Advanced AI Demo (Presented at AI Developers #14 meetup)
Automate advanced AI interactions and intelligent email management with this comprehensive workflow, originally showcased at the AI Developers #14 meetup. This powerful 39-node template leverages a webhook trigger to initiate complex processes, integrating OpenAI, Gmail, Pinecone, Slack, and Anthropic for diverse AI-driven tasks. For instance, it can automatically process incoming emails from "nathan's inbox" via a Gmail trigger, using an AI text classifier to assign relevant labels like "automation" or "music" in Gmail based on content. Beyond email, the workflow demonstrates sophisticated AI capabilities such as downloading PDFs via HTTP requests and embedding their content into a Pinecone vector store using OpenAI embeddings, enabling robust document retrieval and question-answering chains. It also features an AI agent capable of booking appointments by checking calendar availability and interacting with users through a Slack "send message" node, showcasing real-time conversational AI. This workflow is ideal for developers and businesses looking to implement cutting-edge AI for automated customer support, intelligent document processing, and smart inbox organization, significantly reducing manual effort in information management and communication.
Workflow JSON
{"meta": {"instanceId": "84ba6d895254e080ac2b4916d987aa66b000f88d4d919a6b9c76848f9b8a7616", "templateId": "2358"}, "nodes": [{"id": "fb774d11-da48-4481-ad4e-8c93274f123e", "name": "Send message", "type": "n8n-nodes-base.slack", "position": [2340, 580], "parameters": {"text": "=Data from webhook: {{ $json.query.email }}", "select": "channel", "channelId": {"__rl": true, "mode": "list", "value": "C079GL6K3U6", "cachedResultName": "general"}, "otherOptions": {}, "authentication": "oAuth2"}, "typeVersion": 2.2}, {"id": "5a3ad8f1-eba7-4076-80fc-0c1237aab50b", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [380, 240], "parameters": {"color": 7, "width": 1163.3132111854613, "height": 677.0358687053997, "content": ""}, "typeVersion": 1}, {"id": "01c59396-0fef-4d1c-aa1f-787669300650", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [1860, 240], "parameters": {"color": 7, "width": 437, "height": 99, "content": "# What is n8n?\n### Low-code Automation Platform for technical teams"}, "typeVersion": 1}, {"id": "0bdd4a35-7f5c-443c-a14a-4e6f7ed18712", "name": "Execute JavaScript", "type": "n8n-nodes-base.code", "position": [2340, 380], "parameters": {"jsCode": "// Loop over input items and add a new field called 'myNewField' to the JSON of each one\nfor (const item of $input.all()) {\n item.json.myNewField = 1;\n}\n\nreturn $input.all();"}, "typeVersion": 2}, {"id": "4b1b6cc1-1a9f-4a0c-96d5-fd179c84c79d", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [4440, 240], "parameters": {"color": 6, "width": 318, "height": 106, "content": "# Example #2\n### RAG with PDF as source"}, "typeVersion": 1}, {"id": "7e9e7802-5695-4240-83b9-d6f02192ad2b", "name": "Recursive Character Text Splitter", "type": "@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter", "position": [5120, 1000], "parameters": {"options": {}, "chunkSize": 3000, "chunkOverlap": 200}, "typeVersion": 1}, {"id": "63783c21-af6d-4e70-8dec-c861641c53fb", "name": "Embeddings OpenAI", "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi", "position": [4880, 820], "parameters": {"options": {}}, "typeVersion": 1}, {"id": "5742ce9c-2f73-4129-85eb-876f562cf6b1", "name": "Default Data Loader", "type": "@n8n/n8n-nodes-langchain.documentDefaultDataLoader", "position": [5100, 820], "parameters": {"loader": "pdfLoader", "options": {"metadata": {"metadataValues": [{"name": "document-title", "value": "={{ $('PDFs to download').item.json.whitepaper_title }}"}, {"name": "document-publish-year", "value": "={{ $('PDFs to download').item.json.publish_year }}"}, {"name": "document-author", "value": "={{ $('PDFs to download').item.json.author }}"}]}}, "dataType": "binary"}, "typeVersion": 1}, {"id": "686c63fa-4672-4107-bd58-ffbb0650b44b", "name": "OpenAI Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [5840, 840], "parameters": {"model": "gpt-4o", "options": {"temperature": 0.3}}, "typeVersion": 1}, {"id": "73a7df02-aa2c-4f0f-aa88-38cbbbf3b1cb", "name": "Embeddings OpenAI2", "type": "@n8n/n8n-nodes-langchain.embeddingsOpenAi", "position": [5980, 1140], "parameters": {"options": {}}, "typeVersion": 1}, {"id": "42737305-fd39-4ec7-b4ba-53f70085dd5f", "name": "Vector Store Retriever", "type": "@n8n/n8n-nodes-langchain.retrieverVectorStore", "position": [6040, 840], "parameters": {}, "typeVersion": 1}, {"id": "2c7a3666-e123-439d-8b74-41eb375f066c", "name": "Download PDF", "type": "n8n-nodes-base.httpRequest", "position": [4700, 600], "parameters": {"url": "={{ $json.file_url }}", "options": {}}, "typeVersion": 4.2}, {"id": "866eaeb9-6a7c-4209-b485-8ef13ed006b4", "name": "PDFs to download", "type": "n8n-nodes-base.noOp", "notes": "BTC Whitepaper + metadata", "position": [4440, 600], "parameters": {}, "notesInFlow": true, "typeVersion": 1}, {"id": "e78f2191-096c-4575-9d48-fb891fd18698", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [4440, 440], "parameters": {"color": 4, "width": 414.36616595939887, "height": 91.0723900084547, "content": "## A. Load PDF into Pinecone\nDownload the PDF, then text embeddings into Pincecone"}, "typeVersion": 1}, {"id": "7c3ccf27-32b1-4ea7-b2ef-6997793de733", "name": "Sticky Note5", "type": "n8n-nodes-base.stickyNote", "position": [5600, 460], "parameters": {"color": 4, "width": 284.62109466374466, "height": 86.95121951219511, "content": "## B. Chat with PDF\nUse GPT4o to chat with Pinecone index"}, "typeVersion": 1}, {"id": "6063d009-da6e-4cbf-899f-c86b879931a7", "name": "Read Pinecone Vector Store", "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone", "position": [5980, 980], "parameters": {"options": {"pineconeNamespace": "whitepaper"}, "pineconeIndex": {"__rl": true, "mode": "list", "value": "whitepapers", "cachedResultName": "whitepapers"}}, "typeVersion": 1}, {"id": "8aa52156-264d-4911-993c-ac5117a76b21", "name": "Question and Answer Chain", "type": "@n8n/n8n-nodes-langchain.chainRetrievalQa", "position": [5840, 620], "parameters": {"text": "={{ $json.chatInput }}. \nOnly use vector store knowledge to answer the question. Don't make anything up. If you don't know the answer, tell the user that you don't know.", "promptType": "define"}, "typeVersion": 1.3}, {"id": "b394ee1d-a2ca-4db0-8caa-981f8f066787", "name": "Sticky Note6", "type": "n8n-nodes-base.stickyNote", "position": [7380, 240], "parameters": {"color": 6, "width": 504.25, "height": 106, "content": "# Example #3\n### AI Assistant that knows how to use predefined API endpoints "}, "typeVersion": 1}, {"id": "37a8b8f2-c444-4c6e-9b02-b97a5c616e84", "name": "Sticky Note7", "type": "n8n-nodes-base.stickyNote", "position": [3020, 220], "parameters": {"color": 6, "width": 318, "height": 111, "content": "# Example #1\n### Categorize incoming emails with AI"}, "typeVersion": 1}, {"id": "07123e8e-8760-4c89-acda-aaef6de68be2", "name": "Anthropic Chat Model", "type": "@n8n/n8n-nodes-langchain.lmChatAnthropic", "position": [7580, 700], "parameters": {"options": {"temperature": 0.4}}, "typeVersion": 1.2}, {"id": "e338a175-e823-4cd4-b77d-f5acbfcbdb9d", "name": "Get calendar availability", "type": "@n8n/n8n-nodes-langchain.toolHttpRequest", "position": [7900, 700], "parameters": {"url": "https://www.googleapis.com/calendar/v3/freeBusy", "method": "POST", "jsonBody": "={\n \"timeMin\": \"{timeMin}\",\n \"timeMax\": \"{timeMax}\",\n \"timeZone\": \"Europe/Berlin\",\n \"groupExpansionMax\": 20,\n \"calendarExpansionMax\": 10,\n \"items\": [\n {\n \"id\": \"max@n8n.io\"\n }\n ]\n}", "sendBody": true, "specifyBody": "json", "authentication": "predefinedCredentialType", "toolDescription": "Call this tool to get the appointment availability for a particular period on the calendar. The tool may refer to availability as \"Free\" or \"Busy\". \n\nUse {timeMin} and {timeMax} to specify the window for the availability query. For example, to get availability for 25 July, 2024 the {timeMin} would be 2024-07-25T09:00:00+02:00 and {timeMax} would be 2024-07-25T17:00:00+02:00.\n\nIf the tool returns an empty response, it means that something went wrong. It does not mean that there is no availability.", "nodeCredentialType": "googleCalendarOAuth2Api"}, "typeVersion": 1}, {"id": "ae05933c-dfa9-4272-b610-8b5fc94d76fe", "name": "Appointment booking agent", "type": "@n8n/n8n-nodes-langchain.agent", "position": [7680, 480], "parameters": {"options": {"systemMessage": "=You are an efficient and courteous assistant tasked with scheduling appointments with Max Tkacz.\n\nWhen users mention an appointment or meeting, they are referring to a meeting with Max.\nWhen users refer to the calendar or \"your schedule,\" they are referring to Max's calendar. \n\nYou can use various tools to access and manage Max's calendar. Your primary goal is to assist users in successfully booking an appointment with Max, ensuring no scheduling conflicts. Only book an appointment if the requested time slot is available (the tool may refer to this as \"Free\")\n\nToday's date is {{ $today.format('dd LLL yyyy') }}.\nAppointments are always 30 minutes in length. \n\n\nProvide accurate information at all times. If the tools are not functioning correctly, inform the user that you are unable to assist them at the moment.\n"}}, "typeVersion": 1.6}, {"id": "7e3b1797-150e-4c7c-93a5-306b981e0b6c", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [8300, 440], "parameters": {"color": 7, "width": 327.46658341463433, "height": 571.8601927804875, "content": "\n[Open Calendar](https://calendar.google.com/calendar/u/0/r/day/2024/7/26)"}, "typeVersion": 1}, {"id": "afe8d14d-d0d0-4a11-bb4f-57358de66bc1", "name": "Window Buffer Memory", "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow", "position": [7720, 700], "parameters": {"contextWindowLength": 10}, "typeVersion": 1.2}, {"id": "53d131ea-3235-4e4e-828b-dc22c9021e50", "name": "Sticky Note8", "type": "n8n-nodes-base.stickyNote", "position": [6380, 640], "parameters": {"color": 7, "width": 615.2162978341456, "height": 403.1877919219511, "content": "\nBTC Whitepaper references"}, "typeVersion": 1}, {"id": "55a0f180-bb35-4b35-b72c-b9361698e5ad", "name": "Sticky Note9", "type": "n8n-nodes-base.stickyNote", "position": [9660, 240], "parameters": {"color": 7, "width": 345.33741540309194, "height": 398.9629539487597, "content": "### Connect with me or explore this demo \ud83d\udc47\n"}, "typeVersion": 1}, {"id": "14b3231d-aa96-4783-be8f-cb2f70b0bc7f", "name": "Sticky Note10", "type": "n8n-nodes-base.stickyNote", "position": [9220, 240], "parameters": {"color": 7, "width": 411.2946586626259, "height": 197.19036476628202, "content": "# Thank you and happy flowgramming \ud83e\udd18\n\n### Max Tkacz | Senior Developer Advocate @ n8n"}, "typeVersion": 1}, {"id": "c9a2fcdc-c8ab-4b9d-9979-4fd7cca1e8a8", "name": "Insert into Pinecone vector store", "type": "@n8n/n8n-nodes-langchain.vectorStorePinecone", "position": [4920, 600], "parameters": {"mode": "insert", "options": {"clearNamespace": true, "pineconeNamespace": "whitepaper"}, "pineconeIndex": {"__rl": true, "mode": "list", "value": "whitepapers", "cachedResultName": "whitepapers"}}, "typeVersion": 1}, {"id": "6a890c74-67f9-4eee-bb56-7c9a68921ae1", "name": "Book appointment", "type": "@n8n/n8n-nodes-langchain.toolHttpRequest", "position": [8060, 700], "parameters": {"url": "https://www.googleapis.com/calendar/v3/calendars/max@n8n.io/events", "method": "POST", "jsonBody": "={\n \"summary\": \"Appointment with {userName}\",\n \"start\": {\n \"dateTime\": \"{startTime}\",\n \"timeZone\": \"Europe/Berlin\"\n },\n \"end\": {\n \"dateTime\": \"{endTime}\",\n \"timeZone\": \"Europe/Berlin\"\n },\n \"attendees\": [\n {\"email\": \"max@n8n.io\"},\n {\"email\": \"{userEmail}\"}\n ]\n}", "sendBody": true, "specifyBody": "json", "authentication": "predefinedCredentialType", "toolDescription": "Call this tool to book an appointment in the calendar. ", "nodeCredentialType": "googleCalendarOAuth2Api", "placeholderDefinitions": {"values": [{"name": "userName", "description": "The full name of the user making the appointment. Like John Doe"}, {"name": "startTime", "description": "The start time of the event in Europe/Berlin timezone. For example, 2024-07-24T10:00:00+02:00"}, {"name": "endTime", "description": "The end time of the event in Europe/Berlin timezone. It should always be 30 minutes after the startTime. "}, {"name": "userEmail", "description": "The email address of the user making the appointment"}]}}, "typeVersion": 1}, {"id": "7f6e62f2-2d72-4fd2-a6ef-e57028d0055b", "name": "When chat message received", "type": "@n8n/n8n-nodes-langchain.chatTrigger", "position": [5600, 620], "webhookId": "c348693e-9c43-4bf2-90a5-23786273e809", "parameters": {"public": true, "options": {"title": "Book an appointment with Max"}, "initialMessages": "Hi there! \ud83d\udc4b\nI can help you schedule an appointment with Max Tkacz. On which day would you like to meet?"}, "typeVersion": 1.1}, {"id": "52c65975-479d-4c76-bcd3-23f5c9bb6acf", "name": "Sticky Note11", "type": "n8n-nodes-base.stickyNote", "position": [9220, 460], "parameters": {"color": 7, "width": 411.2946586626259, "height": 80, "content": "### Explore 100+ AI Workflow templates on n8n.io\n[Open Templates Library](https://n8n.io/workflows)"}, "typeVersion": 1}, {"id": "ba0635c0-2ca4-4b27-b960-3a0e0f93a56a", "name": "Sticky Note12", "type": "n8n-nodes-base.stickyNote", "position": [9220, 560], "parameters": {"color": 7, "width": 411.2946586626259, "height": 80, "content": "### Ask a question in our community (13k+ members)\n[Explore n8n community](https://community.n8n.io/)"}, "typeVersion": 1}, {"id": "29227c52-a9cc-4bd1-b1a3-78fb805b659c", "name": "OpenAI Chat Model1", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [3260, 660], "parameters": {"model": "gpt-4o", "options": {"temperature": 0.5}}, "typeVersion": 1}, {"id": "494a2868-9ff5-402c-b83b-6dd2c3ddbcc9", "name": "Add automation label", "type": "n8n-nodes-base.gmail", "position": [3760, 300], "parameters": {"labelIds": ["Label_4763053241338138112"], "messageId": "={{ $json.id }}", "operation": "addLabels"}, "typeVersion": 2.1}, {"id": "0f9d834d-ec47-43f5-945b-8c464d371122", "name": "On new email to nathan's inbox", "type": "n8n-nodes-base.gmailTrigger", "disabled": true, "position": [3040, 460], "parameters": {"simple": false, "filters": {}, "options": {}, "pollTimes": {"item": [{"mode": "everyMinute"}]}}, "typeVersion": 1.1}, {"id": "142e2a49-40bd-4bf5-9ba3-f14ecd68618e", "name": "Add music label", "type": "n8n-nodes-base.gmail", "position": [3760, 500], "parameters": {"labelIds": ["Label_6822395192337188416"], "messageId": "={{ $json.id }}", "operation": "addLabels"}, "typeVersion": 2.1}, {"id": "2eb46753-a0e8-43ec-a460-466b1dd265c9", "name": "Assign label with AI", "type": "@n8n/n8n-nodes-langchain.textClassifier", "position": [3280, 460], "parameters": {"options": {}, "inputText": "={{ $json.text }}", "categories": {"categories": [{"category": "automation", "description": "email on the topic of automation or workflows and automated processes, includes newsletters on this topic"}, {"category": "music", "description": "email on the topic of music, for example from an artist "}]}}, "typeVersion": 1}, {"id": "576d8206-1b1e-4671-ba45-86e9d844a73b", "name": "Webhook", "type": "n8n-nodes-base.webhook", "position": [1860, 460], "webhookId": "74facfd7-0f51-4605-9724-2c300594fcf9", "parameters": {"path": "74facfd7-0f51-4605-9724-2c300594fcf9", "options": {}}, "typeVersion": 2}, {"id": "1e612376-1a3b-4c48-9cd3-97867ba4cad5", "name": "Whether email contains n8n", "type": "n8n-nodes-base.if", "position": [2060, 460], "parameters": {"options": {}, "conditions": {"options": {"leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"id": "a0b16c44-03ea-4e96-9671-7b168697186d", "operator": {"type": "string", "operation": "contains"}, "leftValue": "={{ $json.query.email }}", "rightValue": "@n8n"}]}}, "typeVersion": 2}], "pinData": {}, "connections": {"Webhook": {"main": [[{"node": "Whether email contains n8n", "type": "main", "index": 0}]]}, "Download PDF": {"main": [[{"node": "Insert into Pinecone vector store", "type": "main", "index": 0}]]}, "Book appointment": {"ai_tool": [[{"node": "Appointment booking agent", "type": "ai_tool", "index": 0}]]}, "PDFs to download": {"main": [[{"node": "Download PDF", "type": "main", "index": 0}]]}, "Embeddings OpenAI": {"ai_embedding": [[{"node": "Insert into Pinecone vector store", "type": "ai_embedding", "index": 0}]]}, "OpenAI Chat Model": {"ai_languageModel": [[{"node": "Question and Answer Chain", "type": "ai_languageModel", "index": 0}]]}, "Embeddings OpenAI2": {"ai_embedding": [[{"node": "Read Pinecone Vector Store", "type": "ai_embedding", "index": 0}]]}, "OpenAI Chat Model1": {"ai_languageModel": [[{"node": "Assign label with AI", "type": "ai_languageModel", "index": 0}]]}, "Default Data Loader": {"ai_document": [[{"node": "Insert into Pinecone vector store", "type": "ai_document", "index": 0}]]}, "Anthropic Chat Model": {"ai_languageModel": [[{"node": "Appointment booking agent", "type": "ai_languageModel", "index": 0}]]}, "Assign label with AI": {"main": [[{"node": "Add automation label", "type": "main", "index": 0}], [{"node": "Add music label", "type": "main", "index": 0}]]}, "Window Buffer Memory": {"ai_memory": [[{"node": "Appointment booking agent", "type": "ai_memory", "index": 0}]]}, "Vector Store Retriever": {"ai_retriever": [[{"node": "Question and Answer Chain", "type": "ai_retriever", "index": 0}]]}, "Get calendar availability": {"ai_tool": [[{"node": "Appointment booking agent", "type": "ai_tool", "index": 0}]]}, "Read Pinecone Vector Store": {"ai_vectorStore": [[{"node": "Vector Store Retriever", "type": "ai_vectorStore", "index": 0}]]}, "When chat message received": {"main": [[{"node": "Question and Answer Chain", "type": "main", "index": 0}]]}, "Whether email contains n8n": {"main": [[{"node": "Execute JavaScript", "type": "main", "index": 0}, {"node": "Send message", "type": "main", "index": 0}]]}, "On new email to nathan's inbox": {"main": [[{"node": "Assign label with AI", "type": "main", "index": 0}]]}, "Recursive Character Text Splitter": {"ai_textSplitter": [[{"node": "Default Data Loader", "type": "ai_textSplitter", "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
Text to Speech (OpenAI)
Converts text into natural-sounding speech using OpenAI's Text-to-Speech API. It sends your input text to OpenAI and receives an audio file in return. This is useful for creating audio versions of articles, generating voiceovers for videos, or providing accessibility features for web content. Quickly transform written content into engaging audio.
LangChain - Example - Code Node Example
Explore a basic LangChain agent that answers questions using a custom tool. This workflow connects n8n's AI nodes and custom code nodes to OpenAI for language model interactions. It's useful for developers building custom AI assistants or researchers experimenting with agentic workflows. This saves development time by providing a ready-to-use example of a LangChain agent.
AI-Powered Candidate Shortlisting Automation for ERPNext
Automate AI-powered candidate shortlisting for ERPNext job applications. This workflow connects ERPNext, Google Gemini, WhatsApp, and Outlook to process resumes, evaluate candidates, and communicate outcomes. Recruiters and HR departments can use this to efficiently screen applicants, automatically reject unqualified candidates, and send acceptance notifications. It significantly reduces manual review time and streamlines the hiring process.