Zain Ali This workflow corresponds to n8n.io template #5908 — 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": "6m6Tp8bUVb0t6lwo",
"name": "Email RAG for new Emails",
"tags": [
{
"id": "PNmVCFjr9sq0xind",
"name": "RAG",
"createdAt": "2025-07-12T09:30:51.202Z",
"updatedAt": "2025-07-12T09:30:51.202Z"
},
{
"id": "3Jr6wxDndYE0FaUt",
"name": "email",
"createdAt": "2025-07-12T10:08:56.337Z",
"updatedAt": "2025-07-12T10:08:56.337Z"
}
],
"nodes": [
{
"id": "a896498a-dc44-4d77-8268-7f7001510974",
"name": "Gmail Trigger",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
740,
340
],
"parameters": {
"filters": {},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
}
},
"typeVersion": 1.2
},
{
"id": "7fa7e6b4-ea5e-4716-be0e-58b96458ec0d",
"name": "Get Mail Data",
"type": "n8n-nodes-base.gmail",
"position": [
960,
340
],
"parameters": {
"simple": false,
"options": {},
"messageId": "={{ $json.id }}",
"operation": "get"
},
"typeVersion": 2.1
},
{
"id": "bce4a290-a71c-4277-9381-3cf86867341e",
"name": "Recursive Character Text Splitter2",
"type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter",
"position": [
1460,
700
],
"parameters": {
"options": {
"splitCode": "markdown"
},
"chunkSize": 2000,
"chunkOverlap": 200
},
"typeVersion": 1
},
{
"id": "71ae9619-51ae-4c9a-8697-031725d037af",
"name": "Embeddings OpenAI3",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
1080,
620
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "9e7bd487-f657-4522-9f29-e937f604fff0",
"name": "Enhanced Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
1380,
540
],
"parameters": {
"options": {
"metadata": {
"metadataValues": [
{
"name": "=data_source",
"value": "=gmail"
},
{
"name": "=created_at",
"value": "={{ $json.date }}"
}
]
}
},
"jsonData": "=Email details:\nDate: {{ $json.headers.date }}\n\nFrom Email: {{ $json.from.value[0].address }}\nFrom Name: {{ $json.from.value[0].name }}\n\nTo Email: {{ $json.to.value[0].address }}\n\nEmail Subject:\n{{ $json.subject }}\n\nEmail body:\n{{ $json.text }}",
"jsonMode": "expressionData"
},
"typeVersion": 1
},
{
"id": "251eaeab-ec58-48ad-b51c-556c739ba777",
"name": "Postgres PGVector Store3",
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"position": [
1220,
340
],
"parameters": {
"mode": "insert",
"options": {},
"tableName": "emails_vector_history"
},
"typeVersion": 1.1
},
{
"id": "c0930431-754d-4f87-bf44-6415a816aa7d",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
680,
120
],
"parameters": {
"color": 4,
"width": 1200,
"height": 740,
"content": "## Watch Trigger (Email) - New Email\n## Get new Email -> Extract the text -> Add to Vector Store"
},
"typeVersion": 1
},
{
"id": "c6abb6a2-bc2a-4b2c-98c8-4de628c2776d",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-60,
540
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "fa5ca8d4-5997-4e77-8ab3-f0efe560042d",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-380,
120
],
"parameters": {
"width": 902,
"height": 928,
"content": "## RAG AI Agent\n\nThis powerful n8n workflow creates an intelligent email search and query system using RAG (Retrieval-Augmented Generation) technology. The system automatically ingests Gmail emails into a vector database and provides conversational AI-powered search capabilities through a chat interface"
},
"typeVersion": 1
},
{
"id": "99153412-5aa8-4ab0-918e-172802fc8590",
"name": "New RAG Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
60,
320
],
"parameters": {
"options": {
"systemMessage": "=You are a helpful assistant that will get data from RAG and send a good response to user.\n\nToday date is this if user ask for dated or latest data: {{ $now }}"
}
},
"typeVersion": 1.7
},
{
"id": "00e80343-3f3c-4fed-93d9-213435012df7",
"name": "Postgres PGVector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStorePGVector",
"position": [
240,
640
],
"parameters": {
"mode": "retrieve-as-tool",
"topK": 5,
"options": {},
"toolName": "emails_vector_search",
"tableName": "emails_vector_history",
"toolDescription": "Call this tool to perform a vector embeddings search in my e-mail database. For time-specific queries:\n1. ALWAYS include the time frame in your query (e.g., \"interviews scheduled after April 27, 2025\" or \"interviews for next week April 28-May 4, 2025\")\n2. For future events, explicitly mention \"future\" or \"upcoming\" in your query"
},
"typeVersion": 1.1
},
{
"id": "2c39ec49-ac2b-42bc-b176-7f15a712c6b7",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
200,
800
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "e569097d-79b8-4648-86d5-67298c2a25d6",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-220,
320
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "13c464b8-66a1-4503-b853-4b9ae2365146",
"connections": {
"Get Mail Data": {
"main": [
[
{
"node": "Postgres PGVector Store3",
"type": "main",
"index": 0
}
]
]
},
"Gmail Trigger": {
"main": [
[
{
"node": "Get Mail Data",
"type": "main",
"index": 0
}
]
]
},
"New RAG Agent": {
"main": [
[]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Postgres PGVector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "New RAG Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Embeddings OpenAI3": {
"ai_embedding": [
[
{
"node": "Postgres PGVector Store3",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Postgres PGVector Store": {
"ai_tool": [
[
{
"node": "New RAG Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "New RAG Agent",
"type": "main",
"index": 0
}
]
]
},
"Enhanced Default Data Loader": {
"ai_document": [
[
{
"node": "Postgres PGVector Store3",
"type": "ai_document",
"index": 0
}
]
]
},
"Recursive Character Text Splitter2": {
"ai_textSplitter": [
[
{
"node": "Enhanced Default Data Loader",
"type": "ai_textSplitter",
"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.
openAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow is ideal for: Professionals Project managers Sales and support teams Anyone managing high volumes of Gmail messages
Source: https://n8n.io/workflows/5908/ — 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.
Order and Delivery Support. Uses lmChatOpenAi, documentDefaultDataLoader, embeddingsOpenAi, toolVectorStore. Event-driven trigger; 29 nodes.
OpenAI Chat, Document Default Data Loader, OpenAI Embeddings +15
This workflow implements a complete Retrieval-Augmented Generation (RAG) knowledge assistant with built-in document ingestion, conversational AI, and automated analytics using n8n, OpenAI, and Pinecon
Form Trigger, Data Table, Text Splitter Recursive Character Text Splitter +8
This powerful AI automation add-on upgrades your Telegram Bot Starter Template by integrating a fully functional AI chatbot and a context-aware AI agent that answers user questions using your internal
OpenAI Chat, Document Default Data Loader, OpenAI Embeddings +10
<h2>📧 Analyze, classify, and summarize emails using RAG (automatic taxonomy learning)</h2>
OpenAI Chat, Gmail Trigger, Google Sheets +7
HR & IT Helpdesk Chatbot with Audio Transcription. Uses stickyNote, manualTrigger, httpRequest, extractFromFile. Event-driven trigger; 27 nodes.
HTTP Request, Vector Store Pgvector, OpenAI Embeddings +9