Gmail to Telegram: email summaries with OpenAI GPT-4o
🧑💼 Who is this for? This workflow is for anyone who receives too many emails and wants to stay informed without drowning in their inbox. If you're constantly checking your Gmail and wish you had someone summarizing messages and sending just the important parts to your phone, this is for you. Especially useful for solopreneurs, customer support, busy professionals, or newsletter addicts. 🧠 What problem is this workflow solving? Email is powerful, but also overwhelming. Important info gets buried in threads, and staying on top of things can mean hours wasted scanning messages. This workflow turns that chaos into clarity: as soon as a new email arrives, you get a concise AI-generated summary in Telegram — straight to your pocket. No more checking Gmail constantly. No more missing key updates. Just a clean, human-style summary, written in the language you choose. ⚙️ What this workflow does Watches your Gmail inbox for new messages Prepares the content, including sender, subject, and message body Sends it to OpenAI to generate a friendly, casual summary Delivers that summary to your Telegram chat All in seconds, completely automated. 🛠️ Setup Connect your accounts: Gmail, Telegram, and OpenAI credentials must be added to the respective nodes. Set your Telegram chat ID: Use a bot like @userinfobot to get it. Customize the language in the Set summary language node (default is English). Activate the workflow — and watch it go. 🧩 How to customize this workflow to your needs You can make this workflow your own in a few easy ways: Summarize only some emails: Add a Filter node after the Gmail trigger (e.g., only messages from certain senders). Change the tone or detail of summaries: Tweak the system prompt in the Summary generation agent. Use a different model: Swap OpenAI’s GPT-4o for another provider like Claude or DeepSeek. Translate to your preferred language: Just change "english" to "español", "français", etc.
By Lucía Maio BriosoStock portfolio analysis with Perplexity AI, GPT-4, and Google Sheets
📊 Dynamic Portfolio Advisor – Daily Stock Market Intelligence with Google Sheets Description: This advanced AI-powered n8n workflow automatically delivers a daily market intelligence briefing tailored to your stock holdings portfolio stored in Google Sheets. It uses real-time data from Perplexity AI, combines it with your portfolio, and generates personalized insights, risk alerts, and trade suggestions — all delivered via Telegram or any messaging app of your choice. For step-by-step build of workflows like this, check out: https://www.youtube.com/@Automatewithmarc ⚙️ How It Works: 🕒 Daily Trigger Starts every day at a scheduled time (default: 10 AM) to fetch the most recent market data. 📈 Holdings Fetch Reads your current portfolio dynamically from Google Sheets — no hardcoding required. 🧠 AI Analysis Agent Combines: Market headlines Company-specific developments Macroeconomic updates And analyzes how they might affect your holdings. 🔍 Perplexity Web Research Tool Finds and summarizes the most relevant stock market news from the past 24 hours. 💬 Telegram Delivery Sends a customized summary of: Market highlights Asset-specific impacts Opportunities and risks Actionable trade ideas (buy/sell/hold) 🛠️ Tools & Integrations: Google Sheets (live holdings feed) Perplexity AI (real-time market research) OpenAI GPT (financial summarization) Telegram (output, customizable) 💡 Use Cases: Portfolio-aware market intelligence Automated investor briefing assistant Risk alert + opportunity scanner Daily trade idea generator Finance bloggers or equity analysts streamlining prep work 📍Note: You can easily replace Telegram with Slack, Email, Notion, or any output tool supported by n8n. This template is perfect for active investors, financial advisors, or automation-savvy traders who want to turn AI and data into actionable daily signals.
By Automate With MarcWhatsApp group chat with your vector database — no Facebook Business required
Enable smart, real-time answers in your WhatsApp groups using a custom webhook, Pinecone vector database, and no Facebook Business setup. > 🟡 Note: This template uses a custom WhatsApp webhook. It does not use the official WhatsApp Business API. --- 👥 Who is this for? This workflow is designed for individuals and teams who want to enable smart WhatsApp group automation — without going through Meta’s official WhatsApp Business API. Ideal for small businesses, internal teams, communities, and personal power users. --- ❓ What problem is this solving? Setting up WhatsApp bots with intelligent responses often requires approval from Meta and a verified business account. This workflow removes those barriers by using a self-hosted webhook to handle incoming messages and respond using a document-trained AI via Pinecone. --- ⚙️ What this workflow does Connects a regular WhatsApp number to a custom webhook Adds the bot to any group chat (it stays silent unless mentioned) Indexes documents from Google Drive into Pinecone Responds with intelligent, context-aware answers from your custom knowledge base Auto-updates its knowledge every minute as the document changes --- 🛠️ Setup Step 1: Connect Google Drive Set up your Google Drive credentials in n8n Step 2: Configure Pinecone Create an index in Pinecone Dimension: 1536 Select this index in both Pinecone nodes Click Test Workflow to ingest your document into Pinecone Step 3: Get Access to the WhatsApp Webhook Fill out this form to request access You’ll receive a WhatsApp confirmation for linking Step 4: Test WhatsApp Integration ✅ One-on-one test: Send a message from another number 👥 Group test: Add the bot to a group; it will only respond when tagged --- 🧩 How to customize this workflow Modify the system prompt inside the AI agent node to control tone and behavior Update the connected Google Doc to match your specific domain (e.g. FAQs, SOPs, product manuals) Adjust the Pinecone sync frequency if you want updates more or less often --- 📚 Use cases Customer Support: Instant, intelligent replies in WhatsApp without live agents Team Knowledge Bot: Tag the bot for quick access to SOPs and internal docs Community Groups: Automate common questions while keeping noise low Personal AI Assistant: A WhatsApp chatbot trained on your notes and files --- 📝 Sticky Note Suggestion 💬 What this template does: > Enables an AI bot in your WhatsApp group that answers questions based on a Google Doc you provide. It uses a custom webhook, Google Drive, and Pinecone. 🔧 Requirements: > Google Drive account > Pinecone account with an index (dimension 1536) > Access to the custom WhatsApp webhook (see setup steps)
By Cecilia MukimaPost unassigned Zendesk tickets to Slack
> This has been updated to support the Query feature added to the Zendesk node in 0.144.0 This workflow will post all New and Open tickets without an agent assigned to a Slack channel on a schedule. The function node is used in this example to merge multiple inputs into one output message which is then used as the Slack message. The output in Slack will be similar to the below message, The "TICKET_ID" will be a link to the ticket. > Unassigned Tickets TICKETID [STATUS] - TICKETSUBJECT Usage Update the Cron schedule, The default value is 16:30 daily. Update the Credentials in the Zendesk nodes Update the Credentials and Channel in the Slack Node Grab a coffee and enjoy! Zendesk Query In the Zendesk node we are using the query assignee:none status<pending this returns all New and Open tickets with no assignee allowing us to remove the extra nodes.
By Jonathan BennettsProcess documents & build semantic search with OpenAI, Gemini & Qdrant
🎯 Overview This n8n workflow automates the process of ingesting documents from multiple sources (Google Drive and web forms) into a Qdrant vector database for semantic search capabilities. It handles batch processing, document analysis, embedding generation, and vector storage - all while maintaining proper error handling and execution tracking. 🚀 Key Features Dual Input Sources: Accepts files from both Google Drive folders and web form uploads Batch Processing: Processes files one at a time to prevent memory issues and ensure reliability AI-Powered Analysis: Uses Google Gemini to extract metadata and understand document context Vector Embeddings: Generates OpenAI embeddings for semantic search capabilities Automated Cleanup: Optionally deletes processed files from Google Drive (configurable) Loop Processing: Handles multiple files efficiently with Split In Batches nodes Interactive Chat Interface: Built-in chatbot for testing semantic search queries against indexed documents 📋 Use Cases Knowledge Base Creation: Build searchable document repositories for organizations Document Compliance: Process and index legal/regulatory documents (like Fair Work documents) Content Management: Automatically categorize and store uploaded documents Research Libraries: Create semantic search capabilities for research papers or reports Customer Support: Enable instant answers to policy and documentation questions via chat interface 🔧 Workflow Components Input Methods Google Drive Integration Monitors a specific folder for new files Processes existing files in batch mode Supports automatic file conversion to PDF Web Form Upload Public-facing form for document submission Accepts PDF, DOCX, DOC, and CSV files Processes multiple file uploads in a single submission Processing Pipeline File Splitting: Separates multiple uploads into individual items Document Analysis: Google Gemini extracts document understanding Text Extraction: Converts documents to plain text Embedding Generation: Creates vector embeddings via OpenAI Vector Storage: Inserts documents with embeddings into Qdrant Loop Control: Manages batch processing with proper state handling Key Nodes Split In Batches: Processes files one at a time with reset: false to maintain state Google Gemini: Analyzes documents for context and metadata Langchain Vector Store: Handles Qdrant insertion with embeddings HTTP Request: Direct API calls for custom operations Chat Interface: Interactive chatbot for testing vector search queries 🛠️ Technical Implementation Batch Processing Logic The workflow uses a clever looping mechanism: Split In Batches with batchSize: 1 ensures single-file processing reset: false maintains loop state across iterations Loop continues until all files are processed Error Handling All nodes include continueOnFail options where appropriate Execution logs are preserved for debugging File deletion only occurs after successful insertion Data Flow Form Upload → Split Files → Batch Loop → Analyze → Insert → Loop Back Google Drive → List Files → Batch Loop → Download → Analyze → Insert → Delete → Loop Back 📊 Performance Considerations Processing Time: ~20-30 seconds per file Batch Size: Set to 1 for reliability (configurable) Memory Usage: Optimized for files under 10MB API Costs: Uses OpenAI embeddings (text-embedding-3-large model) 🔐 Required Credentials Google Drive OAuth2: For file access and management OpenAI API: For embedding generation Qdrant API: For vector database operations Google Gemini API: For document analysis 💡 Implementation Tips Start Small: Test with a few files before processing large batches Monitor Costs: Track OpenAI API usage for embedding generation Backup First: Consider archiving instead of deleting processed files Check Collections: Ensure Qdrant collection exists before running 🎨 Customization Options Change Embedding Model: Switch to text-embedding-3-small for cost savings Adjust Chunk Size: Modify text splitting parameters for different document types Add Metadata: Extend the Gemini prompt to extract specific fields Archive vs Delete: Replace delete operation with move to "processed" folder 📈 Real-World Application This workflow was developed to process business documents and legal agreements, making them searchable through semantic queries. It's particularly useful for organizations dealing with large volumes of regulatory documentation that need to be quickly accessible and searchable. Chat Interface Testing The integrated chatbot interface allows users to: Query processed documents using natural language Test semantic search capabilities in real-time Verify document indexing and retrieval accuracy Ask questions about specific topics (e.g., "What are the pay rates for junior employees?") Get instant AI-powered responses based on the indexed content 🌟 Benefits Automation: Eliminates manual document processing Scalability: Handles individual files or bulk uploads Intelligence: AI-powered understanding of document content Flexibility: Multiple input sources and processing options Reliability: Robust error handling and state management 👨💻 About the Creator Jeremy Dawes is the CEO of Jezweb, specializing in AI and automation deployment solutions. This workflow represents practical, production-ready automation that solves real business challenges while maintaining simplicity and reliability. 📝 Notes The workflow intelligently handles the n8n form upload pattern where multiple files create a single item with multiple binary properties (Files0, Files1, etc.) The Split In Batches pattern with reset: false is crucial for proper loop execution Direct API integration provides more control than pure Langchain implementations 🔗 Resources Qdrant Documentation OpenAI Embeddings n8n Documentation Jezweb - AI & Automation Solutions --- This workflow demonstrates practical automation that bridges document management with modern AI capabilities, creating intelligent document processing systems that scale with your needs.
By JezCryptocurrency dip alerts for Bitcoin & Ethereum via Telegram, Slack & SMS
📉 Buy the Dip Alert (Telegram/Slack/SMS) 📌 Overview This workflow automatically notifies you when Bitcoin or Ethereum drops more than a set percentage in the last 24 hours. It’s ideal for traders who want to stay ready for buy-the-dip opportunities without constantly refreshing charts. --- ⚙️ How it works Schedule Trigger — runs every 30 minutes (adjustable). HTTP Request (CoinGecko) — fetches BTC & ETH prices and 24h % change. Code Node (“Dip Check”) — compares changes against your dip threshold. IF Node — continues only if dip condition is true. Notification Node — sends alert via Telegram, Slack, or SMS (Twilio). Example Output: Dip Alert — BTC –3.2%, ETH –2.8% Not financial advice. --- 🛠 Setup Guide 1) Dip threshold Open the Code node. Change the line: js const DIP = -2.5; // trigger if 24h drop <= -2.5% Set your preferred dip value (e.g., –5 for a 5% drop). 2) Choose your alert channel Telegram: add your bot token & chat ID. Slack: connect Slack API & set channel name. Twilio: configure SID, token, from/to numbers. 3) Test Temporarily set DIP to 0 to force an alert. Run once from the Code node → confirm alert message text. Execute the Notification node → confirm delivery to your channel. 🎛 Customization Cadence: change Schedule Trigger (every 5m, 15m, hourly, etc.). Coins: extend the CoinGecko call (add solana, bnb) and update Code node logic. Multiple alerts: duplicate IF → Notification branch for different thresholds (minor vs major dip). Combine with “Threshold Alerts” workflow to cover both upside breakouts and downside dips. Storage: log alerts into Google Sheets for tracking dip history. 🧩 Troubleshooting No alerts firing: check CoinGecko API response in Execution Data. Wrong %: CoinGecko returns usd24hchange directly — no math needed. Duplicate alerts: add a debounce using a Sheet/DB to store last fired time. Telegram not posting: confirm bot has access to your channel/group.
By David OlusolaCreate an AI Telegram bot using Google Drive, Qdrant, and OpenAI GPT-4.1
How it works This workflow creates an intelligent Telegram bot with a knowledge base powered by Qdrant vector database. The bot automatically processes documents uploaded to Google Drive, stores them as embeddings, and uses this knowledge to answer questions in Telegram. It consists of two independent flows: document processing (Google Drive → Qdrant) and chat interaction (Telegram → AI Agent → Telegram). Step-by-step Document Processing Flow: New File Trigger: The workflow starts when the New File Trigger node detects a new file created in the specified Google Drive folder (polling every 15 minutes). Download File: The Download File (Google Drive) node downloads the detected file from Google Drive. Text Splitting: The Split Text into Chunks node splits the document text into chunks of 3000 characters with 300 character overlap for optimal embedding. Load Document Data: The Load Document Data node processes the binary file data and prepares it for vectorization. OpenAI Embeddings: The OpenAI Embeddings node generates vector embeddings for each text chunk. Insert into Qdrant: The Insert into Qdrant node stores the embeddings in the Qdrant vector database collection. Move to Processed Folder: After successful processing, the Move to Processed Folder (Google Drive) node moves the file to a "Qdrant Ready" folder to keep files organized. Telegram Chat Flow: Telegram Message Trigger: The Telegram Message Trigger node receives new messages from the Telegram bot. Filter Authorized User: The Filter Authorized User node checks if the message is from an authorized chat ID (26899549) to restrict bot access. AI Agent Processing: The AI Agent receives the user's message text and processes it using the fine-tuned GPT-4.1 model with access to the Qdrant knowledge base tool. Qdrant Knowledge Base: The Qdrant Knowledge Base node retrieves relevant information from the vector database to provide context for the AI agent's responses. Conversation Memory: The Conversation Memory node maintains conversation history per chat ID, allowing the bot to remember context. Send Response to Telegram: The Send Response to Telegram node sends the AI-generated response back to the user in Telegram. Set up steps Estimated set up time: 15 minutes Google Drive Setup: Add your Google Drive OAuth2 credentials to the New File Trigger, Download File, and Move to Processed Folder nodes. Create two folders in your Google Drive: one for incoming files and one for processed files. Copy the folder IDs from the URLs and update them in the New File Trigger (folderToWatch) and Move to Processed Folder (folderId) nodes. Qdrant Setup: Add your Qdrant API credentials to the Insert into Qdrant and Qdrant Knowledge Base nodes. Create a collection in your Qdrant instance (e.g., "Test-youtube-adept-ecom"). Update the collection name in both Qdrant nodes. OpenAI Setup: Add your OpenAI API credentials to the OpenAI Chat Model and OpenAI Embeddings nodes. (Optional) Replace the fine-tuned model ID in OpenAI Chat Model with your own model or use a standard model like gpt-4-turbo. Telegram Setup: Create a Telegram bot via @BotFather and obtain the bot token. Add your Telegram bot credentials to the Telegram Message Trigger and Send Response to Telegram nodes. Update the authorized chat ID in the Filter Authorized User node (replace 26899549 with your Telegram user ID). Customize System Prompt (Optional): Modify the system message in the AI Agent node to customize your bot's personality and behavior. The current prompt is configured for an n8n automation expert creating social media content. Activate the Workflow: Toggle "Active" in the top-right to enable both the Google Drive trigger and Telegram trigger. Upload a document to your Google Drive folder to test the document processing flow. Send a message to your Telegram bot to test the chat interaction flow.
By Konstantin