Zain Ali This workflow corresponds to n8n.io template #6699 — we link there as the canonical source.
This workflow follows the Agent → Chat Trigger 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": "npjeGNOHqwXLz1AX",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Product Recommendation RAG",
"tags": [],
"nodes": [
{
"id": "ab7e0eb2-1a72-4dee-8b6a-c6a836fce257",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1360,
-16
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "8882b64e-5caf-4a05-a7f3-d78b93d9f30c",
"name": "RAG Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-896,
160
],
"parameters": {},
"typeVersion": 1.7
},
{
"id": "3788a0b5-4f73-4bd1-bdca-b659a49710f5",
"name": "When clicking \u2018Execute workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
176,
192
],
"parameters": {},
"typeVersion": 1
},
{
"id": "ec896b04-a5cc-4cc4-b7ce-3b552e2fe258",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-96,
-32
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "cc6b47eb-87b1-44a8-8319-c5a0254b83ba",
"name": "Qdrant Vector Database",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
256,
544
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "6b5d2b60-f65a-4075-b5a6-415c1fb1dcc8",
"name": "Create Embedding",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
192,
752
],
"parameters": {},
"typeVersion": 1.2
},
{
"id": "9db5b8ae-a9c9-4465-a426-71bb9cda333d",
"name": "Set Data Properly in vector database",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
384,
784
],
"parameters": {},
"typeVersion": 1
},
{
"id": "186a5ebf-57fd-4aa4-8031-89c503603431",
"name": "Split text into chunks",
"type": "@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter",
"position": [
464,
960
],
"parameters": {},
"typeVersion": 1
},
{
"id": "b969d3a6-f663-46bd-9207-666861aa4e49",
"name": "Create Embedding2",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-560,
640
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "37d1974e-0e65-441d-9a22-977035e6e1af",
"name": "Loop over each product",
"type": "n8n-nodes-base.splitInBatches",
"position": [
800,
192
],
"parameters": {},
"typeVersion": 3
},
{
"id": "d6cff138-2513-4acd-bf37-3e6691b3cf07",
"name": "Get data from Qdrant database",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
-656,
464
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "bf1668c5-cc6a-4ab3-9f97-e9cd701df1ed",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-1120,
160
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "e05d5065-dec0-435e-a65d-e4f831541388",
"name": "OpenAI LLM",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-976,
384
],
"parameters": {},
"typeVersion": 1
},
{
"id": "e14dc3fe-f0e4-479b-ad7e-d5477d478e20",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
96,
96
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "95f86512-e0f7-48e0-bb44-9b727ecb320a",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
96,
448
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "672df8d1-81bd-4709-b7be-76cf04c92593",
"name": "Store Chats",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-816,
384
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "28d9b9f0-0b67-4828-b502-71e6f7c55ad8",
"name": "Get all products",
"type": "n8n-nodes-base.googleSheets",
"position": [
416,
192
],
"parameters": {},
"typeVersion": 4.6
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "3cc040a0-9a81-4134-ae19-3efbfb3a8133",
"connections": {
"RAG Agent": {
"main": [
[]
]
},
"OpenAI LLM": {
"ai_languageModel": [
[
{
"node": "RAG Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Store Chats": {
"ai_memory": [
[
{
"node": "RAG Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Create Embedding": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Database",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Get all products": {
"main": [
[
{
"node": "Loop over each product",
"type": "main",
"index": 0
}
]
]
},
"Create Embedding2": {
"ai_embedding": [
[
{
"node": "Get data from Qdrant database",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Loop over each product": {
"main": [
[],
[
{
"node": "Qdrant Vector Database",
"type": "main",
"index": 0
}
]
]
},
"Qdrant Vector Database": {
"main": [
[
{
"node": "Loop over each product",
"type": "main",
"index": 0
}
]
]
},
"Split text into chunks": {
"ai_textSplitter": [
[
{
"node": "Set Data Properly in vector database",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "RAG Agent",
"type": "main",
"index": 0
}
]
]
},
"Get data from Qdrant database": {
"ai_tool": [
[
{
"node": "RAG Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Set Data Properly in vector database": {
"ai_document": [
[
{
"node": "Qdrant Vector Database",
"type": "ai_document",
"index": 0
}
]
]
},
"When clicking \u2018Execute workflow\u2019": {
"main": [
[
{
"node": "Get all products",
"type": "main",
"index": 0
}
]
]
}
}
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow is perfect for: Healthcare ecommerce businesses that want to automate product recommendations. Founders or developers building an AI assistant using retrieval-augmented generation (RAG) with product data. Anyone wanting to combine OpenAI, Qdrant vector search, and…
Source: https://n8n.io/workflows/6699/ — 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.
Chat with docs - 5minAI New version. Uses httpRequest, documentDefaultDataLoader, textSplitterRecursiveCharacterTextSplitter, embeddingsOpenAi. Event-driven trigger; 62 nodes.
I prepared a detailed guide that illustrates the entire process of building an AI agent using Supabase and Google Drive within N8N workflows.
OIL Rag. Uses lmChatOpenAi, embeddingsOpenAi, agent, telegramTrigger. Event-driven trigger; 53 nodes.
Code Extractfromfile. Uses manualTrigger, sort, httpRequest, compression. Event-driven trigger; 50 nodes.
🤖 AI Powered RAG Chatbot for Your Docs + Google Drive + Gemini + Qdrant. Uses documentDefaultDataLoader, textSplitterTokenSplitter, vectorStoreQdrant, splitInBatches. Event-driven trigger; 50 nodes.