Adrian This workflow corresponds to n8n.io template #6170 — we link there as the canonical source.
This workflow follows the Agent → Documentdefaultdataloader recipe pattern — see all workflows that pair these two integrations.
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 →
{
"id": "5yOJSx1X0M3Q2VFM",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "n8n__demo__WAMM_Assistent_Pinecode",
"tags": [],
"nodes": [
{
"id": "1e7bc1dc-d577-4a46-8cfb-ab3f7b918922",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
320,
0
],
"parameters": {
"text": "={{ $json.body.data.message_text }}",
"options": {
"systemMessage": "=You are Alex, a warm and friendly assistant. Talk naturally like a good friend would - never mention searching or looking up information. Just remember and respond naturally.\n\nAlways respond in the user's language (note: \u201csalut\u201d is in Romanian.). Be conversational, not robotic.\n\nTalking to: {{ $json.body.data.source_number }}\nTime: {{ $now.toISO() }}"
},
"promptType": "define"
},
"typeVersion": 1.8
},
{
"id": "13fa7ec6-fdca-43ed-b5e7-5aae02b61fa6",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"position": [
100,
-240
],
"parameters": {
"path": "1c9432a6-f982-4102-ad0e-39ec15876b0a",
"options": {},
"httpMethod": "POST"
},
"typeVersion": 2
},
{
"id": "ed764250-105f-4a87-beb7-070c42473340",
"name": "WAMM: Send Message",
"type": "n8n-nodes-wamm.wammpro",
"position": [
880,
-240
],
"parameters": {
"phone": "={{ $('Webhook').item.json.body.data.source_number }}",
"message": "={{ $json.output }}",
"instanceId": "68xxxxxxxxx3F"
},
"credentials": {
"wammApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "cb99b578-c02e-4469-b6b5-3ac95b9004f1",
"name": "Google Gemini Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
"position": [
100,
360
],
"parameters": {
"options": {},
"modelName": "models/gemini-2.5-flash"
},
"credentials": {
"googlePalmApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "01bddfd1-4a4e-42b9-9d3c-fa2d1670bf94",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
960,
640
],
"parameters": {
"model": "text-embedding-3-large",
"options": {
"dimensions": 3072
}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "90ee2d53-da04-4105-b66d-7234ac13baac",
"name": "Processing data for Pinecone",
"type": "n8n-nodes-base.code",
"position": [
1320,
0
],
"parameters": {
"jsCode": "// Preg\u0103te\u0219te datele pentru salvare \u00een memorie\nconst aiAgentOutput = $('AI Agent').first().json.output;\nconst webhookData = $('Webhook').first().json.body.data;\n\n// Creeaz\u0103 textul conversa\u021biei\nconst conversationText = `Utilizator (${webhookData.source_number}): ${webhookData.message_text}\nAsistent: ${aiAgentOutput}\nTimestamp: ${new Date().toISOString()}`;\n\n// Returneaz\u0103 documentul \u00een formatul cerut de Pinecone\nreturn {\n json: {\n pageContent: conversationText,\n metadata: {\n user_number: webhookData.source_number,\n timestamp: new Date().toISOString()\n }\n }\n};"
},
"typeVersion": 2
},
{
"id": "94d3df7d-4680-46b7-9886-1439958a26c4",
"name": "Reading from Pinecone (from knowledge)",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
260,
360
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolName": "reading_knowledge",
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "knowledge",
"cachedResultName": "knowledge"
},
"toolDescription": "Use this tool to search the general knowledge base and standard answers to frequently asked questions."
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "f89342bf-eebc-40e5-8442-a228bc250a7d",
"name": "Reading from Pinecone (at phone number)",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
580,
360
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolName": "reading_historywa",
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "historywa",
"cachedResultName": "historywa"
},
"toolDescription": "Use this tool to search past conversation history with this user ( {{ $('Webhook').item.json.body.data.source_number }} ) and find relevant information to answer the user\u2019s current question."
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "b474ec47-e34b-4065-a83b-a9a55452346c",
"name": "Pinecone Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePinecone",
"position": [
1600,
0
],
"parameters": {
"mode": "insert",
"options": {},
"pineconeIndex": {
"__rl": true,
"mode": "list",
"value": "historywa",
"cachedResultName": "historywa"
}
},
"credentials": {
"pineconeApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "b0e4114e-9775-4cce-a151-4a558dc97733",
"name": "Default Data Loader1",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
1480,
340
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "user_number",
"value": "={{ $json.metadata.user_number }}"
},
{
"name": "timestamp",
"value": "={{ $json.metadata.timestamp }}"
}
]
}
},
"jsonData": "={{ $json.pageContent }}",
"jsonMode": "expressionData"
},
"typeVersion": 1
},
{
"id": "affac18f-f2e6-42b2-8b75-f90a305935ce",
"name": "Recursive Character Text Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1560,
600
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "cd0c6f62-2e7c-405c-84fe-204ddf4ba51e",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-760,
-760
],
"parameters": {
"width": 760,
"height": 1640,
"content": "# \ud83e\udd16 WAMM AI Assistant with Pinecone Memory - n8n Template\n\n## \ud83d\udccb Description\n\nThis template creates an intelligent AI assistant for WhatsApp that can:\n- **Respond naturally** to messages using Google Gemini AI\n- **Remember previous conversations** for each user\n- **Access a knowledge base** for answering frequently asked questions\n- **Automatically save** all conversations for long-term memory\n\n## \ud83d\udee0\ufe0f Requirements\n\n### 1. **WAMM.pro Account** (FREE tier available)\n- **What is WAMM.pro?** - A platform that enables WhatsApp automation using proprietary API technology\n- **Free tier:** 50 messages/month\n- **PRO tier:** Unlimited messages + advanced features\n- **Link:** [wamm.pro](https://wamm.pro)\n\n### 2. **Pinecone Account** (for AI memory)\n- For storing conversations and knowledge base\n- Free tier available\n\n### 3. **Google AI Account** (for Gemini)\n- For the conversational AI model\n\n### 4. **OpenAI Account** (for embeddings)\n- For generating memory vectors\n\n## \ud83d\ude80 Step-by-step Setup\n\n### **Step 1: WAMM.pro Configuration**\n### **Step 2: Webhook Configuration**\n### **Step 3: Pinecone Configuration**\n\n### **Step 4: n8n Configuration**\n\n1. **Configure credentials:**\n - **WAMM:** Instance ID + Access Token\n - **Pinecone:** API Key\n - **Google Gemini:** API Key \n - **OpenAI:** API Key for embeddings\n\n### **Available AI Tools:**\n\n1. **Memory Tool** - Searches previous conversations with the user\n2. **Knowledge Tool** - Searches the general knowledge base\n\n### **Special Features:**\n\n- **Natural conversations** - AI doesn't mention \"searching history\"\n- **Persistent context** - Remembers names, preferences, previous conversations\n- **User language detection** - Automatically responds in user's language\n- **Organized memory** - Each user has their own memory space\n\n## \ud83d\udcca Benefits\n\n\u2705 **Zero maintenance** - Runs automatically \n\u2705 **Scalable** - Supports multiple users simultaneously \n\u2705 **Intelligent memory** - Uses similarity search for relevant context \n\u2705 **Extensible** - Easy to add new features \n\u2705 **Cost-effective** - Free tiers available for all services \n"
},
"typeVersion": 1
},
{
"id": "6c179b6f-5a31-4a49-8a4a-933686892234",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
640,
-760
],
"parameters": {
"width": 540,
"height": 720,
"content": "# WAMM configuration\n\n### **Step 1: WAMM.pro Configuration**\n\n1. **Create account** at [wamm.pro](https://wamm.pro)\n2. **Account Manager** \u2192 **Add WhatsApp profile**\n3. **Scan QR code** with your WhatsApp\n4. **Note down:** `Instance ID` and `Access Token`\n\n### **Step 2: Webhook Configuration**\n\n1. **In WAMM.pro:** Integrations \u2192 Webhooks \u2192 Messages Webhooks\n2. **Add Webhook** with the n8n URL\n3. **Required configuration:**\n - **From others:** \u2705 Relevant + \u2705 Without media + \u2705 Exclude no text\n - **To others:** \u2705 Relevant + \u2705 Without media + \u2705 Exclude no text \n - **To myself:** \u2705 None (to avoid responding to own messages)"
},
"typeVersion": 1
},
{
"id": "62a9577a-9cd6-49fa-ac36-f3a9b364569b",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
240,
320
],
"parameters": {
"width": 1560,
"height": 560,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n# Pinecone configuration\n\n### **Step 3: Pinecone Configuration**\n\n1. **Create 2 indexes:**\n - `historywa` - for conversation memory\n - `knowledge` - for knowledge base\n2. **Index settings:**\n - **Dimensions:** 3072\n - **Metric:** cosine\n - **Embedding model:** text-embedding-3-large"
},
"typeVersion": 1
},
{
"id": "8ece35d4-654d-4167-aa95-020f8d23194d",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1520,
-760
],
"parameters": {
"width": 400,
"height": 720,
"content": "## \ud83c\udfaf Use Cases\n\n- **Automated customer support** with memory\n- **Personal assistant** for WhatsApp \n- **Business chatbot** with specific knowledge\n- **Conversation automation** with persistent context\n\n## \ud83d\udd12 Security\n\n- **Data** stored in Pinecone as vector embeddings\n- **No plain text** message storage \n- **Each user** has separate memory space\n- **API keys** secured in n8n credentials\n\n## \ud83d\udcc8 Possible Extensions\n\n- **CRM** integrations\n- **Scheduling** and reminders\n- **Advanced multi-language** support \n- **Analytics** and conversation reports\n- **Custom knowledge bases** per user\n\n---\n\n**\ud83d\udca1 Tip:** For optimal results, populate the knowledge base with frequently asked questions specific to your business!"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "83064b5e-171e-4c8c-8fc5-378fc3eadd8b",
"connections": {
"Webhook": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"AI Agent": {
"main": [
[
{
"node": "WAMM: Send Message",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Reading from Pinecone (from knowledge)",
"type": "ai_embedding",
"index": 0
},
{
"node": "Reading from Pinecone (at phone number)",
"type": "ai_embedding",
"index": 0
},
{
"node": "Pinecone Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"WAMM: Send Message": {
"main": [
[
{
"node": "Processing data for Pinecone",
"type": "main",
"index": 0
}
]
]
},
"Default Data Loader1": {
"ai_document": [
[
{
"node": "Pinecone Vector Store",
"type": "ai_document",
"index": 0
}
]
]
},
"Google Gemini Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Processing data for Pinecone": {
"main": [
[
{
"node": "Pinecone Vector Store",
"type": "main",
"index": 0
}
]
]
},
"Recursive Character Text Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader1",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Reading from Pinecone (from knowledge)": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Reading from Pinecone (at phone number)": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
}
}
}
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.
googlePalmApiopenAiApipineconeApiwammApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This template creates an intelligent AI assistant for WhatsApp that can: Respond naturally to messages using Google Gemini AI Remember previous conversations for each user Access a knowledge base for answering frequently asked questions Automatically save all conversations for…
Source: https://n8n.io/workflows/6170/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This n8n template automatically classifies incoming emails (Sales, Support, Internal, Finance, Promotions) and routes them to a dedicated OpenAI LLM Agent for processing. Depending on the category, th
OpenAI, Gmail, Text Classifier +16
HeyDinastia. Uses executeCommand, httpRequest, youTube, postgres. Webhook trigger; 66 nodes.
Execute Command, HTTP Request, YouTube +15
Unlock unparalleled efficiency and elevate customer satisfaction with our AI-Powered Customer Support: Email, Knowledge Base & Human Escalation Automation template. This sophisticated n8n workflow is
OpenAI Chat, Agent, Gmail +11
Enable smart, real-time answers in your WhatsApp groups using a custom webhook, Pinecone vector database, and no Facebook Business setup.
Document Default Data Loader, Text Splitter Recursive Character Text Splitter, OpenAI Embeddings +6
This workflow creates a WhatsApp chatbot that answers questions using your own PDFs through RAG (Retrieval-Augmented Generation). Every time you upload a document to Google Drive, it is processed into
Google Drive Trigger, Google Drive, Pinecone Vector Store +9