conte\u00fado do arquivo PDF.\nClareza, concis\u00e3o e precis\u00e3o conceitual.\nAbrang\u00eancia dos t\u00f3picos-chave.\nQuest\u00f5es desafiadoras, com justificativas corretas e \u00fateis para estudo.\nObserva\u00e7\u00e3o:\nSe a transcri\u00e7\u00e3o estiver incompleta, indique as lacunas e evite extrapolar. Se houver minutagens, utilize-as para contextualizar as cita\u00e7\u00f5es no resumo e nos coment\u00e1rios do quiz.\n\nExemplo do estilo de pergunta solicitado (adapte ao conte\u00fado do arquivo PDF):\n\n\u201cA que parte do RNA se refere a seguinte parte do texto: \u2018se baseia no modo como a estrutura \u00e9 dada, de maneira a fazer com que o conhecimento experimental seja armazenado nessa estrutura, ou melhor dizendo, nas conex\u00f5es sin\u00e1pticas entre os neur\u00f4nios (Haykin, 2001, p. 28).\u2019\u201d\nA) A estrutura.\nB) A programa\u00e7\u00e3o.\nC) Ao texto.\nD) Ao algoritmo de aprendizagem.\nResposta: D\nComent\u00e1rio: \u201cO algoritmo de aprendizagem, por sua vez, se baseia no modo como a estrutura \u00e9 dada...\u201d\n",
"role": "system"
}
]
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.openAi",
"typeVersion": 1.8,
"position": [
432,
0
],
"id": "7a354419-bd31-42fd-bc23-ad431a65bcfe",
"name": "Message a model1",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "pdf",
"binaryPropertyName": "=data0",
"options": {}
},
"type": "n8n-nodes-base.extractFromFile",
"typeVersion": 1,
"position": [
224,
0
],
"id": "0a270b5c-ab4c-4ac8-80cd-9a40191153fa",
"name": "Extract from File",
"alwaysOutputData": false
},
{
"parameters": {
"folderId": "=14fNRjKaLEHEsSP019F5GqRmPkVYGsaXl",
"title": "={{ $json.message.content.substr(0,78) }}"
},
"id": "e31ed62a-794a-4ed8-962a-1ae32c434d3d",
"name": "Create Doc Filename is title",
"type": "n8n-nodes-base.googleDocs",
"position": [
768,
0
],
"typeVersion": 2,
"credentials": {
"googleDocsOAuth2Api": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"operation": "update",
"documentURL": "={{ $json.id }}",
"actionsUi": {
"actionFields": [
{
"action": "insert",
"locationChoice": "location",
"text": "={{ $('Message a model1').item.json.message.content }}"
}
]
}
},
"id": "873258bf-bc77-4a83-b8e3-c5621367cfb9",
"name": "Add Final Article",
"type": "n8n-nodes-base.googleDocs",
"position": [
976,
0
],
"typeVersion": 2,
"credentials": {
"googleDocsOAuth2Api": {
"name": "<your credential>"
}
}
}
],
"connections": {
"When chat message received": {
"main": [
[
{
"node": "Extract from File",
"type": "main",
"index": 0
}
]
]
},
"Message a model1": {
"main": [
[
{
"node": "Create Doc Filename is title",
"type": "main",
"index": 0
}
]
]
},
"Extract from File": {
"main": [
[
{
"node": "Message a model1",
"type": "main",
"index": 0
}
]
]
},
"Create Doc Filename is title": {
"main": [
[
{
"node": "Add Final Article",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
},
"staticData": null,
"meta": {
"templateCredsSetupCompleted": true
},
"versionId": "3b8fbb21-8df2-41fd-abff-44bebfc075f5",
"triggerCount": 1,
"shared": [
{
"updatedAt": "2025-11-28T17:36:31.254Z",
"createdAt": "2025-11-28T17:36:31.254Z",
"role": "workflow:owner",
"workflowId": "QFvLylMg9TswRZTe",
"projectId": "CK6XEsloykybki2p"
}
],
"tags": [
{
"updatedAt": "2025-11-27T22:32:06.122Z",
"createdAt": "2025-11-27T22:32:06.122Z",
"id": "lf6jGzaXcolij5dW",
"name": "prod"
},
{
"updatedAt": "2025-11-27T22:30:51.794Z",
"createdAt": "2025-11-27T22:30:51.794Z",
"id": "V4F4G6t2C5blKSYh",
"name": "internal-infra"
}
],
"n8n_host_name ": "https://n8n.trymyapp.tech/"
}
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.
googleDocsOAuth2ApiopenAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
PDF Summarizer. Uses chatTrigger, openAi, googleDocs. Chat trigger; 5 nodes.
Source: https://github.com/denissongomes/Backup-N8N-workflows/blob/d3c3368a5664119f3cf42362354f22a691dfb119/Workflows/PDF_Summarizer.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 workflow is for: People who want to quickly launch simple landing pages without paying monthly fees to landing page creators. It’s ideal for rapid prototyping, generation of large amounts of land
Google Gemini, OpenAI, Chat Trigger +3
Most career advice is generic. This workflow builds a fully personalized AI coaching system that remembers every user, adapts to their career stage and goals, detects what kind of help they need, and
Google Sheets, Gmail, Chat Trigger +2
Automate the creation of high-performing YouTube Shorts in minutes! Content Creators: Generate engaging short videos effortlessly. Marketing Agencies: Produce client-ready content quickly. Business Ow
Chat Trigger, HTTP Request, OpenAI
I prepared a comprehensive guide demonstrating how to build a multi-level retrieval AI agent in n8n that smartly narrows down search results first by file descriptions, then retrieves detailed vector
Tool Code, Chat Trigger, OpenAI +2
This workflow is for anyone who needs to research topics quickly and thoroughly: content creators, marketers, product managers, researchers, journalists, students, or anyone seeking deep insights with
Chat Trigger, N8N Nodes Oxylabs Ai Studio, Data Table +1