AutomationFlowsAI & RAG › Whatsapp AI Assistant with Ollama

Whatsapp AI Assistant with Ollama

WhatsApp AI Assistant with Ollama. Uses ollama, httpRequest. Webhook trigger; 7 nodes.

Webhook trigger★★★★☆ complexityAI-powered7 nodesOllamaHTTP Request
AI & RAG Trigger: Webhook Nodes: 7 Complexity: ★★★★☆ AI nodes: yes Added:

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 →

Download .json
{
  "name": "WhatsApp AI Assistant with Ollama",
  "nodes": [
    {
      "parameters": {
        "path": "whatsapp-webhook",
        "responseMode": "responseNode",
        "options": {}
      },
      "name": "WhatsApp Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 1,
      "position": [
        220,
        300
      ]
    },
    {
      "parameters": {
        "jsCode": "// Extract WhatsApp message data\nconst body = $input.item.json.body;\n\n// Check if it's a WhatsApp message\nif (body && body.object === 'whatsapp_business_account') {\n  try {\n    const entry = body.entry[0];\n    const changes = entry.changes[0];\n    const value = changes.value;\n    \n    if (value.messages && value.messages.length > 0) {\n      const message = value.messages[0];\n      const from = message.from;\n      const messageText = message.text?.body || \"\";\n      \n      // Return processed data\n      return {\n        json: {\n          phone: from,\n          message: messageText,\n          messageId: message.id,\n          whatsappBusinessId: value.metadata.phone_number_id\n        }\n      };\n    }\n  } catch (error) {\n    console.error('Error processing WhatsApp message:', error);\n  }\n}\n\n// Return empty if not a valid message\nreturn { json: { invalid: true } };"
      },
      "name": "Extract Message Data",
      "type": "n8n-nodes-base.code",
      "typeVersion": 1,
      "position": [
        440,
        300
      ]
    },
    {
      "parameters": {
        "conditions": {
          "string": [
            {
              "value1": "={{ $json.invalid }}",
              "operation": "exists"
            }
          ]
        }
      },
      "name": "Is Valid Message?",
      "type": "n8n-nodes-base.if",
      "typeVersion": 1,
      "position": [
        660,
        300
      ]
    },
    {
      "parameters": {
        "content": "=# System Instructions\nYou are a helpful AI assistant responding to users via WhatsApp. Keep your responses concise, friendly, and helpful. If you're asked to do something you can't do, politely explain your limitations.\n\n# User Input\nUser: {{ $json.message }}",
        "model": "llama2:latest",
        "options": {
          "temperature": 0.7,
          "topP": 0.9,
          "topK": 40,
          "maxTokens": 500
        }
      },
      "name": "Generate AI Response",
      "type": "n8n-nodes-base.ollama",
      "typeVersion": 1,
      "position": [
        860,
        220
      ]
    },
    {
      "parameters": {
        "url": "=https://graph.facebook.com/v17.0/{{ $json.whatsappBusinessId }}/messages",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "method": "POST",
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "messaging_product",
              "value": "whatsapp"
            },
            {
              "name": "recipient_type",
              "value": "individual"
            },
            {
              "name": "to",
              "value": "={{ $json.phone }}"
            },
            {
              "name": "type",
              "value": "text"
            },
            {
              "name": "text",
              "value": "={{ {\"preview_url\":false,\"body\":$node[\"Generate AI Response\"].json.output} }}"
            }
          ]
        },
        "options": {
          "redirect": {
            "redirect": {
              "followRedirects": true
            }
          }
        }
      },
      "name": "Send WhatsApp Response",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.1,
      "position": [
        1060,
        220
      ]
    },
    {
      "parameters": {
        "options": {}
      },
      "name": "Webhook Response",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1,
      "position": [
        1280,
        300
      ]
    },
    {
      "parameters": {
        "options": {}
      },
      "name": "Respond to Verification",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1,
      "position": [
        860,
        380
      ]
    }
  ],
  "connections": {
    "WhatsApp Webhook": {
      "main": [
        [
          {
            "node": "Extract Message Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Message Data": {
      "main": [
        [
          {
            "node": "Is Valid Message?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Is Valid Message?": {
      "main": [
        [
          {
            "node": "Generate AI Response",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Respond to Verification",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Generate AI Response": {
      "main": [
        [
          {
            "node": "Send WhatsApp Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Send WhatsApp Response": {
      "main": [
        [
          {
            "node": "Webhook Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Respond to Verification": {
      "main": [
        [
          {
            "node": "Webhook Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": true,
  "settings": {
    "executionOrder": "v1",
    "saveManualExecutions": false,
    "callerPolicy": "workflowsFromSameOwner",
    "errorWorkflow": ""
  },
  "staticData": null,
  "tags": [
    {
      "name": "whatsapp"
    },
    {
      "name": "ollama"
    },
    {
      "name": "ai"
    }
  ],
  "triggerCount": 1,
  "versionId": "",
  "id": "whatsapp-ollama-assistant"
}
Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

WhatsApp AI Assistant with Ollama. Uses ollama, httpRequest. Webhook trigger; 7 nodes.

Source: https://github.com/ThijsdeZeeuw/cloud-local-ngrok/blob/860736ba97cc56d031ed68d017e7042823e59077/examples/whatsapp-bot-workflow.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.

AI & RAG

The Ultimate Scraper for n8n uses Selenium and AI to retrieve any information displayed on a webpage. You can also use session cookies to log in to the targeted webpage for more advanced scraping need

OpenAI Chat, HTTP Request, Information Extractor +1
AI & RAG

z-Api. Uses httpRequest, openAi, redis, postgres. Webhook trigger; 61 nodes.

HTTP Request, OpenAI, Redis +4
AI & RAG

How it works: • Receives WhatsApp messages via webhook from Whapi.Cloud • Routes commands: AI chat (/ai), numeric commands (1-9), or help menu • Sends responses: text, images, documents, videos, conta

HTTP Request, OpenAI
AI & RAG

This workflow will allow you to use OpenAI Assistant API together with a chatting platform. This version is configured to work with Hubspot, however, the Hubspot modules can be replaced by other platf

HTTP Request, Airtable, OpenAI
AI & RAG

This template automates the extraction of structured data from Thai government letters received via LINE or uploaded to Google Drive. It uses Mistral AI for OCR and OpenAI for information extraction,

HTTP Request, Google Drive Trigger, Google Drive +4