Asistente Conciliación Bancaria

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": "Asistente Conciliaci\u00f3n Bancaria",
  "nodes": [
    {
      "parameters": {
        "updates": [
          "message"
        ],
        "additionalFields": {}
      },
      "type": "n8n-nodes-base.telegramTrigger",
      "typeVersion": 1.2,
      "position": [
        -144,
        -256
      ],
      "id": "0e1682f6-b9d7-4775-a010-bd7bd2c6377f",
      "name": "Recibir mensaje",
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "chatId": "={{ $node[\"Construir Contexto RAG\"].json.chat_id }}",
        "text": "={{ $json.message.content }}",
        "additionalFields": {}
      },
      "type": "n8n-nodes-base.telegram",
      "typeVersion": 1.2,
      "position": [
        976,
        -256
      ],
      "id": "683f0fd7-fde8-4dee-8048-a15797511a66",
      "name": "Enviar Respuesta",
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "method": "POST",
        "url": "http://TU_SERVIDOR_OLLAMA:11434/api/chat",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ JSON.stringify({\n  model: \"llama3\",\n  messages: [\n    {\n      role: \"system\",\n      content: \"Eres un Analista Virtual experto en conciliaci\u00f3n bancaria. Responde en espa\u00f1ol, de forma clara y profesional. Usa el CONTEXTO como base, redactado de forma fluida y natural.\"\n    },\n    {\n      role: \"user\",\n      content: \"CONTEXTO:\\n\" + $json.contexto + \"\\n\\nPREGUNTA:\\n\" + $json.pregunta\n    }\n  ],\n  stream: false\n}) }}",
        "options": {
          "response": {
            "response": {
              "responseFormat": "json"
            }
          },
          "timeout": 300000
        }
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.4,
      "position": [
        752,
        -256
      ],
      "id": "4c8691f8-3f49-4657-93b8-3630efedd264",
      "name": "Generar Respuesta con LLM"
    },
    {
      "parameters": {
        "jsCode": "const contexto = items.map(item => item.json.texto).join(\"\\n\\n\");\n\nreturn [{\n  json: {\n    contexto: contexto,\n    pregunta: $node[\"Recibir mensaje\"].json.message.text,\n    chat_id: $node[\"Recibir mensaje\"].json.message.chat.id\n  },\n  pairedItem: 0\n}];"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        528,
        -256
      ],
      "id": "effe9729-b1f8-4af3-89ef-b8596eb4f905",
      "name": "Construir Contexto RAG"
    },
    {
      "parameters": {
        "operation": "executeQuery",
        "query": "SELECT doc_id, texto,\n       1 - (embedding <=> '{{ JSON.stringify($json.embeddings[0]) }}'::vector) AS similitud\nFROM knowledge_base\nORDER BY embedding <=> '{{ JSON.stringify($json.embeddings[0]) }}'::vector\nLIMIT 3;",
        "options": {}
      },
      "type": "n8n-nodes-base.postgres",
      "typeVersion": 2.6,
      "position": [
        304,
        -256
      ],
      "id": "015c215a-e666-495b-aefe-6d8901bf0f30",
      "name": "Buscar Documentos Similares",
      "credentials": {
        "postgres": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "method": "POST",
        "url": "http://TU_SERVIDOR_OLLAMA:11434/api/embed",
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ JSON.stringify({\n  model: \"nomic-embed-text\",\n  input: [$json.message.text]\n}) }}",
        "options": {}
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.4,
      "position": [
        80,
        -256
      ],
      "id": "a3326247-2117-49b2-9e33-c46f77d9269b",
      "name": "Generar Embedding Pregunta"
    }
  ],
  "connections": {
    "Recibir mensaje": {
      "main": [
        [
          {
            "node": "Generar Embedding Pregunta",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generar Respuesta con LLM": {
      "main": [
        [
          {
            "node": "Enviar Respuesta",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Construir Contexto RAG": {
      "main": [
        [
          {
            "node": "Generar Respuesta con LLM",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Buscar Documentos Similares": {
      "main": [
        [
          {
            "node": "Construir Contexto RAG",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generar Embedding Pregunta": {
      "main": [
        [
          {
            "node": "Buscar Documentos Similares",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1",
    "binaryMode": "separate",
    "availableInMCP": false
  },
  "versionId": "ab8902b9-fc77-4d9a-8896-871a19037980",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "BpyozaHORElkSz9Y",
  "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.

• postgres
• telegramApi

About this workflow

Asistente Conciliación Bancaria. Uses telegramTrigger, telegram, httpRequest, postgres. Event-driven trigger; 6 nodes.

Source: https://github.com/Nel620/analista-virtual-conciliacion/blob/431bca139226d100fcb7957d4dc909735fa6e7e9/n8n/workflow.example.json — original creator credit. Request a take-down →

More Slack & Telegram workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.