Apologies for the newbie question here.
I have created a webhook for whatsapp and get the correct response when testing in get mode. I then duplicate the node and change the webhook to post and at the same time update the Facebook app (for whatsapp) to use the production url.
This works in test mode but even after moving the workflow to active no executions trigger.
What is the error message (if any)?
Please share your workflow
{
“nodes”: [
{
“parameters”: {
“name”: “user_documents”,
“description”: “Contains all the user’s documents that you can check for context to answer user questions.”,
“topK”: 10
},
“id”: “83d5acd3-c69c-4387-a105-700d06eeeb52”,
“name”: “Retrieve Documents”,
“type”: “@n8n/n8n-nodes-langchain.toolVectorStore”,
“typeVersion”: 1,
“position”: [
360,
60
]
},
{
“parameters”: {
“agent”: “conversationalAgent”,
“promptType”: “define”,
“text”: "={{ $(‘Respond’).item.json.body.entry[0].changes[0].value.messages[0].text.body }} ",
“options”: {
“systemMessage”: “You are an AI-powered assistant for a kayaking and pedal boat company based in Cape Town, South Africa. Your primary goal is to assist customers by providing accurate and helpful information about the services offered, bookings, and general support. Use the provided knowledge base (retrieved documents) to answer questions with precision and fiendliness. \n\nGuidelines:\n1. Services Information:\n - Provide detailed descriptions of services offered, including availability.\n - Highlight key selling points and suitability to different age groups. \n - Mention availability, pricing, and promotions if applicable.\n\n2. Customer Service:\n - Respond politely and professionally to all inquiries.\n - If a question is unclear, ask for clarification to provide the best possible answer.\n - For booking-related questions (e.g., cancellations, refunds, or postponements), guide customers on how to proceed using the companies systems.\n\n3. Knowledge Base Usage:\n - Always reference the provided knowledge base (retrieved documents) to ensure accuracy.\n - If the knowledge base does not contain relevant information, inform the customer and offer to forward the query to a manager.\n\n4. Tone and Style:\n - Use a friendly, approachable, and professional tone.\n - Avoid technical jargon unless the customer demonstrates familiarity with the topic.\n - Keep responses concise but informative.\n\nExample Interactions:\n1. Service Inquiry:\n - Customer: "What is the difference between a kayak tour and hiring a kayak by the hour?"\n - AI: "The 1,5 hr kayak tour when the conditions are very good (approx. 100 days a year) operates between Sep and May. If you are lucky enough to join us on one of these tours, it will be one of your most memorable experiences in Cape Town. The tour is lead by a well trained and experienced guide. The kayak rentals allow you to take a kayak out on Clifton beach on your own and enjoy the bay at your leisure. "\n\n2. Booking Support:\n - Customer: "What is your Cancellation, Rescheduling and Postponement Policy?"\n - AI: "If we postpone or reschedule a trip we offer a full refund to people who are not able to reschedule.\n\nIn the past we have had people who postponed their trips several times last minute on a whim of theirs. This is very frustrating for us as we book the amount of guides needed in advance, we still need to pay them and we lose the income on those spaces that sometimes could have been filled by other customers. In order to discourage people from doing this to us, we have implemented the following cancellation policy:\n\nMore than 24 hours before trip:\nCancellation: Full refund less R100 admin fee.\nRescheduling: Free. It must be done by WhatsApp or email more than 24 before the start of the booked trip.\nLess than 24 hours before trip: No refund for cancellations and no rescheduling allowed."\n\nLimitations:\n- If the question is outside the scope of the knowledge base or requires human intervention, inform the customer and provide contact details for the appropriate department.\n- Do not provide speculative or unverified information. Always rely on the knowledge base or direct the customer to official resources.\n”
}
},
“id”: “8c501d54-99e5-427a-bcc6-e73ef1468ccf”,
“name”: “RAG AI Agent”,
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 1.6,
“position”: [
-300,
60
]
},
{
“parameters”: {
“tableName”: {
“__rl”: true,
“value”: “documents”,
“mode”: “list”,
“cachedResultName”: “documents”
},
“options”: {
“queryName”: “match_documents”
}
},
“id”: “f6f33385-9979-46fb-9a84-1682884a5a76”,
“name”: “Supabase Vector Store”,
“type”: “@n8n/n8n-nodes-langchain.vectorStoreSupabase”,
“typeVersion”: 1,
“position”: [
260,
260
],
“credentials”: {
“supabaseApi”: {
“id”: “6uV7DTzGqfVr7dbG”,
“name”: “Supabase account 2”
}
}
},
{
“parameters”: {
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.embeddingsOpenAi”,
“typeVersion”: 1.2,
“position”: [
360,
420
],
“id”: “29cc5701-8ef4-4a45-908a-e9e3beae6fa2”,
“name”: “Embeddings OpenAI”,
“credentials”: {
“openAiApi”: {
“id”: “FdXbEo6F1kt5c3VN”,
“name”: “OpenAi account”
}
}
},
{
“parameters”: {
“model”: {
“__rl”: true,
“mode”: “list”,
“value”: “gpt-4o-mini”
},
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatOpenAi”,
“typeVersion”: 1.2,
“position”: [
580,
320
],
“id”: “adabbe50-89a8-433a-804f-821d16c9ca1e”,
“name”: “OpenAI Chat Model1”,
“credentials”: {
“openAiApi”: {
“id”: “FdXbEo6F1kt5c3VN”,
“name”: “OpenAi account”
}
}
},
{
“parameters”: {
“conditions”: {
“options”: {
“caseSensitive”: true,
“leftValue”: “”,
“typeValidation”: “loose”,
“version”: 2
},
“conditions”: [
{
“id”: “0f72df1b-9fa6-4c13-9038-f4e9c7d14461”,
“leftValue”: “={{ $json.body.entry[0].changes[0].value.messages }}”,
“rightValue”: “”,
“operator”: {
“type”: “string”,
“operation”: “exists”,
“singleValue”: true
}
}
],
“combinator”: “and”
},
“looseTypeValidation”: true,
“options”: {}
},
“type”: “n8n-nodes-base.if”,
“typeVersion”: 2.2,
“position”: [
-820,
120
],
“id”: “b04c5577-4c60-42b5-9ef0-e4828f006b19”,
“name”: “Is Message?”
},
{
“parameters”: {
“operation”: “send”,
“phoneNumberId”: “=578544348678556”,
“recipientPhoneNumber”: “={{ $(‘Is Message?’).item.json.body.entry[0].changes[0].value.contacts[0].wa_id }}”,
“textBody”: “={{ $json.output }}”,
“additionalFields”: {}
},
“type”: “n8n-nodes-base.whatsApp”,
“typeVersion”: 1,
“position”: [
80,
140
],
“id”: “ad4e0a19-2ce9-4c5e-be20-f797205cef77”,
“name”: “Send”,
“webhookId”: “e4d9d1dd-dc57-4fe5-8b12-b20d8bee982d”,
“credentials”: {
“whatsAppApi”: {
“id”: “JnXoQx3aiAPNtsEB”,
“name”: “WhatsApp account”
}
}
},
{
“parameters”: {
“sessionIdType”: “customKey”,
“sessionKey”: “={{ $(‘Respond’).item.json.body.entry[0].changes[0].value.contacts[0].wa_id }}”
},
“type”: “@n8n/n8n-nodes-langchain.memoryBufferWindow”,
“typeVersion”: 1.3,
“position”: [
-180,
340
],
“id”: “9c327a1a-dc02-4ae9-b441-6cf02d26d4d3”,
“name”: “Window Buffer Memory”
},
{
“parameters”: {
“model”: {
“__rl”: true,
“mode”: “list”,
“value”: “claude-3-7-sonnet-20250219”,
“cachedResultName”: “Claude 3.7 Sonnet”
},
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatAnthropic”,
“typeVersion”: 1.3,
“position”: [
-460,
280
],
“id”: “b2f9352b-de6b-4948-938b-6d29f840598c”,
“name”: “Anthropic Chat Model”,
“credentials”: {
“anthropicApi”: {
“id”: “HvNQgFr8GDaeADAQ”,
“name”: “Anthropic account”
}
}
},
{
“parameters”: {
“httpMethod”: “POST”,
“path”: “ec92d946-bec4-4053-995d-e2f5c6d14342”,
“options”: {}
},
“type”: “n8n-nodes-base.webhook”,
“typeVersion”: 2,
“position”: [
-1040,
120
],
“id”: “85c94730-2486-4ad7-9b09-0c1fa4b2780a”,
“name”: “Respond”,
“webhookId”: “ec92d946-bec4-4053-995d-e2f5c6d14342”
}
],
“connections”: {
“Retrieve Documents”: {
“ai_tool”: [
[
{
“node”: “RAG AI Agent”,
“type”: “ai_tool”,
“index”: 0
}
]
]
},
“RAG AI Agent”: {
“main”: [
[
{
“node”: “Send”,
“type”: “main”,
“index”: 0
}
]
]
},
“Supabase Vector Store”: {
“ai_vectorStore”: [
[
{
“node”: “Retrieve Documents”,
“type”: “ai_vectorStore”,
“index”: 0
}
]
]
},
“Embeddings OpenAI”: {
“ai_embedding”: [
[
{
“node”: “Supabase Vector Store”,
“type”: “ai_embedding”,
“index”: 0
}
]
]
},
“OpenAI Chat Model1”: {
“ai_languageModel”: [
[
{
“node”: “Retrieve Documents”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Is Message?”: {
“main”: [
[
{
“node”: “RAG AI Agent”,
“type”: “main”,
“index”: 0
}
],
]
},
“Window Buffer Memory”: {
“ai_memory”: [
[
{
“node”: “RAG AI Agent”,
“type”: “ai_memory”,
“index”: 0
}
]
]
},
“Anthropic Chat Model”: {
“ai_languageModel”: [
[
{
“node”: “RAG AI Agent”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Respond”: {
“main”: [
[
{
“node”: “Is Message?”,
“type”: “main”,
“index”: 0
}
]
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “80e8e5e6c275ad20a018cfeebf67e4c156c7085889854ec684b6bbdb08c38f30”
}
}
Share the output returned by the last node
Information on your n8n setup
- n8n version: 1.84.1