Botws13

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": "botws13",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "whatsapp"
      },
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2,
      "position": [
        0,
        0
      ],
      "id": "ec1f5c66-09f3-4d91-89fd-43680809e7ac",
      "name": "Webhook"
    },
    {
      "parameters": {
        "jsCode": "// Validaci\u00f3n y sanitizaci\u00f3n de entrada\nconst input = $input.first().json.body;\n\n// Validar campos requeridos\nif (!input || !input.from || !input.message) {\n  return [{\n    json: {\n      error: 'Campos requeridos faltantes',\n      status: 400\n    }\n  }];\n}\n\n// Sanitizar y validar n\u00famero de tel\u00e9fono\nconst cleanPhone = input.from.replace(/\\D/g, '');\n\n// Detectar intenci\u00f3n del mensaje\nconst intents = {\n  pregunta: /\\?$/,\n  saludo: /^(hola|buenos d\u00edas|buenas tardes|buenas noches)/i,\n  despedida: /(adi\u00f3s|chao|hasta luego|nos vemos)/i,\n  emergencia: /(urgente|emergencia|ayuda|socorro)/i\n};\n\nconst intent = Object.entries(intents).find(([_, regex]) => \n  regex.test(input.message)\n)?.[0] || 'conversacion';\n\n// Timestamp en formato ISO\nconst timestamp = new Date().toISOString();\n\nreturn [{\n  json: {\n    sender: cleanPhone,\n    mensaje: input.message.trim(),  // Cambiado de message a mensaje\n    intent,\n    timestamp,\n    priority: intent === 'emergencia' ? 'high' : 'normal'\n  }\n}];"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        180,
        -20
      ],
      "id": "047ce904-6f8e-403b-af0c-523cddc10dac",
      "name": "Input Validation"
    },
    {
      "parameters": {
        "model": "mistral:latest",
        "temperature": 0.7,
        "maxTokens": 2000,
        "topP": 0.95,
        "frequencyPenalty": 0.5,
        "presencePenalty": 0.5
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOllama",
      "typeVersion": 1,
      "position": [
        700,
        260
      ],
      "id": "eecb615d-bc19-46bc-bb32-f0740669059b",
      "name": "Ollama Chat Model",
      "credentials": {
        "ollamaApi": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "sessionIdType": "customKey",
        "sessionKey": "={{ $json.sender }}",
        "tableName": "interacciones",
        "contextWindowLength": 5,
        "summarizeAfter": 15,
        "columnNames": {
          "sessionId": "numero_telefono",
          "userInput": "mensaje",
          "botResponse": "respuesta",
          "timestamp": "fecha_creacion"
        }
      },
      "type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
      "typeVersion": 1.3,
      "position": [
        520,
        200
      ],
      "id": "67846270-0ce4-4a8d-be2f-8f91432cc0e5",
      "name": "Postgres Chat Memory",
      "credentials": {
        "postgres": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "Eres un asistente emp\u00e1tico y profesional. Analiza el siguiente contexto:\n\nUsuario: {{$json.sender}}\nIntenci\u00f3n detectada: {{$json.intent}}\nPrioridad: {{$json.priority}}\nHistorial reciente: {{$('Postgres Chat Memory').item.json.chatHistory}}\n\nMensaje actual: {{$json.mensaje}}\n\nResponde de manera emp\u00e1tica, profesional y concisa, manteniendo el contexto de la conversaci\u00f3n.",
        "options": {
          "temperature": 0.7,
          "maxTokens": 500
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.9,
      "position": [
        700,
        60
      ],
      "id": "ai-response-generator",
      "name": "AI Response Generator"
    },
    {
      "parameters": {
        "jsCode": "// Procesamiento de respuesta\nconst response = $input.first().json;\n\n// Validaci\u00f3n de respuesta\nif (!response || !response.output) {\n  return [{\n    json: {\n      error: 'Respuesta inv\u00e1lida del modelo',\n      status: 500\n    }\n  }];\n}\n\n// Formateo y limpieza\nlet mensaje = response.output\n  .replace(/[\\n\\r\\t]/g, ' ')\n  .replace(/\\s{2,}/g, ' ')\n  .trim();\n\n// Logging y m\u00e9tricas\nconst metrics = {\n  responseTime: Date.now() - new Date($json.timestamp).getTime(),\n  messageLength: mensaje.length,\n  intent: $json.intent,\n  priority: $json.priority\n};\n\nreturn [{\n  json: {\n    mensaje,\n    metrics,\n    sender: $json.sender,\n    timestamp: new Date().toISOString()\n  }\n}];"
      },
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        840,
        60
      ],
      "id": "response-processor",
      "name": "Response Processor"
    },
    {
      "parameters": {
        "method": "POST",
        "url": "http://host.docker.internal:3080/api/n8n-webhook",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "x-webhook-token",
              "value": "portIvan2015"
            },
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={\n  \"action\": \"send_message\",\n  \"data\": {\n    \"phone\": \"{{ $json.sender }}\",\n    \"message\": \"{{ $json.mensaje }}\"\n  },\n  \"metadata\": {\n    \"intent\": \"{{ $json.metrics.intent }}\",\n    \"priority\": \"{{ $json.metrics.priority }}\",\n    \"responseTime\": {{ $json.metrics.responseTime }}\n  }\n}"
      },
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        1120,
        60
      ],
      "id": "message-sender",
      "name": "Message Sender"
    }
  ],
  "connections": {
    "Webhook": {
      "main": [
        [
          "Input Validation"
        ]
      ]
    },
    "Input Validation": {
      "main": [
        [
          "Postgres Chat Memory"
        ]
      ]
    },
    "Postgres Chat Memory": {
      "main": [
        [
          "AI Response Generator"
        ]
      ],
      "ai_memory": [
        [
          "AI Response Generator"
        ]
      ]
    },
    "Ollama Chat Model": {
      "ai_languageModel": [
        [
          "AI Response Generator"
        ]
      ]
    },
    "AI Response Generator": {
      "main": [
        [
          "Response Processor"
        ]
      ]
    },
    "Response Processor": {
      "main": [
        [
          "Message Sender"
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "tags": [
    "chatbot",
    "production"
  ]
}

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.

• ollamaApi
• postgres

About this workflow

botws13. Uses lmChatOllama, memoryPostgresChat, agent, httpRequest. Webhook trigger; 7 nodes.

Source: https://github.com/oscivan84/apoyoEmocional/blob/a4728b9fc8fd0bdeb073d23a2e1420721e190c29/n8nv2.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

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