Albert Ho 
This workflow corresponds to n8n.io template #8080 — we link there as the canonical source.
This workflow follows the Chainllm → Gmail 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": "p88sqsRiRSpYb4Da",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "Auto email labeler",
"tags": [
{
"id": "KXa95L999LpnSKKK",
"name": "Gmail",
"createdAt": "2025-08-30T14:29:58.156Z",
"updatedAt": "2025-08-30T14:29:58.156Z"
}
],
"nodes": [
{
"id": "9bf78ec9-a9a9-4db5-8cb0-4eb6cb6cf3b5",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
608,
32
],
"parameters": {
"text": "=Provide a summary of the email in JSON format. You will provide a (1) Id, (2) summary, (3) extract the relevant entity such as person, organization, (4) provide a list of up to 5 labels from the list provided in the \"Labels List\" below to categorize the email. Or if none are appropriate, please come up with new labels (up to 5).\n\nHere is the email content:\nFrom: {{ $json.From }}\nSubject: {{ $json.Subject }}\nContent: {{ $json.snippet }}\nLabel List: {{ $json.existing_labels.map(label => label.name) }}\n\nHere is an example output:\n{\n \"summary\": \"This is an email advertising a new designer collection of goods from Haider Ackermann on Mr. Porter. It is Haider Ackermann's debut collection.\",\n \"people\": \"Mr. Porter\",\n \"labels\":\n [\n \"Advertisement\",\n \"Designer Label\",\n \"Clothes\",\n \"Online Shopping\"\n ]\n}\n\nYour Output:\n",
"batching": {},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.7,
"waitBetweenTries": 100
},
{
"id": "0216c4d9-041b-41d0-ae1d-6965399bfc61",
"name": "Gmail Trigger",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
-432,
304
],
"parameters": {
"filters": {},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
}
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 1.3
},
{
"id": "d8d3a318-0477-4e5d-8e1d-2d7ab073f217",
"name": "Structured Output Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
736,
320
],
"parameters": {
"autoFix": true,
"jsonSchemaExample": "{\n \"messageId\": \"\",\n \"summary\": \"This email higlights the convenience of using an Alexa-enabled smart thermostat for temperature control and mentions Alexa's ability to assist with shopping lists, specifically laundry detergent. It also references a 'Weekly Spotlight' feature related to product sorting.\",\n \"people\": \"Alexa\",\n \"labels\":\n [\n \"Smart Home\",\n \"Voice Assistant\",\n \"Thermostat\",\n \"Shopping\",\n \"Productivity\"\n ]\n}"
},
"typeVersion": 1.3
},
{
"id": "99594eaa-8459-4cb9-905e-399549cb8b72",
"name": "Create a label",
"type": "n8n-nodes-base.gmail",
"onError": "continueRegularOutput",
"position": [
1472,
400
],
"parameters": {
"name": "={{ $json[\"output.labels\"] }}",
"options": {},
"resource": "label",
"operation": "create"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "c2beef7d-1352-40ac-868c-be730a463d69",
"name": "Code",
"type": "n8n-nodes-base.code",
"position": [
1216,
320
],
"parameters": {
"jsCode": "var item = $input.first();\nvar new_labels = new Set(item.json.output.labels) // new labels defined by LLM\nvar old_labels = new Set(item.json.existing_labels.map(label => label.name)) // message labels\nvar label_array = item.json.existing_labels // users label dictionary\nvar labels_to_create = new Set();\nvar existing_labels = new Set();\n\n// identify new labels to create\nnew_labels.forEach(label => {\n if (old_labels.has(label)) {\n console.log(\"dupe found: \" + label)\n existing_labels.add(label)\n } else {\n console.log(\"unique found: \" + label)\n labels_to_create.add(label)\n }\n});\n\n// each new label to create ends up in output.labels array\nitem.json.output.labels = []\nlabels_to_create.forEach(label => item.json.output.labels.push(label))\n\n// existing labels end up in output.old_labels array\n// for each old label, look up the label id\nitem.json.output.old_labels = []\nexisting_labels.forEach(label => {\n var label_obj = label_array.find(l => l.name == label)\n if (label_obj) {\n console.log(\"replacing \" + label + \" with id \" + label_obj.id)\n item.json.output.old_labels.push(label_obj.id)\n item.json.output.added_label_names.push(label_obj.name)\n }\n})\n\nitem.json.output.messageId = item.json.id;\n\nreturn $input.all();"
},
"typeVersion": 2
},
{
"id": "c8153181-5a9a-4ec7-a61b-f559d34e0d3f",
"name": "Merge2",
"type": "n8n-nodes-base.merge",
"position": [
1040,
48
],
"parameters": {
"mode": "combineBySql",
"query": "SELECT * FROM input1 LEFT JOIN input2",
"options": {}
},
"typeVersion": 3.2
},
{
"id": "3ab1de7a-2dc1-4199-98f5-1e0e0cd8fcc3",
"name": "Split Out",
"type": "n8n-nodes-base.splitOut",
"position": [
1344,
400
],
"parameters": {
"options": {},
"fieldToSplitOut": "output.labels"
},
"typeVersion": 1,
"alwaysOutputData": true
},
{
"id": "758ce7fa-b66a-4018-b576-e754cff5e5f9",
"name": "Merge3",
"type": "n8n-nodes-base.merge",
"position": [
1888,
128
],
"parameters": {
"mode": "combineBySql",
"query": "SELECT * FROM input1 LEFT JOIN input2",
"options": {}
},
"typeVersion": 3.2
},
{
"id": "7be3f984-3cf7-4868-8148-8e3a012028e3",
"name": "Add label to message",
"type": "n8n-nodes-base.gmail",
"position": [
2208,
16
],
"parameters": {
"labelIds": "={{ $json.labels_to_add }}",
"messageId": "={{ $json.output.messageId }}",
"operation": "addLabels"
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "97c77c1d-0857-46cf-ba2a-4e38b0b48e4f",
"name": "Send a message",
"type": "n8n-nodes-base.discord",
"position": [
2848,
304
],
"parameters": {
"content": "={{ $json.text.split(\"MESSAGE STARTS HERE\").last() }}",
"guildId": {
"__rl": true,
"mode": "list",
"value": "1411315313664069778",
"cachedResultUrl": "https://discord.com/channels/1411315313664069778",
"cachedResultName": "terribletap's server"
},
"options": {},
"resource": "message",
"channelId": {
"__rl": true,
"mode": "list",
"value": "1411315314624430103",
"cachedResultUrl": "https://discord.com/channels/1411315313664069778/1411315314624430103",
"cachedResultName": "general"
}
},
"credentials": {
"discordBotApi": {
"name": "<your credential>"
}
},
"typeVersion": 2
},
{
"id": "4e637594-2570-471e-89a3-129c990c70f7",
"name": "Get many labels",
"type": "n8n-nodes-base.gmail",
"position": [
-80,
400
],
"parameters": {
"resource": "label",
"returnAll": true
},
"credentials": {
"gmailOAuth2": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "0652a435-b021-46bb-911e-8d66ad4ab262",
"name": "Filter",
"type": "n8n-nodes-base.filter",
"position": [
80,
400
],
"parameters": {
"options": {},
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "652bbdfc-8258-4acf-b8cc-38f88a69d87c",
"operator": {
"type": "string",
"operation": "startsWith"
},
"leftValue": "={{ $json.id }}",
"rightValue": "Label"
}
]
}
},
"typeVersion": 2.2
},
{
"id": "fb63935c-5a27-4e9e-96b8-5d73301890bf",
"name": "Aggregate1",
"type": "n8n-nodes-base.aggregate",
"position": [
224,
400
],
"parameters": {
"options": {},
"aggregate": "aggregateAllItemData",
"destinationFieldName": "existing_labels"
},
"typeVersion": 1
},
{
"id": "1173c4fc-0037-4c9f-81cc-0e52cd4caa2a",
"name": "Aggregate2",
"type": "n8n-nodes-base.aggregate",
"position": [
1600,
400
],
"parameters": {
"options": {},
"aggregate": "aggregateAllItemData",
"destinationFieldName": "created_labels"
},
"typeVersion": 1
},
{
"id": "19f5848c-d7e6-45c1-8ed9-c5a6aa6c9f5e",
"name": "Edit Fields3",
"type": "n8n-nodes-base.set",
"position": [
2064,
16
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "30b6e814-f461-4957-bee3-433acf9df86e",
"name": "output.messageId",
"type": "string",
"value": "={{ $json.output.messageId }}"
},
{
"id": "cc6b96ee-7eed-463f-b324-511395366671",
"name": "labels_to_add",
"type": "array",
"value": "={{ $json.output.old_labels.concat($json.created_labels.map(item => item.id))}}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "a537fe85-ff6b-44f6-8676-ec118a451f57",
"name": "Loop Over Items",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-288,
304
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "23a89c87-5b44-4a1d-8750-2b817984e33a",
"name": "OpenAI Chat 10001",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
608,
736
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "/home/rocketegg/.cache/huggingface/hub/models--unsloth--gpt-oss-20b-GGUF/snapshots/YOUR_AWS_SECRET_KEY_HERE/gpt-oss-20b-F16.gguf",
"cachedResultName": "/home/rocketegg/.cache/huggingface/hub/models--unsloth--gpt-oss-20b-GGUF/snapshots/YOUR_AWS_SECRET_KEY_HERE/gpt-oss-20b-F16.gguf"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "3a3c249c-b2a5-4b26-8565-345a78bbe347",
"name": "OpenAI Chat 10000",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-688,
-688
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "/home/rocketegg/.cache/huggingface/hub/models--unsloth--GLM-4.5-Air-GGUF/snapshots/YOUR_AWS_SECRET_KEY_HERE/Q4_K_S/GLM-4.5-Air-Q4_K_S-00001-of-00002.gguf",
"cachedResultName": "/home/rocketegg/.cache/huggingface/hub/models--unsloth--GLM-4.5-Air-GGUF/snapshots/YOUR_AWS_SECRET_KEY_HERE/Q4_K_S/GLM-4.5-Air-Q4_K_S-00001-of-00002.gguf"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "7514e196-94bf-462e-95c4-8698978e8b9e",
"name": "Basic LLM Chain1",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
2592,
304
],
"parameters": {
"text": "=INSTRUCTIONS: Rewrite the message below with fun emojis per the instructions below. PREPEND the message with \"MESSAGE STARTS HERE\".\n\nI'm sending a fun discord message so I need the following summary in markdown with emojis appropriate for the content (e.g. financial emails with financial emojis, advertisements with advertisement emojis, and depending on what they are selling, the appropriate emoji, etc).\n\n---\nCONTENT OF THE MESSAGE:\n\nHello! I finished labeling an email.\n\n**From:** {{ $json.From }}\n**Subject:** {{ $json.Subject }}\n**Summary:** {{ $json.output.summary }}\n**Entity:** {{ $json.output.people }}\n**Date:** {{ new Date(parseInt($json.internalDate)) }}\n**Id:** {{ $json.id }}\n\n**Labels Added:**\n{{ $json.created_labels.map(l => `- ${l.name}`).join('\\n> ') }}\n\n**Appended Labels:**\n{{ $json.output.added_label_names.map(name => `- ${name}`).join('\\n> ') }}\n\n--- OUTPUT:\nMESSAGE STARTS HERE:\n\n",
"batching": {},
"promptType": "define"
},
"retryOnFail": true,
"typeVersion": 1.7
},
{
"id": "dd821c19-35ed-4295-89d5-d3202ea7258a",
"name": "Merge",
"type": "n8n-nodes-base.merge",
"position": [
2464,
304
],
"parameters": {
"mode": "combineBySql",
"query": "SELECT * FROM input1 LEFT JOIN input2 ",
"options": {}
},
"typeVersion": 3.2
},
{
"id": "e05d0e9c-161e-4082-a09b-cada4ffcca4c",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1808,
-48
],
"parameters": {
"width": 608,
"height": 288,
"content": "### Label the message with new and existing labels\n"
},
"typeVersion": 1
},
{
"id": "4091dfff-76e6-44a9-bdf4-f333d1b721e6",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
2432,
240
],
"parameters": {
"color": 4,
"width": 608,
"height": 288,
"content": "### Rewrite and send message notification to discord\n"
},
"typeVersion": 1
},
{
"id": "25e5a3f4-b5bc-465a-9701-4fc4ee59c02d",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
1184,
240
],
"parameters": {
"color": 5,
"width": 608,
"height": 288,
"content": "### Create additional gmail labels if needed."
},
"typeVersion": 1
},
{
"id": "f7cb8412-72b5-4e34-8118-8c7b6a99d64a",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-128,
240
],
"parameters": {
"color": 3,
"width": 608,
"height": 288,
"content": "### Find existing Gmail labels as options for LLM to choose from."
},
"typeVersion": 1
},
{
"id": "48d5b5a3-19b9-4b6f-8072-5cd4c51e9441",
"name": "Merge labels into list (for llm to pick)",
"type": "n8n-nodes-base.merge",
"position": [
368,
288
],
"parameters": {
"mode": "combineBySql",
"query": "SELECT * FROM input1 LEFT JOIN input2 ",
"options": {}
},
"typeVersion": 3.2
},
{
"id": "20de5d24-adc4-464c-94c5-8da4729e3682",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
544,
-48
],
"parameters": {
"color": 6,
"width": 608,
"height": 288,
"content": "### LLM chooses labels or defines new ones\n"
},
"typeVersion": 1
},
{
"id": "4c12d9c2-2f47-4c1b-92b1-7164c038efe8",
"name": "Add old_labels []",
"type": "n8n-nodes-base.set",
"position": [
896,
32
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "b4b52de9-a671-4d06-baaa-241f3ec4dea8",
"name": "output",
"type": "object",
"value": "={{ $json.output }}"
},
{
"id": "a27b466e-acad-4e8a-b69f-846d3220595f",
"name": "output.old_labels",
"type": "array",
"value": "[]"
},
{
"id": "25481eb7-7e0e-400b-b80a-f0b460e85c42",
"name": "output.added_label_names",
"type": "array",
"value": "[]"
}
]
},
"duplicateItem": true
},
"typeVersion": 3.4
}
],
"active": true,
"settings": {
"callerPolicy": "workflowsFromSameOwner",
"executionOrder": "v1",
"saveExecutionProgress": true
},
"versionId": "df9e9f97-93f7-4e3e-9092-e85ffda7dcd6",
"connections": {
"Code": {
"main": [
[
{
"node": "Split Out",
"type": "main",
"index": 0
},
{
"node": "Merge3",
"type": "main",
"index": 0
}
]
]
},
"Merge": {
"main": [
[
{
"node": "Basic LLM Chain1",
"type": "main",
"index": 0
}
]
]
},
"Filter": {
"main": [
[
{
"node": "Aggregate1",
"type": "main",
"index": 0
}
]
]
},
"Merge2": {
"main": [
[
{
"node": "Code",
"type": "main",
"index": 0
}
]
]
},
"Merge3": {
"main": [
[
{
"node": "Edit Fields3",
"type": "main",
"index": 0
},
{
"node": "Merge",
"type": "main",
"index": 1
}
]
]
},
"Split Out": {
"main": [
[
{
"node": "Create a label",
"type": "main",
"index": 0
}
]
]
},
"Aggregate1": {
"main": [
[
{
"node": "Merge labels into list (for llm to pick)",
"type": "main",
"index": 1
}
]
]
},
"Aggregate2": {
"main": [
[
{
"node": "Merge3",
"type": "main",
"index": 1
}
]
]
},
"Edit Fields3": {
"main": [
[
{
"node": "Add label to message",
"type": "main",
"index": 0
}
]
]
},
"Gmail Trigger": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Create a label": {
"main": [
[
{
"node": "Aggregate2",
"type": "main",
"index": 0
}
]
]
},
"Send a message": {
"main": [
[]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Add old_labels []",
"type": "main",
"index": 0
}
]
]
},
"Get many labels": {
"main": [
[
{
"node": "Filter",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[],
[
{
"node": "Get many labels",
"type": "main",
"index": 0
},
{
"node": "Merge labels into list (for llm to pick)",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain1": {
"main": [
[
{
"node": "Send a message",
"type": "main",
"index": 0
}
]
]
},
"Add old_labels []": {
"main": [
[
{
"node": "Merge2",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat 10000": {
"ai_languageModel": [
[]
]
},
"OpenAI Chat 10001": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Structured Output Parser",
"type": "ai_languageModel",
"index": 0
},
{
"node": "Basic LLM Chain1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Add label to message": {
"main": [
[
{
"node": "Merge",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser": {
"ai_outputParser": [
[
{
"node": "Basic LLM Chain",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Merge labels into list (for llm to pick)": {
"main": [
[
{
"node": "Merge2",
"type": "main",
"index": 1
},
{
"node": "Basic LLM Chain",
"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.
discordBotApigmailOAuth2openAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow will trigger upon new mail in your gmail inbox and will automatically apply existing labels OR identify, create, then apply up to 5 new labels. This is currently set up to run using a OpenAI endpoint which I have set up connected to my local llama.cpp server…
Source: https://n8n.io/workflows/8080/ — 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.
A sophisticated n8n workflow that transforms your email management with AI-powered classification, automatic responses, and intelligent organization.
Output Parser Autofixing, Output Parser Structured, Gmail Trigger +5
[](https://www.youtube.com/watch?v=rfu4MSvtpAw)
Lm Open Ai, Output Parser Structured, Chain Llm +7
[](https://youtu.be/nC2mSry3xFo)
Gmail Trigger, OpenAI Chat, Output Parser Structured +6
This workflow gives you the ability to reply to a long email with a voice note, rather than having to type everything out.
Output Parser Structured, OpenAI Chat, Telegram +5
Suggest Meeting Slots Using Ai. Uses gmailTrigger, lmChatOpenAi, toolWorkflow, stickyNote. Event-driven trigger; 21 nodes.
Gmail Trigger, OpenAI Chat, Tool Workflow +7