Auto-label incoming Gmail messages with AI nodes
Automatically categorize your incoming Gmail messages with intelligent, AI-powered labeling using this n8n workflow. This powerful automation connects your Gmail account with OpenAI's advanced language models to analyze message content and assign relevant labels, streamlining your inbox management. Businesses and individuals can leverage this to automatically sort customer inquiries, sales leads, support tickets, or personal emails, ensuring important messages are always prioritized and easily found. By leveraging the Gmail trigger to initiate the process, the workflow fetches message content, utilizes OpenAI Chat for intelligent label assignment, and then employs a JSON Parser to structure the AI's output before finally adding the appropriate labels back to your Gmail messages. This eliminates the manual effort of sorting and labeling emails, saving significant time and improving response efficiency for anyone dealing with a high volume of incoming communications.
Workflow JSON
{"nodes": [{"id": "8141ffad-df2a-403b-a869-799c036f9733", "name": "Gmail trigger", "type": "n8n-nodes-base.gmailTrigger", "position": [-600, 580], "parameters": {"simple": false, "filters": {}, "options": {}, "pollTimes": {"item": [{"mode": "everyMinute"}]}}, "credentials": {"gmailOAuth2": {"id": "", "name": "[Your gmailOAuth2]"}}, "typeVersion": 1}, {"id": "6d9aa398-e2de-4fd0-b939-2a12d0c9fe14", "name": "Get message content", "type": "n8n-nodes-base.gmail", "position": [-340, 580], "parameters": {"simple": false, "options": {}, "messageId": "={{ $json.id }}", "operation": "get"}, "credentials": {"gmailOAuth2": {"id": "", "name": "[Your gmailOAuth2]"}}, "typeVersion": 2.1}, {"id": "cd86bc09-8c7f-4c85-9cb3-6dbd42420672", "name": "Set label values", "type": "n8n-nodes-base.set", "position": [300, 580], "parameters": {"fields": {"values": [{"name": "labels", "type": "arrayValue", "arrayValue": "={{ $json.labels }}"}]}, "options": {}}, "typeVersion": 3.2}, {"id": "329435a6-51d1-416e-9aa9-5fe9a8dce74f", "name": "Get all labels", "type": "n8n-nodes-base.gmail", "position": [580, 460], "parameters": {"resource": "label", "returnAll": true}, "credentials": {"gmailOAuth2": {"id": "", "name": "[Your gmailOAuth2]"}}, "typeVersion": 2.1}, {"id": "7ae2dd15-472d-4a4b-b036-f80ebd7e3c28", "name": "Split out assigned labels", "type": "n8n-nodes-base.splitOut", "position": [580, 700], "parameters": {"options": {}, "fieldToSplitOut": "labels"}, "typeVersion": 1}, {"id": "744c7afa-75b1-4b3b-8ccb-e2106c01f387", "name": "Merge corresponding labels", "type": "n8n-nodes-base.merge", "position": [860, 580], "parameters": {"mode": "combine", "options": {}, "mergeByFields": {"values": [{"field1": "name", "field2": "labels"}]}, "outputDataFrom": "input1"}, "typeVersion": 2.1}, {"id": "e47424dc-f43e-41a9-b1e5-ab3e08cbf395", "name": "Aggregate label IDs", "type": "n8n-nodes-base.aggregate", "position": [1120, 580], "parameters": {"options": {}, "fieldsToAggregate": {"fieldToAggregate": [{"renameField": true, "outputFieldName": "label_ids", "fieldToAggregate": "id"}]}}, "typeVersion": 1}, {"id": "22ba8297-8efc-463e-8ae0-385fd94a205f", "name": "Add labels to message", "type": "n8n-nodes-base.gmail", "position": [1340, 580], "parameters": {"labelIds": "={{ $json.label_ids }}", "messageId": "={{ $('Gmail trigger').item.json[\"id\"] }}", "operation": "addLabels"}, "credentials": {"gmailOAuth2": {"id": "", "name": "[Your gmailOAuth2]"}}, "typeVersion": 2.1}, {"id": "7ebb1aad-00ad-43fa-9e07-e5f324864a74", "name": "Assign labels for message", "type": "@n8n/n8n-nodes-langchain.chainLlm", "position": [-80, 580], "parameters": {"prompt": "={{ $json.text }}", "messages": {"messageValues": [{"message": "Your task is to categorize the message according to the following labels.\n\nPartnership - email about sponsored content, cooperation etc.\nInquiry - email about products, services.\nNotification - email that doesn't require response. \n\nOne email can have more than one label. Return only label names in JSON format, nothing else. Do not make things up. "}]}}, "typeVersion": 1.3}, {"id": "2f82db6a-422c-4697-a629-cc782d88209d", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [-1100, 400], "parameters": {"color": 4, "width": 420.4803040774015, "height": 240.57943708322733, "content": "## Add AI labels to Gmail messages\nWith this workflow you can automatically set labels for your Gmail message according to its content. \n\nIn this workflow available are 3 labels: \"Partnership\", \"Inquiry\" and \"Notification\". Feel free to adjust labels according to your needs. \n\n**Please remember to set label names both in your Gmail account and workflow.**"}, "typeVersion": 1}, {"id": "4a10fb2b-aebb-4735-bbdb-7f07f1136d95", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [-1100, 660], "parameters": {"width": 421.0932411886662, "height": 257.42916378714597, "content": "## \u26a0\ufe0f Note\n\n1. Complete video guide for this workflow is available [on my YouTube](https://youtu.be/a8Dhj3Zh9vQ). \n2. Remember to add your credentials and configure nodes (covered in the video guide).\n3. If you like this workflow, please subscribe to [my YouTube channel](https://www.youtube.com/@workfloows) and/or [my newsletter](https://workfloows.com/).\n\n**Thank you for your support!**"}, "typeVersion": 1}, {"id": "76e62351-d502-4377-9df2-fe92df00fe03", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [-660, 400], "parameters": {"width": 238.4602598584674, "height": 348.5873725349161, "content": "### Gmail Trigger\nReceive data from Gmail about new incoming message. \n\n\u26a0\ufe0f Set polling interval according to your needs."}, "typeVersion": 1}, {"id": "c10702db-211f-4638-bcf0-fbbe18251cb7", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [60, 780], "parameters": {"width": 241.53974014153226, "height": 319.3323098457962, "content": "###\n\n\n\n\n\n\n\n\n\n\n### JSON schema\nEdit JSON schema and label names according to your needs.\n\n\u26a0\ufe0f **Label names in system prompt and JSON schema should be the same.**"}, "typeVersion": 1}, {"id": "cb6e3573-3d4d-4313-a97e-86a017438399", "name": "Sticky Note5", "type": "n8n-nodes-base.stickyNote", "position": [800, 420], "parameters": {"width": 226.14233872620645, "height": 347.0476323933831, "content": "### Merge labels\nCombine labels retrieved from Gmail account and assigned by AI together."}, "typeVersion": 1}, {"id": "8cfb4341-98e6-4944-b26c-15e39184f468", "name": "Sticky Note6", "type": "n8n-nodes-base.stickyNote", "position": [1060, 420], "parameters": {"width": 452.48413953150185, "height": 347.0476323933831, "content": "### Aggregarte labels and add to message\nCreate array of label IDs and add to the desired email message in Gmail."}, "typeVersion": 1}, {"id": "bb9766e8-0b72-47f8-9a8e-0b291609e814", "name": "Sticky Note7", "type": "n8n-nodes-base.stickyNote", "position": [-400, 400], "parameters": {"width": 238.4602598584674, "height": 348.5873725349161, "content": "### Get message content\nBased on Gmail message ID retrieve body content of the email and pass it to AI chain."}, "typeVersion": 1}, {"id": "48630cbd-8336-4577-928e-37341f09ef9b", "name": "Sticky Note8", "type": "n8n-nodes-base.stickyNote", "position": [-140, 400], "parameters": {"width": 378.57661273793565, "height": 348.5873725349161, "content": "### Assign labels\nLet the AI decide which labels suit the best content of the message.\n\n\u26a0\ufe0f **Remember to edit system prompt** - modify label names and instructions according to your needs."}, "typeVersion": 1}, {"id": "60a9d75e-1564-4b1d-b3f2-acc2e3bf2411", "name": "JSON Parser", "type": "@n8n/n8n-nodes-langchain.outputParserStructured", "position": [140, 800], "parameters": {"jsonSchema": "{\n \"type\": \"object\",\n \"properties\": {\n \"labels\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\",\n \"enum\": [\"Inquiry\", \"Partnership\", \"Notification\"]\n }\n }\n },\n \"required\": [\"labels\"]\n}\n"}, "typeVersion": 1}, {"id": "2bdf3fed-8a7f-411a-bad4-266bfea5cede", "name": "OpenAI Chat", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [-120, 800], "parameters": {"model": "gpt-4-turbo-preview", "options": {"temperature": 0, "responseFormat": "json_object"}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1}], "active": false, "pinData": {}, "settings": {"executionOrder": "v1"}, "connections": {"JSON Parser": {"ai_outputParser": [[{"node": "Assign labels for message", "type": "ai_outputParser", "index": 0}]]}, "OpenAI Chat": {"ai_languageModel": [[{"node": "Assign labels for message", "type": "ai_languageModel", "index": 0}]]}, "Gmail trigger": {"main": [[{"node": "Get message content", "type": "main", "index": 0}]]}, "Get all labels": {"main": [[{"node": "Merge corresponding labels", "type": "main", "index": 0}]]}, "Set label values": {"main": [[{"node": "Get all labels", "type": "main", "index": 0}, {"node": "Split out assigned labels", "type": "main", "index": 0}]]}, "Aggregate label IDs": {"main": [[{"node": "Add labels to message", "type": "main", "index": 0}]]}, "Get message content": {"main": [[{"node": "Assign labels for message", "type": "main", "index": 0}]]}, "Assign labels for message": {"main": [[{"node": "Set label values", "type": "main", "index": 0}]]}, "Split out assigned labels": {"main": [[{"node": "Merge corresponding labels", "type": "main", "index": 1}]]}, "Merge corresponding labels": {"main": [[{"node": "Aggregate label IDs", "type": "main", "index": 0}]]}}}How to Import This Workflow
- 1Copy the workflow JSON above using the Copy Workflow JSON button.
- 2Open your n8n instance and go to Workflows.
- 3Click Import from JSON and paste the copied workflow.
Don't have an n8n instance? Start your free trial at n8nautomation.cloud
Related Templates
Auto categorize wordpress template
Automatically categorize your WordPress posts with the power of AI. This workflow connects your WordPress site with OpenAI's advanced language models to intelligently analyze your content and assign appropriate categories. When you manually trigger this workflow, it first retrieves all your WordPress posts using the "Get All Wordpress Posts" node. This data then flows into an AI Agent, which leverages the "OpenAI Chat Model" to understand the context and content of each post. Based on this analysis, the AI Agent then interacts with your WordPress site to update the categories of your posts, streamlining your content management. This is incredibly useful for bloggers, content marketers, and website administrators who manage large volumes of content and want to ensure their posts are consistently and accurately categorized without manual effort. It saves significant time and reduces the potential for human error in content organization, making your website more navigable and improving SEO.
Effortless Email Management with AI
Automate your email management by intelligently processing incoming messages, summarizing their content, and drafting personalized replies with AI. This powerful workflow connects your Gmail inbox via an IMAP trigger to a Text Classifier that categorizes emails, then uses OpenAI for summarization and drafting responses, and Qdrant for vector storage of relevant documents from Google Drive. It’s ideal for marketing teams, customer support, or busy professionals who need to efficiently handle high volumes of correspondence, saving significant time on reading, understanding, and responding to emails by leveraging AI to streamline communication and ensure timely, relevant replies. The system also allows for reviewing AI-generated drafts before sending, ensuring quality control while drastically reducing manual effort.
Summarize emails with A.I. then send to messenger
Automatically summarize incoming emails using artificial intelligence and then instantly share those summaries to your preferred messenger application with this efficient n8n workflow. This automation connects your IMAP email account to an AI summarization service via an HTTP Request, extracting key information from your messages. The summarized content is then sent to a messenger platform, also through an HTTP Request, ensuring important updates reach your team or personal devices without delay. Businesses can leverage this to quickly disseminate critical client communications, project updates, or urgent alerts from various email accounts directly to team chat channels, saving valuable time spent sifting through lengthy emails. This workflow significantly reduces manual effort in information processing and dissemination, allowing for faster decision-making and improved communication efficiency across your organization.