Generar preguntas de investigación y prompts de IA a partir de documentos PDF basados en vacíos de contenido

• •Pueden requerirse credenciales de autenticación para la API de destino

{
  "id": "oOxhkss1gOyLvJyf",
  "meta": {
    "instanceId": "2a26454b0172ffcb8d70ba77c235b1209f92cd71bf06c79ba609c7173b416d68",
    "templateCredsSetupCompleted": true
  },
  "name": "Generate Research Questions and AI Prompts from PDF Documents based on Content Gaps",
  "tags": [
    {
      "id": "66wgFoDi9Xjl74M3",
      "name": "Support",
      "createdAt": "2025-05-21T17:06:32.355Z",
      "updatedAt": "2025-05-21T17:06:32.355Z"
    },
    {
      "id": "kRM0hQV2zw7VxrON",
      "name": "Research",
      "createdAt": "2025-05-21T19:44:19.136Z",
      "updatedAt": "2025-05-21T19:44:19.136Z"
    },
    {
      "id": "sJk9cUvmMU8FkJXv",
      "name": "AI",
      "createdAt": "2025-05-20T13:16:15.636Z",
      "updatedAt": "2025-05-20T13:16:15.636Z"
    }
  ],
  "nodes": [
    {
      "id": "a2339bb9-abb9-41bf-8064-8c3af94df039",
      "name": "Convertir Archivo a PDF",
      "type": "n8n-nodes-base.httpRequest",
      "disabled": true,
      "position": [
        1880,
        180
      ],
      "parameters": {
        "url": "https://v2.convertapi.com/convert/pdf/to/txt",
        "method": "POST",
        "options": {
          "response": {
            "response": {
              "responseFormat": "text"
            }
          }
        },
        "sendBody": true,
        "contentType": "multipart-form-data",
        "sendHeaders": true,
        "authentication": "genericCredentialType",
        "bodyParameters": {
          "parameters": [
            {
              "name": "file",
              "parameterType": "formBinaryData",
              "inputDataFieldName": "data"
            }
          ]
        },
        "genericAuthType": "httpBearerAuth",
        "headerParameters": {
          "parameters": [
            {
              "name": "Accept",
              "value": "application/octet-stream"
            }
          ]
        }
      },
      "credentials": {
        "httpBearerAuth": {
          "id": "9fXf9Np7XsCWgxhg",
          "name": "Perplexity"
        }
      },
      "notesInFlow": true,
      "typeVersion": 4.2
    },
    {
      "id": "989a0d6c-12a1-45d4-8b6b-206855177df7",
      "name": "Nota Adhesiva5",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1840,
        -400
      ],
      "parameters": {
        "color": 2,
        "width": 360,
        "height": 820,
        "content": "## Optional: Better PDF Conversion\n\n### Standard Map PDF to Text node will split your PDF files into very short chunks, which deteriorates retrieval. \n\nUse can use [ConvertAPI](https://convertapi.com?ref=4l54n) which is a high-quality convertor that will respect the layout of the original document and not cut the paragraphs into short chunks. \n\nHere is an HTTP node that makes a request to their API to convert the PDF into text. If you have a ConvertAPI account, you can replace the \"Extract Text from PDF\" node in Step 3 with this node. \n\nNote that you will need to map the text output from this node correctly in the Step 4 after.\n"
      },
      "typeVersion": 1
    },
    {
      "id": "4d698efb-6b02-4e95-9a6f-dca8bc1fbea7",
      "name": "Al enviar el formulario",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        -380,
        -60
      ],
      "webhookId": "f35f0686-fbcb-466c-a59e-48ee9d360024",
      "parameters": {
        "options": {
          "appendAttribution": false
        },
        "formTitle": "Find Content Gaps in Your PDF Files",
        "formFields": {
          "values": [
            {
              "fieldType": "file",
              "fieldLabel": "Add Your Files",
              "acceptFileTypes": ".pdf"
            }
          ]
        },
        "formDescription": "Upload the files you'd like to analyze and we will extract content gaps and interesting questions based on them."
      },
      "typeVersion": 2.2
    },
    {
      "id": "5798ca71-eb05-4097-ace1-9457be450e21",
      "name": "Convertir archivos binarios a PDF",
      "type": "n8n-nodes-base.code",
      "position": [
        -60,
        -60
      ],
      "parameters": {
        "jsCode": "let results = [];\n\nfor (let item of items) {\n    if (item.binary) {\n        // If there's binary data in the item, process each binary file\n        for (let key in item.binary) {\n            // Use the key as the file name\n            let binaryKey = key.replace(/\\s/g, '_'); // Replace spaces with underscores for the key\n            results.push({\n                json: {\n                    fileName: binaryKey\n                },\n                binary: {\n                    [binaryKey]: item.binary[key] // Use the modified key for the binary data\n                }\n            });\n        }\n    }\n}\n\nreturn results;\n"
      },
      "typeVersion": 2
    },
    {
      "id": "6770b616-db38-48a8-8063-f3f5639d0946",
      "name": "Extraer texto de archivos PDF",
      "type": "n8n-nodes-base.extractFromFile",
      "position": [
        280,
        -60
      ],
      "parameters": {
        "options": {},
        "operation": "pdf",
        "binaryPropertyName": "={{ $json.fileName }}"
      },
      "typeVersion": 1
    },
    {
      "id": "2e47ecb8-cb9e-434a-ae9e-aae2ddb5fb54",
      "name": "Preparar para InfraNodus",
      "type": "n8n-nodes-base.code",
      "position": [
        580,
        -60
      ],
      "parameters": {
        "jsCode": "\nlet plainText = '' // we send plain text from all the PDFs to InfraNodus for analysis\n\nconst randomNum = Math.floor(Math.random() * 3); // replace this with a 0 if you'd like to address the biggest gap in the knowledge graph\n\nfor (let item of items) {\n   plainText += item.json.text + '\\n\\n'  \n}\n\n\nreturn {text: plainText, randomNum};"
      },
      "typeVersion": 2
    },
    {
      "id": "422faf1e-1545-4e5e-98aa-75c51a06c863",
      "name": "Mostrar en el Formulario al Usuario",
      "type": "n8n-nodes-base.form",
      "position": [
        1380,
        -60
      ],
      "webhookId": "091aab99-a4cf-40ec-b3bb-655d8e0b9a5c",
      "parameters": {
        "operation": "completion",
        "respondWith": "showText",
        "responseText": "=<br>\n<h3>{{ $json.aiAdvice[0].text }}</h3>\n<br>\n"
      },
      "typeVersion": 1
    },
    {
      "id": "820a3e64-1108-4c41-88e2-90d98fbd548f",
      "name": "Nota Adhesiva",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -420,
        -400
      ],
      "parameters": {
        "height": 520,
        "content": "## Step 1: User uploads the PDF files for analysis\n\n### You can expose this endpoint and make it publicly available via a URL to your organization."
      },
      "typeVersion": 1
    },
    {
      "id": "8dc2769a-b797-42c4-b531-82ce7f866dac",
      "name": "Nota Adhesiva1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -120,
        -400
      ],
      "parameters": {
        "width": 280,
        "height": 520,
        "content": "## Step 2: Convert uploaded binaries into PDF files\n\n### We need to convert the binaries uploaded to the PDF files so we can extract text from them."
      },
      "typeVersion": 1
    },
    {
      "id": "8f8cf47a-726c-4db8-9362-f68c94e75254",
      "name": "Nota Adhesiva2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        220,
        -400
      ],
      "parameters": {
        "width": 220,
        "height": 520,
        "content": "## Step 3: Extract plain text from PDF files\n\n### For better quality text extraction, you can use the optional [ConvertAPI](https://convertapi.com?ref=4l54n) node to the right, which respects the files' original formatting."
      },
      "typeVersion": 1
    },
    {
      "id": "f8da708a-ab86-40d7-bef0-dea600e5a032",
      "name": "Nota Adhesiva3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        520,
        -400
      ],
      "parameters": {
        "width": 220,
        "height": 520,
        "content": "## Step 4: Combine extracted text into a text string\n\n### Prepare data for InfraNodus: combine all the extracted text into a text string and also tell InfraNodus the gap depth it should use when generating advice"
      },
      "typeVersion": 1
    },
    {
      "id": "d63bb46c-5d0a-4fb9-8f9c-06a3aba63959",
      "name": "Nota Adhesiva4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        820,
        -400
      ],
      "parameters": {
        "width": 380,
        "height": 820,
        "content": "## Step 5: Use InfraNodus GraphRAG to build a knowledge graph, find the gap, and generate a research question based on it.\n\n### [InfraNodus](https://infranodus.com) builds a knowledge graph from all the texts, identifies the topical clusters that are least connected, and generates a research question that has a potential to bridge them in a new way.\n\n🚨 PROVIDE YOUR INFRANODUS API KEY HERE"
      },
      "typeVersion": 1
    },
    {
      "id": "0eeaef66-b9f5-4589-b663-9a992913fe1e",
      "name": "Nota Adhesiva6",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1280,
        -400
      ],
      "parameters": {
        "width": 380,
        "height": 820,
        "content": "## Step 6: Show question / prompt to the user\n\n### Optionally, you can feed the response to your other n8n workflow or expose it via a webhook and show it in your own app using an iframe."
      },
      "typeVersion": 1
    },
    {
      "id": "b82fefa5-5882-4ecf-8b68-f884b42411c9",
      "name": "Nota Adhesiva7",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -420,
        180
      ],
      "parameters": {
        "color": 5,
        "width": 1160,
        "height": 1000,
        "content": "# How does InfraNodus GraphRAG generate research questions?\n\n## [InfraNodus](https://infranodus.com) GraphRAG helps avoid generic responses and LLM bias through analyzing your text's structure. Here's how it works:\n\n### 1. It represents your text as a network of concepts and relations building a knowledge graph.\n\n### 2. It then identifies the clusters of cocnepts that are furthest apart from each other — they appear in the same context (your texts) but are not well connected.\n\n### 3. InfraNodus will then use the AI to generate a question / prompt that bridges this gap — touching upon relevant topics but connecting them in a new way.\n\n![structural gap infranodus](https://infranodus.com/images/front/infranodus-structural-gaps-ideas.jpg)"
      },
      "typeVersion": 1
    },
    {
      "id": "da7cf09a-d3f3-41d8-9ae4-4b4b1bcfc80f",
      "name": "InfraNodus GraphRAG Question Generator",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        960,
        0
      ],
      "parameters": {
        "url": "=https://infranodus.com/api/v1/graphAndAdvice?doNotSave=true&optimize=develop&includeGraph=false&includeGraphSummary=true&gapDepth={{ $json.randomNum }}",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "authentication": "genericCredentialType",
        "bodyParameters": {
          "parameters": [
            {
              "name": "aiTopics",
              "value": "true"
            },
            {
              "name": "requestMode",
              "value": "question"
            },
            {
              "name": "text",
              "value": "={{ $json.text }}"
            }
          ]
        },
        "genericAuthType": "httpBearerAuth"
      },
      "credentials": {
        "httpBearerAuth": {
          "id": "FPDx6PA5CtzGEIQc",
          "name": "InfraNodus DeeMeeTree API Key"
        }
      },
      "typeVersion": 4.2
    }
  ],
  "active": false,
  "pinData": {},
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "abd96e27-8999-4490-9c4c-8eda846dfc3b",
  "connections": {
    "4d698efb-6b02-4e95-9a6f-dca8bc1fbea7": {
      "main": [
        [
          {
            "node": "5798ca71-eb05-4097-ace1-9457be450e21",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "2e47ecb8-cb9e-434a-ae9e-aae2ddb5fb54": {
      "main": [
        [
          {
            "node": "da7cf09a-d3f3-41d8-9ae4-4b4b1bcfc80f",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "5798ca71-eb05-4097-ace1-9457be450e21": {
      "main": [
        [
          {
            "node": "6770b616-db38-48a8-8063-f3f5639d0946",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "6770b616-db38-48a8-8063-f3f5639d0946": {
      "main": [
        [
          {
            "node": "2e47ecb8-cb9e-434a-ae9e-aae2ddb5fb54",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "da7cf09a-d3f3-41d8-9ae4-4b4b1bcfc80f": {
      "main": [
        [
          {
            "node": "422faf1e-1545-4e5e-98aa-75c51a06c863",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}