📖 Creador de Database

🧠 Objetivo del Workflow

Detectar automáticamente archivos (PDF, Word o Excel) subidos o modificados en una carpeta específica de Google Drive, extraer su contenido de texto, unificarlo y prepararlo para usarlo como entrada de un sistema RAG o de análisis posterior.

🔄 Flujo paso a paso

1. Trigger inicial

📂 Google Drive Trigger: Detecta cuándo se sube o actualiza un archivo en la carpeta "RAG N8N".

2. Preparación

🧩 Analiza el type: Extrae el file_id y el tipo MIME del archivo (PDF, DOCX, XLS).
🔁 bucle: Prepara el procesamiento para cada archivo individualmente.
📥 descarga de archivo: Descarga el archivo desde Google Drive.

3. Clasificación por tipo

🔀 Switch: Revisa el tipo de archivo (file_type) y decide el camino:

PDF → Extract from File2
Word (DOCX) → Extract from File1
Excel (XLS) → Extract from File

4. Extracción de texto

🔍 Extract from File*: Usa el nodo para sacar el texto del archivo.
📦 junta todas las lineas en uno*: Reagrupa todas las líneas de texto en un solo bloque.
🔗 concatena lo que extrae de *: Une ese bloque de texto en un único string.

5. Resultado final

📝 Edit Fields1: Crea una nueva variable llamada documento que contiene todo el texto extraído y concatenado.

🧩 ¿Qué falta para completar el sistema?

Puedes conectar Edit Fields1 a un sistema RAG, por ejemplo:

Un nodo LangChain o agente de IA que use documento como entrada.
O enviar ese texto a una base vectorial como Weaviate.

Descargar Workflow

{
  "nodes": [
    {
      "parameters": {
        "pollTimes": {
          "item": [
            {
              "mode": "everyMinute"
            }
          ]
        },
        "triggerOn": "specificFolder",
        "folderToWatch": {
          "__rl": true,
          "value": "1xeX3L3e7g89oKKIjHEr8TkxGVhfaUERh",
          "mode": "list",
          "cachedResultName": "RAG N8N",
          "cachedResultUrl": "https://drive.google.com/drive/folders/1xeX3L3e7g89oKKIjHEr8TkxGVhfaUERh"
        },
        "event": "fileUpdated",
        "options": {}
      },
      "type": "n8n-nodes-base.googleDriveTrigger",
      "typeVersion": 1,
      "position": [
        0,
        10
      ],
      "id": "a81bdb0b-b2e0-4afc-aa82-2c0825b493f2",
      "name": "Google Drive Trigger",
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "HRkn47TE1r8AxmSH",
          "name": "Google Drive account 2"
        }
      }
    },
    {
      "parameters": {
        "rules": {
          "values": [
            {
              "conditions": {
                "options": {
                  "caseSensitive": true,
                  "leftValue": "",
                  "typeValidation": "strict",
                  "version": 2
                },
                "conditions": [
                  {
                    "leftValue": "={{ $json.file_type }}",
                    "rightValue": "application/pdf",
                    "operator": {
                      "type": "string",
                      "operation": "equals"
                    },
                    "id": "bc458477-4362-4dd4-bf4c-cf1990f920f5"
                  }
                ],
                "combinator": "and"
              },
              "renameOutput": true,
              "outputKey": "PDF"
            },
            {
              "conditions": {
                "options": {
                  "caseSensitive": true,
                  "leftValue": "",
                  "typeValidation": "strict",
                  "version": 2
                },
                "conditions": [
                  {
                    "id": "ec88d521-c864-4bda-93f2-a55a4e3be00e",
                    "leftValue": "={{ $json.file_type }}",
                    "rightValue": "=application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                    "operator": {
                      "type": "string",
                      "operation": "equals",
                      "name": "filter.operator.equals"
                    }
                  }
                ],
                "combinator": "and"
              },
              "renameOutput": true,
              "outputKey": "Text File"
            },
            {
              "conditions": {
                "options": {
                  "caseSensitive": true,
                  "leftValue": "",
                  "typeValidation": "strict",
                  "version": 2
                },
                "conditions": [
                  {
                    "id": "196b02e9-cf58-4bca-b00d-85153af2dfa3",
                    "leftValue": "={{ $json.file_type }}",
                    "rightValue": "application/vnd.ms-excel",
                    "operator": {
                      "type": "string",
                      "operation": "equals",
                      "name": "filter.operator.equals"
                    }
                  }
                ],
                "combinator": "and"
              },
              "renameOutput": true,
              "outputKey": "Excel"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.switch",
      "typeVersion": 3.2,
      "position": [
        660,
        -140
      ],
      "id": "98672cc9-87a1-4678-af38-aeea3e6c0971",
      "name": "Switch"
    },
    {
      "parameters": {
        "operation": "xlsx",
        "options": {}
      },
      "type": "n8n-nodes-base.extractFromFile",
      "typeVersion": 1,
      "position": [
        880,
        60
      ],
      "id": "1d154eed-908e-497e-8599-293130204958",
      "name": "Extract from File"
    },
    {
      "parameters": {
        "operation": "text",
        "options": {}
      },
      "type": "n8n-nodes-base.extractFromFile",
      "typeVersion": 1,
      "position": [
        880,
        -140
      ],
      "id": "45f0b40b-4cdc-40da-998b-c1189b9dcf6e",
      "name": "Extract from File1"
    },
    {
      "parameters": {
        "operation": "pdf",
        "options": {}
      },
      "type": "n8n-nodes-base.extractFromFile",
      "typeVersion": 1,
      "position": [
        880,
        -340
      ],
      "id": "de358c15-5463-4e5b-9c9e-5c80d82d263f",
      "name": "Extract from File2"
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "e7971c0f-883c-4918-8e8a-bb04ee02f10b",
              "name": "documento",
              "value": "={{ $json.concatenated_data }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        1560,
        -140
      ],
      "id": "5a70b5b0-df90-47d6-874e-e4556ec75111",
      "name": "Edit Fields1"
    },
    {
      "parameters": {
        "assignments": {
          "assignments": [
            {
              "id": "6693dd8f-21a9-4910-a808-47e7c26c0906",
              "name": "file_id",
              "value": "={{ $json.id }}",
              "type": "string"
            },
            {
              "id": "1cfc3ae5-3d81-4b90-b9fe-04a99735e34b",
              "name": "file_type",
              "value": "={{ $json.mimeType }}",
              "type": "string"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.set",
      "typeVersion": 3.4,
      "position": [
        220,
        10
      ],
      "id": "a44b237e-df9e-4de9-a4f4-dbd04872c3f1",
      "name": "Analiza el type"
    },
    {
      "parameters": {
        "options": {}
      },
      "type": "n8n-nodes-base.splitInBatches",
      "typeVersion": 3,
      "position": [
        440,
        10
      ],
      "id": "5560b0cd-2315-4745-a3b7-210a4ac49b54",
      "name": "bucle"
    },
    {
      "parameters": {
        "operation": "download",
        "fileId": {
          "__rl": true,
          "value": "={{ $json.file_id }}",
          "mode": "id"
        },
        "options": {
          "googleFileConversion": {
            "conversion": {
              "docsToFormat": "application/pdf"
            }
          }
        }
      },
      "type": "n8n-nodes-base.googleDrive",
      "typeVersion": 3,
      "position": [
        660,
        60
      ],
      "id": "01d3e455-f803-4fb1-93c3-36d23d44da70",
      "name": "descarga de archivo",
      "credentials": {
        "googleDriveOAuth2Api": {
          "id": "HRkn47TE1r8AxmSH",
          "name": "Google Drive account 2"
        }
      }
    },
    {
      "parameters": {
        "aggregate": "aggregateAllItemData",
        "options": {}
      },
      "type": "n8n-nodes-base.aggregate",
      "typeVersion": 1,
      "position": [
        1100,
        60
      ],
      "id": "97294ba2-b8a9-46c5-a568-d1b530b53b96",
      "name": "junta todas las lineas en uno"
    },
    {
      "parameters": {
        "aggregate": "aggregateAllItemData",
        "options": {}
      },
      "type": "n8n-nodes-base.aggregate",
      "typeVersion": 1,
      "position": [
        1100,
        -140
      ],
      "id": "1f2d2c71-454d-472f-9599-3499713e68e0",
      "name": "junta todas las lineas en uno1"
    },
    {
      "parameters": {
        "aggregate": "aggregateAllItemData",
        "options": {}
      },
      "type": "n8n-nodes-base.aggregate",
      "typeVersion": 1,
      "position": [
        1100,
        -340
      ],
      "id": "6d68583b-17f8-415e-9352-bf6481642912",
      "name": "junta todas las lineas en uno2"
    },
    {
      "parameters": {
        "fieldsToSummarize": {
          "values": [
            {
              "aggregation": "concatenate",
              "field": "data"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.summarize",
      "typeVersion": 1.1,
      "position": [
        1320,
        -340
      ],
      "id": "1c42965a-39fb-4947-aaf6-dac4716c2cb4",
      "name": "concatena lo que extrae de pdf"
    },
    {
      "parameters": {
        "fieldsToSummarize": {
          "values": [
            {
              "aggregation": "concatenate",
              "field": "data"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.summarize",
      "typeVersion": 1.1,
      "position": [
        1320,
        -140
      ],
      "id": "7a3bc8c8-9abd-4495-8fdc-8ff69119b6b8",
      "name": "concatena lo que extrae de texto"
    },
    {
      "parameters": {
        "fieldsToSummarize": {
          "values": [
            {
              "aggregation": "concatenate",
              "field": "data"
            }
          ]
        },
        "options": {}
      },
      "type": "n8n-nodes-base.summarize",
      "typeVersion": 1.1,
      "position": [
        1320,
        60
      ],
      "id": "703124ec-1931-458d-af3f-1a6f72f4c307",
      "name": "concatena lo que extrae de excel"
    },
    {
      "parameters": {
        "content": "## Ultimo paso\nConectar la base vectorial que nosotros queramos. (supabase, milvus, pinecone etc..)",
        "height": 140,
        "width": 220,
        "color": 5
      },
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        1760,
        -160
      ],
      "id": "16a393be-0f53-4215-9767-e009d6658ee4",
      "name": "Ultimo paso"
    }
  ],
  "connections": {
    "Google Drive Trigger": {
      "main": [
        [
          {
            "node": "Analiza el type",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Switch": {
      "main": [
        [
          {
            "node": "Extract from File2",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Extract from File1",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Extract from File",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract from File": {
      "main": [
        [
          {
            "node": "junta todas las lineas en uno",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract from File1": {
      "main": [
        [
          {
            "node": "junta todas las lineas en uno1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract from File2": {
      "main": [
        [
          {
            "node": "junta todas las lineas en uno2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Edit Fields1": {
      "main": [
        []
      ]
    },
    "Analiza el type": {
      "main": [
        [
          {
            "node": "bucle",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "bucle": {
      "main": [
        [
          {
            "node": "Switch",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "descarga de archivo",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "descarga de archivo": {
      "main": [
        [
          {
            "node": "bucle",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "junta todas las lineas en uno": {
      "main": [
        [
          {
            "node": "concatena lo que extrae de excel",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "junta todas las lineas en uno1": {
      "main": [
        [
          {
            "node": "concatena lo que extrae de texto",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "junta todas las lineas en uno2": {
      "main": [
        [
          {
            "node": "concatena lo que extrae de pdf",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "concatena lo que extrae de pdf": {
      "main": [
        [
          {
            "node": "Edit Fields1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "concatena lo que extrae de texto": {
      "main": [
        [
          {
            "node": "Edit Fields1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "concatena lo que extrae de excel": {
      "main": [
        [
          {
            "node": "Edit Fields1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "pinData": {},
  "meta": {
    "templateCredsSetupCompleted": true,
    "instanceId": "2c730164cdb2fb009c04fbde91af79afe6b458d2f36cf4dde6cfb7095899ce0c"
  }
}

← Volver al portafolio