Davide Boizza This workflow corresponds to n8n.io template #2862 — we link there as the canonical source.
This workflow follows the Agent → Chainsummarization 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": "nkPjDxMrrkKbgHaV",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Effortless Email Management with AI",
"tags": [],
"nodes": [
{
"id": "9d77e26f-de2b-4bd4-b0f0-9924a8f459a6",
"name": "Email Trigger (IMAP)",
"type": "n8n-nodes-base.emailReadImap",
"position": [
-2000,
-180
],
"parameters": {
"options": {}
},
"credentials": {
"imap": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "cf2d020b-b125-4a20-8694-8ed0f7acf755",
"name": "Markdown",
"type": "n8n-nodes-base.markdown",
"position": [
-1740,
-180
],
"parameters": {
"html": "={{ $json.textHtml }}",
"options": {}
},
"typeVersion": 1
},
{
"id": "41bfceff-0155-4643-be60-ee301e2d69e1",
"name": "Send Email",
"type": "n8n-nodes-base.emailSend",
"position": [
400,
-320
],
"parameters": {
"html": "={{ $('Edit Fields').item.json.email }}",
"options": {},
"subject": "=Re: {{ $('Email Trigger (IMAP)').item.json.subject }}",
"toEmail": "={{ $('Email Trigger (IMAP)').item.json.from }}",
"fromEmail": "={{ $('Email Trigger (IMAP)').item.json.to }}"
},
"credentials": {
"smtp": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "2aff581a-8b64-405c-b62f-74bf189fd7b1",
"name": "Qdrant Vector Store",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
-320,
600
],
"parameters": {
"mode": "retrieve-as-tool",
"options": {},
"toolName": "company_knowladge_base",
"toolDescription": "Extracts information regarding the request made.",
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "=COLLECTION"
},
"includeDocumentMetadata": false
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "6e3f6df0-8924-47d9-855c-51205d19e86d",
"name": "Embeddings OpenAI",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-440,
800
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "37ac411b-4a74-44d1-917e-b07d1c9ca221",
"name": "Email Summarization Chain",
"type": "@n8n/n8n-nodes-langchain.chainSummarization",
"position": [
-1480,
-180
],
"parameters": {
"options": {
"binaryDataKey": "={{ $json.data }}",
"summarizationMethodAndPrompts": {
"values": {
"prompt": "=Write a concise summary of the following in max 100 words:\n\n\"{{ $json.data }}\"\n\nDo not enter the total number of words used.",
"combineMapPrompt": "=Write a concise summary of the following in max 100 words:\n\n\"{{ $json.data }}\"\n\nDo not enter the total number of words used."
}
}
},
"operationMode": "nodeInputBinary"
},
"typeVersion": 2
},
{
"id": "91edbac9-847b-4f31-a8dd-09418bd93642",
"name": "Write email",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-1040,
-180
],
"parameters": {
"text": "=Write the text to reply to the following email:\n\n{{ $json.response.text }}",
"options": {
"systemMessage": "You are an expert at answering emails. You need to answer them professionally based on the information you have. This is a business email. Be concise and never exceed 100 words. Only the body of the email, not create the subject"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.7
},
{
"id": "1da0e72a-db97-4216-a1a5-038cebaf7e10",
"name": "OpenAI",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-180,
280
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini",
"cachedResultName": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "af2d6284-4c8f-4a07-b689-d0f55aaabd26",
"name": "Gmail",
"type": "n8n-nodes-base.gmail",
"position": [
-300,
-180
],
"parameters": {
"sendTo": "user@example.com",
"message": "=<h3>MESSAGE</h3>\n{{ $('Email Trigger (IMAP)').item.json.textHtml }}\n\n<h3>AI RESPONSE</h3>\n{{ $json.email }}",
"options": {},
"subject": "=[Approval Required] {{ $('Email Trigger (IMAP)').item.json.subject }}",
"operation": "sendAndWait",
"responseType": "freeText"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "aaccc4a6-ce53-4813-8247-65bd1a9d5639",
"name": "Text Classifier",
"type": "@n8n/n8n-nodes-langchain.textClassifier",
"position": [
-60,
-180
],
"parameters": {
"options": {
"systemPromptTemplate": "Please classify the text provided by the user into one of the following categories: {categories}, and use the provided formatting instructions below. Don't explain, and only output the json."
},
"inputText": "={{ $json.data.text }}",
"categories": {
"categories": [
{
"category": "Approved",
"description": "The email has been reviewed and accepted as-is. The human explicitly or implicity express approva, indicating that no changes ar needed.\n\nExample:\n\"Ok\",\n\"Approvato\",\n\"Invia\""
},
{
"category": "Declined",
"description": "The email has been reviewd, but the human request modifications before it sent link tweaks, removing parts, rewording etc... This could include suggested edits, rewording or major revision."
}
]
}
},
"typeVersion": 1
},
{
"id": "b46de5d9-1a2e-4d28-930b-e18fb1d7876e",
"name": "Edit Fields",
"type": "n8n-nodes-base.set",
"position": [
-580,
-180
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "35d7c303-42f4-4dd1-b41e-6eb087c23c3d",
"name": "email",
"type": "string",
"value": "={{ $json.output }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "36ce51c6-8ee1-4230-84c0-40e259eafb1a",
"name": "When clicking \u2018Test workflow\u2019",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-1340,
-1300
],
"parameters": {},
"typeVersion": 1
},
{
"id": "21a0c991-65dc-483e-9b98-5cedaba7ae13",
"name": "Create collection",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1040,
-1440
],
"parameters": {
"url": "https://QDRANTURL/collections/COLLECTION",
"method": "POST",
"options": {},
"jsonBody": "{\n \"filter\": {}\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "9a048d7d-bcdf-40b7-b33a-94b811083eac",
"name": "Refresh collection",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1040,
-1180
],
"parameters": {
"url": "https:/YOUR_AWS_SECRET_KEY_HERE/delete",
"method": "POST",
"options": {},
"jsonBody": "{\n \"filter\": {}\n}",
"sendBody": true,
"sendHeaders": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"headerParameters": {
"parameters": [
{
"name": "Content-Type",
"value": "application/json"
}
]
}
},
"credentials": {
"httpHeaderAuth": {
"name": "<your credential>"
}
},
"typeVersion": 4.2
},
{
"id": "db494d2d-5390-4f83-9b87-3409fef31a7d",
"name": "Get folder",
"type": "n8n-nodes-base.googleDrive",
"position": [
-820,
-1180
],
"parameters": {
"filter": {
"driveId": {
"__rl": true,
"mode": "list",
"value": "My Drive",
"cachedResultUrl": "https://drive.google.com/drive/my-drive",
"cachedResultName": "My Drive"
},
"folderId": {
"__rl": true,
"mode": "id",
"value": "=test-whatsapp"
}
},
"options": {},
"resource": "fileFolder"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "e30dbe6f-482e-47f9-b5b8-62c1113e6c8b",
"name": "Download Files",
"type": "n8n-nodes-base.googleDrive",
"position": [
-600,
-1180
],
"parameters": {
"fileId": {
"__rl": true,
"mode": "id",
"value": "={{ $json.id }}"
},
"options": {
"googleFileConversion": {
"conversion": {
"docsToFormat": "text/plain"
}
}
},
"operation": "download"
},
"credentials": {
"googleDriveOAuth2Api": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "492d48d8-4997-4f04-902b-041da3210417",
"name": "Default Data Loader",
"type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader",
"position": [
-200,
-980
],
"parameters": {
"options": {},
"dataType": "binary"
},
"typeVersion": 1
},
{
"id": "0cf45d10-3cbf-4eb6-ab30-11f264b3aa8d",
"name": "Token Splitter",
"type": "@n8n/n8n-nodes-langchain.textSplitterTokenSplitter",
"position": [
-240,
-820
],
"parameters": {
"chunkSize": 300,
"chunkOverlap": 30
},
"typeVersion": 1
},
{
"id": "7d60f569-c34e-49a8-ba9a-88cf33083136",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-840,
-1500
],
"parameters": {
"color": 6,
"width": 880,
"height": 220,
"content": "# STEP 1\n\n## Create Qdrant Collection\nChange:\n- QDRANTURL\n- COLLECTION"
},
"typeVersion": 1
},
{
"id": "e86b18c4-d7e8-4e81-b520-dbd8125edf38",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1060,
-1240
],
"parameters": {
"color": 4,
"width": 620,
"height": 400,
"content": "# STEP 2\n\n\n\n\n\n\n\n\n\n\n\n\n## Documents vectorization with Qdrant and Google Drive\nChange:\n- QDRANTURL\n- COLLECTION"
},
"typeVersion": 1
},
{
"id": "05f65120-ef31-4c67-ac18-e68a8353909c",
"name": "Qdrant Vector Store1",
"type": "@n8n/n8n-nodes-langchain.vectorStoreQdrant",
"position": [
-360,
-1180
],
"parameters": {
"mode": "insert",
"options": {},
"qdrantCollection": {
"__rl": true,
"mode": "id",
"value": "=COLLECTION"
}
},
"credentials": {
"qdrantApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "c15fd52f-b142-408e-af06-aeed10a1cf85",
"name": "Embeddings OpenAI1",
"type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi",
"position": [
-380,
-980
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "3e47224f-3deb-450b-b825-f16c5f860f28",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2020,
-600
],
"parameters": {
"color": 3,
"width": 580,
"height": 260,
"content": "# STEP 3 - MAIN FLOW\n\n\n## How it works\nThis workflow automates the handling of incoming emails, summarizes their content, generates appropriate responses using a retrieval-augmented generation (RAG) approach, and obtains approval or suggestions before sending replies. \n\nYou can quickly integrate Gmail and Outlook via the appropriate trigger nodes"
},
"typeVersion": 1
},
{
"id": "63097039-58cb-4e0f-9fb6-6bf868275519",
"name": "DeepSeek Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatDeepSeek",
"position": [
-1560,
40
],
"parameters": {
"options": {}
},
"credentials": {
"deepSeekApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "c86d6eeb-cf08-429f-b5b4-60b317071035",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1500,
-260
],
"parameters": {
"width": 320,
"height": 240,
"content": "Chain that summarizes the received email"
},
"typeVersion": 1
},
{
"id": "4afc8b00-d1e5-473c-a71e-1299c84c546e",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1060,
-260
],
"parameters": {
"width": 340,
"height": 240,
"content": "Agent that retrieves business information from a vector database and processes the response"
},
"typeVersion": 1
},
{
"id": "be1762ff-729b-4b83-9139-16f835b748f2",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1800,
-260
],
"parameters": {
"height": 240,
"content": "Convert email to Markdown format for better understanding of LLM models"
},
"typeVersion": 1
},
{
"id": "f818ede7-895a-4860-91d3-f08cc32ec0e3",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-380,
-380
],
"parameters": {
"color": 4,
"height": 360,
"content": "## IMPORTANT\n\nFor the \"Send Draft\" node, you need to send the draft email to a Gmail address because it is the only one that allows the \"Send and wait for response\" function."
},
"typeVersion": 1
},
{
"id": "929b525a-912b-4f7b-a6e7-dfeb88a446c8",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
-100,
-260
],
"parameters": {
"width": 360,
"height": 240,
"content": "Based on the suggestion received, the text classifier can understand whether the feedback received approves the generated email or not."
},
"typeVersion": 1
},
{
"id": "2468e643-013f-4925-ab35-c8ef4ee6eed2",
"name": "Email Reviewer",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
380,
-40
],
"parameters": {
"text": "=Review at the following email:\n{{ $('Edit Fields').item.json.email }}\n\nFeedback from human:\n{{ $json.data.text }}",
"options": {
"systemMessage": "If you are an expert in reviewing emails before sending them. You need to review and structure them in such a way that you can send them. It must be in HTML format and you can insert (if you think it is appropriate) only HTML characters such as <br>, <b>, <i>, <p> where necessary. Be concise and never exceed 100 words. Only the body of the email"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.7
},
{
"id": "ecd9d3f8-2e79-4e5f-a73d-48de60441376",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
340,
-120
],
"parameters": {
"width": 340,
"height": 220,
"content": "The Email Reviewer agent, taking inspiration from human feedback, rewrites the email"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "de11da52-1513-4797-8070-b64e84b84158",
"connections": {
"Gmail": {
"main": [
[
{
"node": "Text Classifier",
"type": "main",
"index": 0
}
]
]
},
"OpenAI": {
"ai_languageModel": [
[
{
"node": "Write email",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Email Reviewer",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Text Classifier",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Markdown": {
"main": [
[
{
"node": "Email Summarization Chain",
"type": "main",
"index": 0
}
]
]
},
"Get folder": {
"main": [
[
{
"node": "Download Files",
"type": "main",
"index": 0
}
]
]
},
"Edit Fields": {
"main": [
[
{
"node": "Gmail",
"type": "main",
"index": 0
}
]
]
},
"Write email": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"Download Files": {
"main": [
[
{
"node": "Qdrant Vector Store1",
"type": "main",
"index": 0
}
]
]
},
"Email Reviewer": {
"main": [
[
{
"node": "Edit Fields",
"type": "main",
"index": 0
}
]
]
},
"Token Splitter": {
"ai_textSplitter": [
[
{
"node": "Default Data Loader",
"type": "ai_textSplitter",
"index": 0
}
]
]
},
"Text Classifier": {
"main": [
[
{
"node": "Send Email",
"type": "main",
"index": 0
}
],
[
{
"node": "Email Reviewer",
"type": "main",
"index": 0
}
]
]
},
"Embeddings OpenAI": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Embeddings OpenAI1": {
"ai_embedding": [
[
{
"node": "Qdrant Vector Store1",
"type": "ai_embedding",
"index": 0
}
]
]
},
"Refresh collection": {
"main": [
[
{
"node": "Get folder",
"type": "main",
"index": 0
}
]
]
},
"DeepSeek Chat Model": {
"ai_languageModel": [
[
{
"node": "Email Summarization Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Default Data Loader": {
"ai_document": [
[
{
"node": "Qdrant Vector Store1",
"type": "ai_document",
"index": 0
}
]
]
},
"Qdrant Vector Store": {
"ai_tool": [
[
{
"node": "Write email",
"type": "ai_tool",
"index": 0
},
{
"node": "Email Reviewer",
"type": "ai_tool",
"index": 0
}
]
]
},
"Email Trigger (IMAP)": {
"main": [
[
{
"node": "Markdown",
"type": "main",
"index": 0
}
]
]
},
"Email Summarization Chain": {
"main": [
[
{
"node": "Write email",
"type": "main",
"index": 0
}
]
]
},
"When clicking \u2018Test workflow\u2019": {
"main": [
[
{
"node": "Create collection",
"type": "main",
"index": 0
},
{
"node": "Refresh collection",
"type": "main",
"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.
deepSeekApigmailOAuth2googleDriveOAuth2ApihttpHeaderAuthimapopenAiApiqdrantApismtp
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow automates the handling of incoming emails, summarizes their content, generates appropriate responses using a retrieval-augmented generation (RAG) approach, and obtains approval or suggestions before sending replies. Below is an explanation of its functionality…
Source: https://n8n.io/workflows/2862/ — 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.
Your AI workforce is ready. Are you?
Google Sheets Tool, Mcp Trigger, Google Drive +29
This comprehensive workflow bundle is designed as a powerful starter kit, enabling you to build a multi-functional AI assistant on Telegram. It seamlessly integrates AI-powered voice interactions, an
Telegram Trigger, Telegram, OpenAI +19
This advanced n8n workflow automates the full lead enrichment, qualification, and personalized outreach process tailored specifically for the B2B real estate sector. Integrating top platforms like Api
N8N Nodes Fillout, OpenAI Chat, Pinecone Vector Store +11
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
Automate Outreach Prospect automates finding, enriching, and messaging potential partners (like restaurants, malls, and bars) using Apify Google Maps scraping, Perplexity enrichment, OpenAI LLMs, Goog
@Devlikeapro/N8N Nodes Waha, Google Drive Trigger, @Apify/N8N Nodes Apify +14