Send specific PDF attachments from Gmail to Google Drive using OpenAI

Automatically extract and categorize specific PDF attachments from incoming Gmail emails and upload them to designated Google Drive folders based on their content, leveraging OpenAI's advanced text analysis capabilities. This marketing workflow begins with the Gmail trigger "On email received," which then checks if the email "Has attachments?" If attachments are present, the workflow iterates through them, identifying if each is a PDF. For each identified PDF, the "Read PDF" node extracts its textual content. This content is then evaluated by the "Is text within token limit?" node to ensure it's suitable for OpenAI processing. If within limits, the "OpenAI matches PDF textual content" node analyzes the text against predefined criteria. Based on whether the PDF is "matched" by OpenAI, the "Upload file to folder" node in Google Drive stores the relevant PDFs, while unmatched or non-PDF attachments are handled accordingly. This workflow is ideal for marketing teams needing to automatically sort client contracts, campaign reports, or specific vendor invoices received via email, ensuring critical documents are filed correctly without manual intervention. It significantly reduces the time spent on document organization and improves data accessibility, allowing teams to focus on strategic marketing initiatives rather than administrative tasks.

18 nodesmanual trigger111 views0 copiesMarketing

Google DriveGmailOpenAI

Workflow JSON

{"meta": {"instanceId": "a2434c94d549548a685cca39cc4614698e94f527bcea84eefa363f1037ae14cd"}, "nodes": [{"id": "deafa2e8-af41-4f11-92e0-09992f6c6970", "name": "Read PDF", "type": "n8n-nodes-base.readPDF", "position": [860, 1420], "parameters": {}, "typeVersion": 1}, {"id": "8e3ddbb1-83a1-4f79-9464-61d5a20f0427", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [-760, 1300], "parameters": {"width": 444.034812880766, "height": 599.5274151436035, "content": "## Send specific PDF attachments from Gmail to Google Drive using OpenAI\n\n_**DISCLAIMER**: You may have varying success when using this workflow so be prepared to validate the correctness of OpenAI's results._\n\nThis workflow reads PDF textual content and sends the text to OpenAI. Attachments of interest will then be uploaded to a specified Google Drive folder. For example, you may wish to send invoices received from an email to an inbox folder in Google Drive for later processing. This workflow has been designed to easily change the search term to match your needs. See the workflow for more details.\n\n### How it works\n1. Triggers off on the `On email received` node.\n2. Iterates over the attachments in the email.\n3. Uses the `OpenAI` node to filter out the attachments that do not match the search term set in the `Configure` node. You could match on various PDF files (i.e. invoice, receipt, or contract).\n4. If the PDF attachment matches the search term, the workflow uses the `Google Drive` node to upload the PDF attachment to a specific Google Drive folder.\n\n\nWorkflow written by [David Sha](https://davidsha.me)."}, "typeVersion": 1}, {"id": "fb2c3697-a92f-4be1-b9a6-0326f87de70b", "name": "Configure", "type": "n8n-nodes-base.set", "position": [-20, 1520], "parameters": {"values": {"number": [{"name": "maxTokenSize", "value": 4000}, {"name": "replyTokenSize", "value": 50}], "string": [{"name": "Match on", "value": "payslip"}, {"name": "Google Drive folder to upload matched PDFs", "value": "https://drive.google.com/drive/u/0/folders/1SKdHTnYoBNlnhF_QJ-Zyepy-3-WZkObo"}]}, "options": {}}, "typeVersion": 1}, {"id": "792c49f4-06e3-4d77-a31f-1513f70abf32", "name": "Is PDF", "type": "n8n-nodes-base.if", "position": [640, 1520], "parameters": {"conditions": {"string": [{"value1": "={{ $binary.data.fileExtension }}", "value2": "pdf"}]}}, "typeVersion": 1}, {"id": "82be9111-665d-41c6-8190-2247acdb749b", "name": "Not a PDF", "type": "n8n-nodes-base.noOp", "position": [860, 1620], "parameters": {}, "typeVersion": 1}, {"id": "c2ac155f-38ee-46f2-8a24-5614e3c32ff5", "name": "Is matched", "type": "n8n-nodes-base.if", "position": [1720, 1480], "parameters": {"conditions": {"string": [{"value1": "={{ $json[\"text\"] }}", "value2": "true"}]}}, "typeVersion": 1}, {"id": "4a8f15b8-c153-493d-9a2a-d63d911d642d", "name": "This is a matched PDF", "type": "n8n-nodes-base.noOp", "position": [1940, 1380], "parameters": {}, "typeVersion": 1}, {"id": "89601591-5c7b-461c-859b-25c7c1f0c2e6", "name": "This is not a matched PDF", "type": "n8n-nodes-base.noOp", "position": [1940, 1580], "parameters": {}, "typeVersion": 1}, {"id": "ac517c4a-83b8-441f-b14c-c927c18f8012", "name": "Iterate over email attachments", "type": "n8n-nodes-base.code", "position": [420, 1420], "parameters": {"jsCode": "// https://community.n8n.io/t/iterating-over-email-attachments/13588/3\nlet results = [];\n\nfor (const item of $input.all()) {\n for (key of Object.keys(item.binary)) {\n results.push({\n json: {},\n binary: {\n data: item.binary[key],\n }\n });\n }\n}\n\nreturn results;"}, "typeVersion": 1}, {"id": "79fdf2de-42fe-4ebb-80fb-cc80dcd284f9", "name": "OpenAI matches PDF textual content", "type": "n8n-nodes-base.openAi", "position": [1300, 1340], "parameters": {"prompt": "=Does this PDF file look like a {{ $(\"Configure\").first().json[\"Match on\"] }}? Return \"true\" if it is a {{ $(\"Configure\").first().json[\"Match on\"] }} and \"false\" if not. Only reply with lowercase letters \"true\" or \"false\".\n\nThis is the PDF filename:\n```\n{{ $binary.data.fileName }}\n```\n\nThis is the PDF text content:\n```\n{{ $json.text }}\n```", "options": {"maxTokens": "={{ $('Configure').first().json.replyTokenSize }}", "temperature": 0.1}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1, "alwaysOutputData": false}, {"id": "8bdb3263-40f2-4277-8cc0-f6edef90a1cd", "name": "Merge", "type": "n8n-nodes-base.merge", "position": [1500, 1480], "parameters": {"mode": "combine", "options": {"clashHandling": {"values": {"resolveClash": "preferInput1"}}}, "combinationMode": "mergeByPosition"}, "typeVersion": 2}, {"id": "8e68e725-b2df-4c0c-8b17-e0cd4610714d", "name": "Upload file to folder", "type": "n8n-nodes-base.googleDrive", "position": [2160, 1380], "parameters": {"name": "={{ $binary.data.fileName }}", "options": {}, "parents": ["={{ $('Configure').first().json[\"Google Drive folder to upload matched PDFs\"].split(\"/\").at(-1) }}"], "binaryData": true}, "credentials": {"googleDriveOAuth2Api": {"id": "", "name": "[Your googleDriveOAuth2Api]"}}, "typeVersion": 2}, {"id": "bda00901-5ade-471c-b6f9-a18ef4d71589", "name": "On email received", "type": "n8n-nodes-base.gmailTrigger", "position": [-240, 1520], "parameters": {"simple": false, "filters": {}, "options": {"downloadAttachments": true, "dataPropertyAttachmentsPrefixName": "attachment_"}, "pollTimes": {"item": [{"mode": "everyMinute"}]}}, "credentials": {"gmailOAuth2": {"id": "", "name": "[Your gmailOAuth2]"}}, "typeVersion": 1}, {"id": "b2ff4774-336b-47a3-af3f-ada809ed9b8a", "name": "Note5", "type": "n8n-nodes-base.stickyNote", "position": [-100, 1440], "parameters": {"width": 259.0890718059702, "height": 607.9684549079709, "content": "### Configuration\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n__`Match on`(required)__: What should OpenAI's search term be? Examples: invoice, callsheet, receipt, contract, payslip.\n__`Google Drive folder to upload matched PDFs`(required)__: Paste the link of the GDrive folder, an example has been provided but will need to change to a folder you own.\n__`maxTokenSize`(required)__: The maximum token size for the model you choose. See possible models from OpenAI [here](https://platform.openai.com/docs/models/gpt-3).\n__`replyTokenSize`(required)__: The reply's maximum token size. Default is 300. This determines how much text the AI will reply with."}, "typeVersion": 1}, {"id": "beb571fe-e7a3-4f3c-862b-dc01821e5f3f", "name": "Ignore large PDFs", "type": "n8n-nodes-base.noOp", "position": [1300, 1620], "parameters": {}, "typeVersion": 1}, {"id": "f3c4f249-08a7-4e5e-8f46-e07393ac10b5", "name": "Is text within token limit?", "type": "n8n-nodes-base.if", "position": [1080, 1520], "parameters": {"conditions": {"boolean": [{"value1": "={{ $json.text.length() / 4 <= $('Configure').first().json.maxTokenSize - $('Configure').first().json.replyTokenSize }}", "value2": true}]}}, "typeVersion": 1}, {"id": "93b6fb96-3e0e-4953-bd09-cf882d2dc69c", "name": "Has attachments?", "type": "n8n-nodes-base.if", "position": [200, 1520], "parameters": {"conditions": {"boolean": [{"value1": "={{ $('On email received').item.binary.isNotEmpty() }}", "value2": true}]}}, "typeVersion": 1}, {"id": "554d415e-a965-46be-8442-35c4cb6b005c", "name": "There are no attachments", "type": "n8n-nodes-base.noOp", "position": [420, 1620], "parameters": {}, "typeVersion": 1}], "connections": {"Merge": {"main": [[{"node": "Is matched", "type": "main", "index": 0}]]}, "Is PDF": {"main": [[{"node": "Read PDF", "type": "main", "index": 0}], [{"node": "Not a PDF", "type": "main", "index": 0}]]}, "Read PDF": {"main": [[{"node": "Is text within token limit?", "type": "main", "index": 0}]]}, "Configure": {"main": [[{"node": "Has attachments?", "type": "main", "index": 0}]]}, "Is matched": {"main": [[{"node": "This is a matched PDF", "type": "main", "index": 0}], [{"node": "This is not a matched PDF", "type": "main", "index": 0}]]}, "Has attachments?": {"main": [[{"node": "Iterate over email attachments", "type": "main", "index": 0}], [{"node": "There are no attachments", "type": "main", "index": 0}]]}, "On email received": {"main": [[{"node": "Configure", "type": "main", "index": 0}]]}, "This is a matched PDF": {"main": [[{"node": "Upload file to folder", "type": "main", "index": 0}]]}, "Is text within token limit?": {"main": [[{"node": "OpenAI matches PDF textual content", "type": "main", "index": 0}, {"node": "Merge", "type": "main", "index": 1}], [{"node": "Ignore large PDFs", "type": "main", "index": 0}]]}, "Iterate over email attachments": {"main": [[{"node": "Is PDF", "type": "main", "index": 0}]]}, "OpenAI matches PDF textual content": {"main": [[{"node": "Merge", "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

Automate Blog Creation in Brand Voice with AI

Generate blog posts in your brand's unique voice and style directly within WordPress using this powerful AI-driven workflow. It begins by fetching existing articles from your blog via an HTTP request, then intelligently extracts their content and structure using an HTML node and an AI chain LLM to understand your established writing patterns. Concurrently, an AI information extractor analyzes these articles to pinpoint and define your brand's distinct voice characteristics. This extracted style and voice, along with the structural insights, are then fed into an AI content generation agent which crafts new blog post drafts. Finally, these AI-generated articles are automatically saved as drafts in your WordPress instance, ready for review and publication. This workflow is ideal for marketing teams, content creators, and agencies looking to scale their content production while maintaining consistent brand messaging and reducing the manual effort involved in drafting new posts, ultimately saving significant time and resources.

27 nodes

Auto-Tag Blog Posts in WordPress with AI

Automatically tag your WordPress blog posts with relevant keywords using the power of AI. This n8n workflow connects your WordPress site with OpenAI's advanced language models to intelligently analyze new or existing articles and assign appropriate tags, streamlining your content management process. It starts by either triggering manually or by an RSS Feed Trigger monitoring your blog for new content, then sends the article text to an OpenAI Chat Model for tag generation. The workflow then checks your existing WordPress tags via an HTTP Request to avoid duplicates, creates any new tags needed with another HTTP Request, and finally updates the WordPress post with the newly generated and existing tags. This automation is perfect for content managers, marketing teams, and bloggers who want to improve SEO, enhance content discoverability, and reduce the manual effort of categorizing a large volume of articles, ultimately saving significant time and ensuring consistent tagging across your entire blog.

32 nodes

Extract spend details (template)

Automate the extraction and tracking of spend details directly from your email inbox into Google Sheets. This workflow connects Gmail to automatically retrieve invoice and payment emails, then uses AI models like Google Gemini Chat Model and Groq Chat Model to intelligently parse and extract key financial data. The extracted information, including vendor, amount, date, and itemized details, is then seamlessly organized and sent to Google Sheets for centralized record-keeping. This powerful automation is ideal for marketing teams, small businesses, and freelancers who need to efficiently monitor expenses, reconcile accounts, and gain better financial visibility without manual data entry, saving significant time and reducing errors in financial tracking.

24 nodes

Ready to automate with n8n?

Get affordable managed n8n hosting with 24/7 support.