Build a chatbot with Reinforced Learning Human Feedback (RLHF) and RAG
Who is this for? This template is designed for internal support teams, product specialists, and knowledge managers who want to build an AI-powered knowledge assistant with retrieval-augmented generation (RAG) and reinforcement learning from human feedback (RLHF) via Telegram. What problem is this workflow solving? Manual knowledge management and answering support queries can be time-consuming and error-prone. This solution automates importing and indexing official documentation into MongoDB vector search and enhances AI responses with Telegram-based user feedback to continuously improve answer quality. What these workflows do Workflow 1: Document ingestion & indexing Manually triggered workflow imports product documentation from Google Docs. Documents are split into manageable chunks and embedded using OpenAI embeddings. Embedded document chunks are stored in MongoDB Atlas vector store to enable semantic search. Workflow 2: Telegram chat with RLHF feedback loop Listens for user messages via Telegram bot integration. Uses vector similarity search on MongoDB to retrieve relevant documentation chunks. Generates answers with OpenAI GPT-4o-mini model using retrieval-augmented generation. Sends answers back via Telegram and waits for user feedback (approval or disapproval). Captures feedback, maps it as positive or negative, and stores it with the conversation data for future model improvement. Setup Setting up vector embeddings Authenticate Google Docs and connect your Google Docs URL containing the product documentation you want to index. Authenticate MongoDB Atlas and connect the collection where you want to store the vector embeddings. Create a search index on this collection to support vector similarity queries. Ensure the index name matches the one configured in n8n (data_index). See the example MongoDB search index template below for reference. Setting up chat with Telegram RLHF Create a bot in Telegram with @botFather using the /newbot command. Connect the MongoDB database and search index used for vector search in the previous workflow. Also create two new collections in MongoDB Atlas: one for feedback and one for chat history. Create a search index for feedback, copying the provided template. Configure the AI system prompt in the “Knowledge Base Agent” node, making sure it references all three tools connected (productDocs, feedbackPositive, feedbackNegative) as provided in the template prompt. Make sure Product documentation and feedback collections must connect to the same MongoDB database. There are three distinct MongoDB collections: one for product documentation, one for feedback, and one for chat history (chat history collection can be separate). Telegram API credentials are valid and webhook URLs are correctly set up. MongoDB Search Index Templates Documentation Collection Index { "mappings": { "dynamic": false, "fields": { "_id": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "source": { "type": "string" }, "doc_id": { "type": "string" } } } } Feedback Collection Index { "mappings": { "dynamic": false, "fields": { "prompt": { "type": "string" }, "response": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "feedback": { "type": "token" } } } }
By NovaNodeRetrieve a Monday.com row and all data in a single node
This workflow is a building block designed to be called from other workflows via an Execute workflow node. When called from another workflow, and given the JSON input of a "pulse" field with the ID to pull from monday, this workflow will return: The items name and ID All column data, indexable by the column name All column data, indexable by the column's ID string All board relation columns, with their data and column values All subitems, with their data and column values For example: ++Prerequisites++ A monday.com account and credential A workflow that needs to get detailed data from a monday.com row The pulse id of the monday.com row to retreive data from. ++Setup++ Import the workflow Configure all monday nodes with your credentials and save the workflow Copy the workflow ID from it's URL In a different workflow, add an Edit Fields node, to output the field "pulse", with the monday item you want to retrieve. Feed the Edit Fields node with your pulse into an Execute workflow node, and paste the workflow ID from above into it This "pulse" field will tell the workflow what pulse to retreive. This can be populated by an expression in your workflow There is an example of the Edit Fields and Execute Workflow nodes in the template
By Joey D’AnnaExport Zammad objects (users, roles, groups, organizations) to Excel
This n8n workflow enables you to export data from Zammad, including Users, Roles, Groups, and Organizations, into individual Excel files. It simplifies data handling and reporting by creating structured outputs for further processing or sharing. Features Export Users with associated details such as email, firstname, lastname, roleids, and groupids. Export Roles and Organizations with their respective identifiers and names. Convert all data into separate Excel files for easy access and use. Usage Import this workflow into your n8n instance. Configure the required Zammad API credentials (zammadbaseurl and zammadapikey) in the Basic Variables node. Run the workflow to generate Excel files containing Zammad data. Issues and Suggestions If you encounter any issues or have suggestions for improvement, please report them on the GitHub repository. We appreciate your feedback to help enhance this workflow!
By SirhexalotGenerate & auto-post tech news AI avatar videos to social media with Heygen and Blotato
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Description This fully automated AI Avatar Social Media system creates talking head AI clone videos, WITHOUT having to film or edit yourself. It combines n8n, AI agent, HeyGen, and Blotato to research, create, and distribute talking head AI clone videos to every social media platform every single day. This template is ideal for content creators, social media managers, social media agencies, small businesses, and marketers who want to to scale short-form video creation, without manually filming and editing every single video. Overview Trigger: Schedule Configured to run once daily at 10am AI News Research Research viral news from tech-focused forum, Hackernews Fetch the selected news item, plus discussion comments AI Writer AI writes 30-second monologue script AI writes short video caption Create Avatar Video Call Heygen API (requires paid API plan), specifying your avatar ID and voice ID Create avatar video, optionally passing in an image/video background if you have a green screen avatar (matte: true) Get Video Wait awhile, then fetch completed avatar video Upload video to Blotato Publish to Social Media via Blotato Connect your Blotato account Choose your social accounts Either post immediately or schedule for later" 📄 Documentation Full Tutorial Troubleshooting Check your Blotato API Dashboard to see every request, response, and error. Click on a request to see the details. Need Help? In the Blotato web app, click the orange button on the bottom right corner. This opens the Support messenger where I help answer technical questions.
By Sabrina Ramonov 🍄Automated email management with Gemini AI: Gmail summarizing, labeling and Notion/Sheets logging
AI Email Manager: Auto Summary, Labeling, and CRM Logging via n8n + Gemini Overview This workflow turns your Gmail inbox into a fully autonomous AI Email Agent that reads, summarizes, categorizes, and organizes emails in real-time. Built with n8n, Google Gemini, Notion, and Google Sheets, it’s perfect for founders, freelancers, and agencies who receive a ton of emails daily and want to automate the triage process without losing control. How It Works Gmail Trigger — Detects new incoming emails. Process Email Data — Extracts sender info, subject, and content in a clean structured format. AI Email Analyzer — Uses Gemini AI to summarize the email and decide the most relevant label (e.g., Project Updates, Client Requests, Invoices, etc.). Create Gmail Label (if not exists) — Dynamically creates a new label if the AI recommends one that doesn’t exist. AI Agent + Add Label to Email — Applies the correct Gmail label automatically using the message ID. Logs in Notion & Google Sheets — Every processed email (summary, sender, date, label) is logged for tracking and analytics. Who It’s For Entrepreneurs & Founders — Manage investor, client, and product update emails automatically. Agencies & Teams — Classify and track client emails effortlessly across projects. Freelancers & Consultants — Get AI summaries and organize leads without manually labeling emails. Tech Builders — Anyone building AI automation tools and SaaS products around inbox management.
By Apurva MishraAuto-send PDF invoices with Stripe payment triggers and Gmail
💰 Auto-Send PDF Invoice When Stripe Payment is Received This workflow automatically generates a PDF invoice every time a successful payment is received in Stripe, then emails the invoice to the customer via Gmail. Perfect for freelancers, SaaS businesses, and service providers who want to automate billing without manual effort. --- ⚙️ How It Works Stripe Payment Webhook Listens for successful payment events (payment_intent.succeeded). Triggers the workflow whenever a new payment is made. Normalize Payment Data A Code node extracts and formats details like: Payment ID Amount & currency Customer name & email Payment date Description Generates a unique invoice number. Generate Invoice HTML A Code node builds a professional invoice template in HTML. Data is dynamically inserted (amount, customer info, invoice number). Output prepared for PDF generation. Send Invoice Email The Gmail node sends an email to the customer. Invoice is attached as a PDF file. Includes a confirmation message with payment details. --- 🛠️ Setup Steps Stripe Webhook In your Stripe Dashboard: Navigate to Developers → Webhooks Add a new endpoint with your Webhook URL from the n8n Webhook node. Select event: payment_intent.succeeded Gmail Setup In n8n, connect your Gmail OAuth2 credentials. Emails will be sent directly from your Gmail account. Customize Invoice Open the Generate Invoice HTML node. Replace "Your Company Name" with your actual business name. Adjust invoice branding, colors, and layout as needed. --- 📧 Example Email Sent Subject: Invoice INV-123456789 - Payment Confirmation Body: Dear John Doe, Thank you for your payment! Please find your invoice attached. Payment Details: Amount: USD 99.00 Payment ID: pi_3JXXXXXXXX Date: 2025-08-29 Best regards, Your Company Name (Attached: invoice_INV-123456789.pdf) --- ⚡ With this workflow, every Stripe payment automatically creates and delivers a polished PDF invoice — no manual work required.
By David OlusolaReal-time sales quote creation in Odoo via Telegram with Google Gemini AI
Overview This template connects Telegram with Odoo to let your sales team create sales quotes and check product availability in real-time — just by sending chat messages. It’s designed for sales representatives, distributors, and small business owners who want to manage quotes and product information quickly without logging into Odoo. ⚙️ How It Works Once configured, this workflow listens to your Telegram bot for incoming messages. Based on the message text, it performs different actions in Odoo: Product Queries Sales reps can ask about products directly in Telegram: “What’s the price of Product B?” “How many units of Product A are available?” The workflow fetches real-time data from Odoo and replies instantly. Sales Quote Creation Sales reps can also create new sales quotes by typing messages like: “My customer Amazon, his email address is abc@amazon.com wants to buy 10 pcs of Product A and 15 pcs of Product B.” The workflow extracts relevant details, creates a sales quote in Odoo, and sends confirmation back in Telegram. 🧰 Setup Instructions Create a Telegram Bot Go to @BotFather on Telegram. Create a new bot and copy the API Token. Prepare Odoo Enable the Sales and Product modules. Generate an API Key from your Odoo user account. Note your Odoo URL (e.g., https://yourcompany.odoo.com). Import Workflow Open your n8n instance (self-hosted or cloud). Click Import Workflow and upload the provided JSON file. Add Credentials Configure your Telegram credentials (Bot Token). Configure your Odoo credentials (Base URL + API Key). Activate the Workflow Set the workflow to active to start listening for Telegram messages. Send a sample message to your bot to test. 🧠 Use Cases Sales reps capturing orders in the field SMEs managing customer inquiries directly from Telegram Real-time price and stock lookups without opening Odoo Automation of repetitive sales quote tasks 🎛️ Customization Options This workflow can be easily adapted to your business needs: Change trigger platform: Replace Telegram with WhatsApp, Slack, or Discord using the respective n8n nodes. Extend data fields: Add fields like delivery date, salesperson, or payment terms. Auto-confirm orders: Add a node to automatically confirm a Sales Quote once approved. ✅ Requirements Odoo v14 or later (with Sales module enabled) Telegram Bot Token n8n instance (Cloud or self-hosted) 💬 Example Prompts Product Query: “What’s the price of Product B?” “How many units of Product A are available?” Order Entry: “My customer Amazon, his email address is abc@amazon.com wants to buy 10 pcs of Product A and 15 pcs of Product B.”
By EvozardAutomated ClickUp time tracking reports & task performance analytics via Gmail
Description Automate your time tracking and task performance reporting with this comprehensive workflow that transforms ClickUp data into actionable insights. This automation pulls tasks directly from ClickUp, processes due dates, priorities, assignees, and time logs, then generates stakeholder-friendly HTML reports with performance metrics and accountability dashboards. Perfect for teams that need daily ClickUp reporting, time tracking, and automated performance insights without manual data compilation. Features 📅 Daily Task Logs - Complete task overview with due date status, sprint points, and time spent 👤 Performance Metrics - Assignee analysis highlighting top performers and improvement areas 📊 Time Analysis - Status breakdown comparing estimated vs. actual hours logged ⚠ Alert System - Overdue and due-today notifications for immediate action 📧 Professional Reports - Polished HTML emails delivered automatically via Gmail 🎯 Accountability Dashboard - Transparent communication for faster decision-making Requirements ClickUp Access: Workspace admin or member permissions Time tracking enabled on relevant tasks Tasks with assignees, due dates, and time estimates configured Technical Setup: n8n instance (v1.0+) ClickUp API token with read permissions for tasks and time tracking Gmail account with app-specific password or OAuth2 Time tracking data populated in ClickUp tasks Setup Instructions ClickUp Configuration: Enable time tracking in your ClickUp workspace and ensure tasks have time estimates and assignees API Access: Generate ClickUp API token from Settings > Apps > API Token and test permissions Gmail Setup: Create app-specific password (enable 2FA first) and configure SMTP credentials in n8n Import Template: Load workflow JSON and update ClickUp workspace/space/list IDs in the configuration nodes Time Zone: Adjust date calculations and reporting periods for your local timezone Recipients: Configure email distribution list in Gmail node for managers and stakeholders Test Execution: Run manual test to verify data retrieval, time log processing, and report delivery Schedule Setup: Configure daily automation (recommended: 9 AM after team check-ins) Perfect for teams that need daily ClickUp reporting, time tracking, and automated performance dashboards — without manual data entry. Keywords: n8n ClickUp automation, time logs, daily task report, ClickUp to Gmail workflow, automated team performance report, sprint analytics automation, due date alerts, assignee productivity tracking
By Rahul Joshi