AI-powered WhatsApp chatbot for text, voice, images, and PDF with RAG
Who is this for? This template is designed for internal support teams, product specialists, and knowledge managers in technology companies who want to automate ingestion of product documentation and enable AI-driven, retrieval-augmented question answering via WhatsApp. What problem is this workflow solving? Support agents often spend too much time manually searching through lengthy documentation, leading to inconsistent or delayed answers. This solution automates importing, chunking, and indexing product manuals, then uses retrieval-augmented generation (RAG) to answer user queries accurately and quickly with AI via WhatsApp messaging. What these workflows do Workflow 1: Document Ingestion & Indexing Manually triggered to import product documentation from Google Docs. Automatically splits large documents into chunks for efficient searching. Generates vector embeddings for each chunk using OpenAI embeddings. Inserts the embedded chunks and metadata into a MongoDB Atlas vector store, enabling fast semantic search. Workflow 2: AI-Powered Query & Response via WhatsApp Listens for incoming WhatsApp user messages, supporting various types: Text messages: Plain text queries from users. Audio messages: Voice notes transcribed into text for processing. Image messages: Photos or screenshots analyzed to provide contextual answers. Document messages: PDFs, spreadsheets, or other files parsed for relevant content. Converts incoming queries to vector embeddings and performs similarity search on the MongoDB vector store. Uses OpenAI’s GPT-4o-mini model with retrieval-augmented generation to produce concise, context-aware answers. Maintains conversation context across multiple turns using a memory buffer node. Routes different message types to appropriate processing nodes to maximize answer quality. 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 Authenticate the WhatsApp node with your Meta account credentials to enable message receiving and sending. Connect the MongoDB collection containing embedded product documentation to the MongoDB Vector Search node used for similarity queries. Set up the system prompt in the Knowledge Base Agent node to reflect your company’s tone, answering style, and any business rules, ensuring it references the connected MongoDB collection for context retrieval. Make sure Both MongoDB nodes (in ingestion and chat workflows) are connected to the same collection with: An embedding field storing vector data, Relevant metadata fields (e.g., document ID, source), and The same vector index name configured (e.g., data_index). Search Index Example: { "mappings": { "dynamic": false, "fields": { "_id": { "type": "string" }, "text": { "type": "string" }, "embedding": { "type": "knnVector", "dimensions": 1536, "similarity": "cosine" }, "source": { "type": "string" }, "doc_id": { "type": "string" } } } }
By NovaNodeCreate & upload AI-generated ASMR YouTube Shorts with Seedance, Fal AI, and GPT-4
//ASMR AI Workflow Who is this for? Content Creators, YouTube Automation Enthusiasts, and AI Hobbyists looking to autonomously generate and publish unique, satisfying ASMR-style YouTube Shorts without manual effort. What problem does this solve? This workflow solves the creative bottleneck and time-consuming nature of daily content creation. It fully automates the entire production pipeline, from brainstorming trendy ideas to publishing a finished video, turning your n8n instance into a 24/7 content factory. What this workflow does Two-Stage AI Ideation & Planning: Uses an initial AI agent to brainstorm a short, viral ASMR concept based on current trends. A second "Planning" AI agent then takes this concept and expands it into a detailed, structured production plan, complete with a viral-optimized caption, hashtags, and descriptions for the environment and sound. Multi-Modal Asset Generation: Video: Feeds detailed scene prompts to the ByteDance Seedance text-to-video model (via Wavespeed AI) to generate high-quality video clips. Audio: Simultaneously calls the Fal AI text-to-audio model to create custom, soothing ASMR sound effects that match the video's theme. Assembly: Automatically sequences the video clips and sound into a single, cohesive final video file using an FFMPEG API call. Closed-Loop Publishing & Logging: Logging: Initially logs the new idea to a Google Sheet with a status of "In Progress". Publishing: Automatically uploads the final, assembled video directly to your YouTube channel, setting the title and description from the AI's plan. Updating: Finds the original row in the Google Sheet and updates its status to "Done", adding a direct link to the newly published YouTube video. Notifications: Sends real-time alerts to Telegram and/or Gmail with the video title and link, confirming the successful publication. Setup Credentials: You will need to create credentials in your n8n instance for the following services: OpenAI API Wavespeed AI API (for Seedance) Fal AI API Google OAuth Credential (enable YouTube Data API v3 and Google Sheets API in your Google Cloud Project) Telegram Bot Credential (Optional) Gmail OAuth Credential Configuration: This is an advanced workflow. The initial setup should take approximately 15-20 minutes. Google Sheet: Create a Google Sheet with these columns: idea, caption, productionstatus, youtubeurl. Add the Sheet ID to the Google Sheets nodes in the workflow. Node Configuration: In the Telegram Notification node, enter your own Chat ID. In the Gmail Notification node, update the recipient email address. Activate: Once configured, save and set the workflow to "Active" to let it run on its schedule. How to customize Creative Direction: To change the style or theme of the videos (e.g., from kinetic sand to soap cutting), simply edit the systemMessage in the "2. Enrich Idea into Plan" and "Prompts AI Agent" nodes. Initial Ideas: To influence the AI's starting concepts, modify the prompt in the "1. Generate Trendy Idea" node. Video & Sound: To change the video duration or sound style, adjust the parameters in the "Create Clips" and "Create Sounds" nodes. Notifications: Add or remove notification channels (like Slack or Discord) after the "Upload to YouTube" node.
By Bilel Aroua🎓 Learn JSON basics with an interactive step-by-step tutorial for beginners
How it works This workflow is an interactive, hands-on tutorial designed to teach you the absolute basics of JSON (JavaScript Object Notation) and, more importantly, how to use it within n8n. It's perfect for beginners who are new to automation and data structures. The tutorial is structured as a series of simple steps. Each node introduces a new, fundamental concept of JSON: Key/Value Pairs: The basic building block of all JSON. Data Types: It then walks you through the most common data types one by one: String (text) Number (integers and decimals) Boolean (true or false) Null (representing "nothing") Array (an ordered list of items) Object (a collection of key/value pairs) Using JSON with Expressions: The most important step! It shows you how to dynamically pull data from a previous node into a new one using n8n's expressions ({{ }}). Final Exam: A final node puts everything together, building a complete JSON object by referencing data from all the previous steps. Each node has a detailed sticky note explaining the concept in simple terms. Set up steps Setup time: 0 minutes! This is a tutorial workflow, so there is no setup required. Simply click the "Execute Workflow" button to run it. Follow the instructions in the main sticky note: click on each node in order, from top to bottom. For each node, observe the output in the right-hand panel and read the sticky note next to it to understand what you're seeing. By the end, you'll have a solid understanding of what JSON is and how to work with it in your own n8n workflows.
By Lucas PeyrinLead generation system: Google Maps to email scraper with Google Sheets export
Google Maps Email Scraper System Categories: Lead Generation, Web Scraping, Business Automation This workflow creates a completely free Google Maps email scraping system that extracts unlimited business emails without requiring expensive third-party APIs. Built entirely in N8N using simple HTTP requests and JavaScript, this system can generate thousands of targeted leads for any industry or location while operating at 99% free cost structure. Benefits Zero API Costs - Operates entirely through free Google Maps scraping without expensive third-party services Unlimited Lead Generation - Extract emails from thousands of Google Maps listings across any industry Geographic Targeting - Search by specific cities, regions, or business types for precise lead targeting Complete Automation - From search query to organized email list with minimal manual intervention Built-in Data Cleaning - Automatic duplicate removal, filtering, and data validation Scalable Processing - Handle hundreds of businesses per search with intelligent rate limiting How It Works Google Maps Search Integration: Uses strategic HTTP requests to Google Maps search URLs Processes search queries like "Calgary + dentist" to extract business listings Bypasses API restrictions through direct HTML scraping techniques Intelligent URL Extraction: Custom JavaScript regex patterns extract website URLs from Google Maps data Filters out irrelevant domains (Google, schema, static files) Returns clean list of actual business websites for processing Smart Website Processing: Loop-based architecture prevents IP blocking through intelligent batching Built-in delays and redirect handling for reliable scraping Processes each website individually with error handling Email Pattern Recognition: Advanced regex patterns identify email addresses within website HTML Extracts contact emails, info emails, and administrative addresses Handles multiple email formats and validation patterns Data Aggregation & Cleaning: Automatically removes duplicate emails across all processed websites Filters null entries and invalid email formats Exports clean, organized email lists to Google Sheets Required Google Sheets Setup Create a Google Sheet with these exact column headers: Search Tracking Sheet: searches - Contains your search queries (e.g., "Calgary dentist", "Miami lawyers") Email Results Sheet: emails - Contains extracted email addresses from all processed websites Setup Instructions: Create Google Sheet with two tabs: "searches" and "emails" Add your target search queries to the searches tab (one per row) Connect Google Sheets OAuth credentials in n8n Update the Google Sheets document ID in all sheet nodes The workflow reads search queries from the first sheet and exports results to the second sheet automatically. Business Use Cases Local Service Providers - Find competitors and potential partners in specific geographic areas B2B Sales Teams - Generate targeted prospect lists for cold outreach campaigns Marketing Agencies - Build industry-specific lead databases for client campaigns Real Estate Professionals - Identify businesses in target neighborhoods for commercial opportunities Franchise Development - Research potential markets and existing competition Market Research - Analyze business density and contact information across regions Revenue Potential This system transforms lead generation economics: $0 per lead vs. $2-5 per lead from paid databases Process 1,000+ leads daily without hitting API limits Sell as a service for $500-2,000 per industry/location Perfect for agencies offering lead generation to local businesses Difficulty Level: Intermediate Estimated Build Time: 1-2 hours Monthly Operating Cost: $0 (completely free) Watch My Complete Build Process Want to watch me build this entire system live from scratch? I walk through every single step - including the JavaScript code, regex patterns, error handling, and all the debugging that goes into creating a bulletproof scraping system. 🎥 Watch My Live Build: "Scrape Unlimited Leads WITHOUT Paying for APIs (99% FREE)" This comprehensive tutorial shows the real development process - including writing custom JavaScript, handling rate limits, and building systems that actually work at scale without getting blocked. Set Up Steps Basic Workflow Architecture: Set up manual trigger for testing and Google Sheets integration Configure initial HTTP request node for Google Maps searches Enable SSL ignore and response headers for reliable scraping URL Extraction Code Setup: Configure JavaScript code node with custom regex patterns Set up input data processing from Google Maps HTML responses Implement URL filtering logic to remove irrelevant domains Website Processing Pipeline: Add "Split in Batches" node for intelligent loop processing Configure HTTP request nodes with proper delays and redirect handling Set up error handling for websites that can't be scraped Email Extraction System: Implement JavaScript code node with email-specific regex patterns Configure email validation and format checking Set up data aggregation for multiple emails per website Data Cleaning & Export: Configure filtering nodes to remove null entries and duplicates Set up "Split Out" node to aggregate emails into single list Connect Google Sheets integration for organized data export Testing & Optimization: Use limit nodes during testing to prevent IP blocking Test with small batches before scaling to full searches Implement proxy integration for high-volume usage Advanced Optimizations Scale the system with: Multi-Page Scraping: Extract URLs from homepages, then scrape contact pages for more emails Proxy Integration: Add residential proxies for unlimited scraping without rate limits Industry Templates: Create pre-configured searches for different business types Contact Information Expansion: Extract phone numbers, addresses, and social media profiles CRM Integration: Automatically add leads to sales pipelines and marketing sequences Important Considerations Rate Limiting: Built-in delays prevent IP blocking during normal usage Scalability: For high-volume usage, consider proxy services for unlimited requests Compliance: Ensure proper usage rights for extracted contact information Data Quality: System includes filtering but manual verification recommended for critical campaigns Check Out My Channel For more advanced automation systems and business-building strategies that generate real revenue, explore my YouTube channel where I share proven automation techniques used by successful agencies and entrepreneurs.
By Nick SaraevAI agent for Instagram DM/inbox. Manychat + Open AI integration
Automate Instagram DMs with OpenAI GPT and ManyChat How It Works: Once connected, GPT will automatically initiate conversations with messages from new recipients in Intagram. Who Is This For? This workflow is ideal for marketers, business owners content creators who want to automatically respond to Instagram direct messages using OpenAI GPT. By integrating ManyChat, you can manage conversations, nurture leads, and provide instant replies at scale. What This Workflow Does Captures incoming Instagram DMs through ManyChat’s integration. Processes messages with GPT to generate a relevant response. Delivers instant replies back to Instagram users, creating efficient, AI-driven communication. Setup Import the Template: Copy the n8n workflow into your workspace. OpenAI Credentials: Add your OpenAI API key in n8n so GPT can generate responses. ManyChat Account: Create (or log in to) your ManyChat account. Connect Instagram: Link your Instagram profile as a channel in ManyChat. ManyChat Custom Field: Create a custom field for storing user input or conversation context. Configure Default Reply: In ManyChat, set up the default Instagram reply flow to point to your n8n webhook. Add External Request: Create an external request step in ManyChat to send messages to n8n. Test the Flow: Send yourself a DM on Instagram to confirm the workflow triggers and GPT responds correctly. Instructions and links: Notion instruction Register in ManyChat
By Alex Hi no code✨ Vision-based AI agent scraper - with Google Sheets, ScrapingBee, and Gemini
Important Notes: Check Legal Regulations: This workflow involves scraping, so ensure you comply with the legal regulations in your country before getting started. Better safe than sorry! Workflow Description: 😮💨 Tired of struggling with XPath, CSS selectors, or DOM specificity when scraping ? This AI-powered solution is here to simplify your workflow! With a vision-based AI Agent, you can extract data effortlessly without worrying about how the DOM is structured. This workflow leverages a vision-based AI Agent, integrated with Google Sheets, ScrapingBee, and the Gemini-1.5-Pro model, to extract structured data from webpages. The AI Agent primarily uses screenshots for data extraction but switches to HTML scraping when necessary, ensuring high accuracy. Key Features: Google Sheets Integration: Manage URLs to scrape and store structured results. ScrapingBee: Capture full-page screenshots and retrieve HTML data for fallback extraction. AI-Powered Data Parsing: Use Gemini-1.5-Pro for vision-based scraping and a Structured Output Parser to format extracted data into JSON. Token Efficiency: HTML is converted to Markdown to optimize processing costs. This template is designed for e-commerce scraping but can be customized for various use cases.
By DatakiGenerate Funny AI Videos with Sora 2 and Auto-Publish to TikTok
This automation creates a fully integrated pipeline to generate AI-powered videos, store them, and publish them on TikTok — all automatically. It connects OpenAI Sora 2, and Postiz (for TikTok publishing) to streamline content creation. --- Key Benefits ✅ Full Automation – From text prompt to TikTok upload, everything happens automatically with no manual intervention once set up. ✅ Centralized Control – Google Sheets acts as a simple dashboard to manage prompts, durations, and generated results. ✅ AI-Powered Creativity – Uses OpenAI Sora 2 for realistic video generation and GPT-5 for optimized titles. ✅ Social Media Integration – Seamlessly posts videos to TikTok via Postiz, ready for your audience. ✅ Scalable & Customizable – Can easily be extended to other platforms like YouTube, Instagram, or LinkedIn. ✅ Time-Saving – Eliminates repetitive steps like manual video uploads or caption writing. --- How it works This workflow automates the end-to-end process of generating AI videos and publishing them to TikTok. It is triggered either manually or on a recurring schedule. Trigger & Data Fetch: The workflow starts by checking a specified Form for new entries. It looks for rows where a video has been requested (a "PROMPT" is filled) but not yet generated (the "VIDEO" column is empty). AI Video Generation: For each new prompt found, the workflow sends a request to the Fal.ai Sora 2 model to generate a video. It then enters a polling loop, repeatedly checking the status of the generation request every 60 seconds until the video is "COMPLETED". Post-Processing & Upload: Once the video is ready, the workflow performs several actions in parallel: Fetch Video & Store: It retrieves the final video URL, downloads the video file Generate Title: It uses the OpenAI GPT-4o-mini model to analyze the original prompt and generate an optimized, engaging title for the video. Publish to TikTok: The video file is uploaded to Postiz, a social media scheduling tool, which then automatically publishes it to a connected TikTok channel, using the AI-generated title as the post's caption. --- Set up steps To make this workflow functional, you need to complete the following configuration steps: Prepare the Google Sheet: Create a Form with at least "PROMPT", "DURATION", and "VIDEO" fields. Configure Fal.ai for Video Generation: Create an account at Fal.ai and obtain your API key. In both the "Create Video" and "Get status" HTTP Request nodes, set up the "Header Auth" credential. Set the Name to Authorization and the Value to Key YOURAPIKEY. Set up TikTok Publishing via Postiz: Create an account on Postiz and connect your TikTok account to get a Channel ID. Obtain your Postiz API key. In the "Upload Video to Postiz" and "TikTok" (Postiz) nodes, configure the API credentials. In the "TikTok" node, replace the placeholder "XXX" in the integrationId field with your actual TikTok Channel ID from Postiz. (Optional) Configure AI Title Generation: The "Generate title" node uses OpenAI. Ensure you have valid OpenAI API credentials configured in n8n for this node to work. --- Need help customizing? Contact me for consulting and support or add me on Linkedin. Header 2
By DavideAI Timesheet Generator with Gmail, Calendar & GitHub to Google Sheets
AI-Powered Automatic Timesheet Generator for Google Sheets Stop wasting billable hours on manual time-tracking. AutoTimesheet Pro uses AI to collect emails, meetings, and GitHub work, then writes a clean timesheet straight into Google Sheets. Perfect for developers, consultants, agencies, and remote teams. Get Started with n8n now! --- 🚀 Key Features Automated Google Sheets time-tracking — zero spreadsheet prep. AI-generated activity summaries (≤ 120 chars) via OpenAI GPT-4o-mini. Gmail integration — logs only important emails, skipping newsletters & no-replies. Google Calendar time logger — captures confirmed events, duration, and attendees. GitHub commit & PR tracker — records your commits plus opened/closed PRs. Daily 7 PM cron trigger (easily adjustable). Month-based sheet creation — new tab spins up on the first run each month. No-code n8n template — just connect credentials and tweak one Set Variables node. 🔌 Easily extensible — drag-and-drop extra n8n nodes to add Slack, Jira, Notion, Asana, Trello, Toggl, or any other data source you need. --- 🔍 How It Works Collect — n8n pulls data from Gmail, Google Calendar, and chosen GitHub repos. Clean — filters remove noise (newsletters, irrelevant commits, etc.). Condense — OpenAI rewrites each item into a concise, SEO-friendly description. Write — workflow appends Date, Type, and Description to your Timesheet Google Sheet. Extend — simply insert new n8n nodes (e.g., Slack, Notion, Jira) and merge them into the same pipeline. --- 📈 Benefits for SEO-Minded Professionals Keyword-rich activity log improves internal search and reporting. Structured data in Sheets simplifies export to accounting or PM tools. Consistent naming (CALENDAR_EVENT, EMAIL, COMMIT, PR) makes analytics easy. --- ✅ Why Choose AutoTimesheet Pro? Zero manual entry — just open the sheet and bill clients. Immediate visibility into where your hours went. Works with any GitHub repo list and any inbox you own. 100 % no-code setup — activate in minutes. Built on n8n, so you can customize and scale without limits. --- 📥 Get Started Ready to replace manual time-tracking with smart automation? https://n8n.partnerlinks.io/ds9podzjls6d Join N8N now, connect your Google & GitHub accounts, and let AI handle your daily log. ---
By Luka ZivkovicAI Assistant which answers questions with a RAG MCP and a Search Engine MCP
Build an AI Agent which accesses two MCP Servers: a RAG MCP Server and a Search Engine API MCP Server. This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Tutorial Click here to watch the full tutorial on YouTube! How it works We build an AI Agent which has access to two MCP servers: An MCP Server with a RAG database (click here for the RAG MCP Server An MCP Server which can access a Search Engine, so the AI Agent also has access to data about more current events Installation In order to use the MCP Client, you also have to use MCP Server Template. Open the MCP Client "MCP Client: RAG" node and update the SSE Endpoint to the MCP Server workflow Install the "n8n-nodes-mcp" community node via settings > community nodes ONLY FOR SELF-HOSTING: In Docker, click on your n8n container. Navigate to "Exec" and execute the below command to allow community nodes: N8NCOMMUNITYPACKAGESALLOWTOOL_USAGE=true Navigate to Bright Data and create a new "Web Unlocker API" with the name "mcp_unlocker". Open the "MCP Client" and add the following credentials: How to use it Run the Chat node and start asking questions More detailed instructions Missed a step? Find more detailed instructions here: Personal Newsfeed With Bright Data and n8n What is Retrievel Augmented Generation (RAG)? Large Language Models (LLM's) are trained on data until a specific cutoff date. Imagine a model is trained in December 2023 based data until September 2023. This means the model doesn't have any knowledge about events which happened in 2024. So if you ask the LLM who was the Formula 1 World Champion of 2024, it doesn't know the answer. The solution? Retrieval Augmented Generation. When using Retrieval Augmented Generation, a user's question is being sent to a semantic database. The LLM will use the information retrieved from the semantic database to answer the user's question. What is Model Context Protocol (MCP)? MCP is a communication protocol which is used by AI agents to call tools hosted on external servers. When an MCP client communicates with an MCP server, the server will provide an overview of all its tools, prompts and resources. The MCP server can then choose which tools to execute (based on the user's request) and execute the tools. An MCP client can communicate with multiple MCP servers, which can all host multiple tools.
By Thomas JanssenUpload video, create playlist and add video to playlist
No description available.
By Harshil AgrawalTelegram bot with Supabase memory and OpenAI assistant integration
Video Guide I prepared a detailed guide that showed the whole process of building an AI bot, from the simplest version to the most complex in a template. .png) Who is this for? This workflow is ideal for developers, chatbot enthusiasts, and businesses looking to build a dynamic Telegram bot with memory capabilities. The bot leverages OpenAI's assistant to interact with users and stores user data in Supabase for personalized conversations. What problem does this workflow solve? Many simple chatbots lack context awareness and user memory. This workflow solves that by integrating Supabase to keep track of user sessions (via telegramid and openaithread_id), allowing the bot to maintain continuity and context in conversations, leading to a more human-like and engaging experience. What this workflow does This Telegram bot template connects with OpenAI to answer user queries while storing and retrieving user information from a Supabase database. The memory component ensures that the bot can reference past interactions, making it suitable for use cases such as customer support, virtual assistants, or any application where context retention is crucial. 1.Receive New Message: The bot listens for incoming messages from users in Telegram. Check User in Database: The workflow checks if the user is already in the Supabase database using the telegram_id. Create New User (if necessary): If the user does not exist, a new record is created in Supabase with the telegramid and a unique openaithread_id. Start or Continue Conversation with OpenAI: Based on the user’s context, the bot either creates a new thread or continues an existing one using the stored openaithreadid. Merge Data: User-specific data and conversation context are merged. Send and Receive Messages: The message is sent to OpenAI, and the response is received and processed. Reply to User: The bot sends OpenAI’s response back to the user in Telegram. Setup Create a Telegram Bot using the Botfather and obtain the bot token. Set up Supabase: Create a new project and generate a SUPABASEURL and SUPABASEKEY. Create a new table named telegram_users with the following SQL query: create table public.telegram_users ( id uuid not null default genrandomuuid (), date_created timestamp with time zone not null default (now() at time zone 'utc'::text), telegram_id bigint null, openaithreadid text null, constraint telegramuserspkey primary key (id) ) tablespace pg_default; OpenAI Setup: Create an OpenAI assistant and obtain the OPENAIAPIKEY. Customize your assistant’s personality or use cases according to your requirements. Environment Configuration in n8n: Configure the Telegram, Supabase, and OpenAI nodes with the appropriate credentials. Set up triggers for receiving messages and handling conversation logic. Set up OpenAI assistant ID in "++OPENAI - Run assistant++" node.
By Mark ShcherbakovPush JSON data into an app or to spreadsheet file
This workflow template shows how to load JSON data into a workflow and push that data into an App or convert it into a Spreadsheet file. Specifically, this workflow shows how to make a generic API request that returns JSON. It then shows how to load that into a Google Sheets spreadsheet, or convert it to .CSV file format. However, you can use the general pattern to load data into any app or convert to any spreadsheet file format (such as .xlsx).
By n8n Team