Workflow Templates

This n8n template shows how anyone can build a simple newsletter-like subscription service where users can enrol themselves to receive messages/content on a regular basis. It uses n8n forms for data capture, Airtable for database, AI for content generation and Gmail for email sending. How it works An n8n form is setup up to allow users to subscribe with a desired topic and interval of which to recieve messages via n8n forms which is then added to the Airtable. A scheduled trigger is executed every morning and searches for subscribers to send messages for based on their desired intervals. Once found, Subscribers are sent to a subworkflow which performs the text content generation via an AI agent and also uses a vision model to generate an image. Both are attached to an email which is sent to the subscriber. This email also includes an unsubscribe link. The unsubscribe flow works similarly via n8n form interface which when submitted disables further scheduled emails to the user. How to use Make a copy of sample Airtable here: https://airtable.com/appL3dptT6ZTSzY9v/shrLukHafy5bwDRfD Make sure the workflow is "activated" and the forms are available and reachable by your audience. Requirements Airtable for Database OpenAI for LLM (but compatible with others) Gmail for Email (but can be replaced with others) Customising this workflow This simple use can be extended to deliver any types of content such as your company newsletter, promotions, social media posts etc. Doesn't have to be limited to just email - try social messaging, Whatsapp, Telegram and others.

This n8n workflow allows you to generate AI images using Nano Banana PRO through a Telegram bot interface, with optional automatic publishing to social media platforms. Users interact with the workflow entirely via Telegram commands and forms. The workflow supports multiple image generation modes and can automatically enhance prompts, compress images, generate captions, and publish content to Facebook, Instagram, and X. This template is especially useful for product visuals, lifestyle scenes, and content creation workflows where manual image generation and posting would otherwise be repetitive. How it works A user sends a command to the Telegram bot (text-to-image, image-to-image, or multi-image fusion). The workflow collects the required inputs (text prompt, uploaded images, aspect ratio, quality). If enabled, an AI Agent enhances the user prompt before image generation. The workflow sends the request to Kie.ai, which runs the Nano Banana PRO image model. The workflow waits for the image generation task to complete and retrieves the result. The generated image is downloaded and sent back to the user via Telegram. Optionally, the image is compressed using TinyPNG. If social sharing is enabled: An AI Agent generates platform-optimized captions. The image and captions are published automatically to selected platforms (Facebook, Instagram, X) via Blotato. How to use Create a Telegram bot using @BotFather and add the bot token to the Telegram Trigger credentials. Configure the required API credentials (see Requirements). Activate the workflow in n8n. Send a command to your Telegram bot: /text_to_image /image_to_image /multi_image Follow the Telegram form prompts to generate and optionally publish images. Requirements The following services are required for the workflow to function: Telegram Bot** – user interaction Kie.ai API** – Nano Banana PRO image generation (Get access) Cloudinary** – image hosting for uploaded files (Create an account) OpenAI API** – prompt enhancement and caption generation Optional services: TinyPNG** – image compression (Get an API key) Blotato** – social media publishing (Connect accounts) Customising the workflow You can disable image compression by removing the TinyPNG nodes. Social media auto-publishing can be disabled by removing the Blotato nodes. Prompt enhancement behavior can be adjusted in the AI Agent system prompt. Additional platforms or posting logic can be added after the caption generation step. The workflow can be adapted to other AI image models by replacing the Kie.ai API calls. Notes This is a self-hosted n8n workflow. All API keys and credentials must be provided by the user. The workflow is modular and can be partially enabled depending on your use case.

This is a simple template to show how to extract multiple email attachments and return them as an iterable output. How it works: The Gmail Trigger node detects any new email that has attachments. The Code node will then extract them as binary files and attaches them to the item. They can then be uploaded via the Google Drive node. Setup steps: add your Gmail Credentials add your Google Drive Credentials Follow the official n8n Documentation for help Feedback & Questions If you have any questions or feedback about this workflow - Feel free to get in touch at ria@n8n.io

What it does This n8n workflow creates a cutting-edge, multi-modal AI Memory Assistant designed to capture, understand, and intelligently recall your personal or business information from diverse sources. It automatically processes voice notes, images, documents (like PDFs), and text messages sent via Telegram. Leveraging GPT-4o for advanced AI processing (including visual analysis, document parsing, transcription, and semantic understanding) and MongoDB Atlas Vector Search for persistent and lightning-fast recall, this assistant acts as an external brain. Furthermore, it integrates with Gmail, allowing the AI to send and search emails as part of its memory and response capabilities. This end-to-end solution blurprint provides a powerful starting point for personal knowledge management and intelligent automation. How it works 1. Multi-Modal Input Ingestion 🗣️📸📄💬 Your memories begin when you send a voice note, an image, a document (e.g., PDF), or a text message to your Telegram bot. The workflow immediately identifies the input type. 2. Advanced AI Content Processing 🧠✨ Each input type undergoes specialized AI processing by GPT-4o: Voice notes are transcribed into text using OpenAI Whisper. Images are visually analyzed by GPT-4o Vision, generating detailed textual descriptions. Documents (PDFs) are processed for text extraction, leveraging GPT-4o for robust parsing and understanding of content and structure. Unsupported document types are gracefully handled with a user notification. Text messages are directly forwarded for further processing. This phase transforms all disparate input formats into a unified, rich textual representation. 3. Intelligent Memory Chunking & Vectorization ✂️🏷️➡️🔢 The processed content (transcriptions, image descriptions, extracted document text, or direct text) is then fed back into GPT-4o. The AI intelligently chunks the information into smaller, semantically coherent pieces, extracts relevant keywords and tags, and generates concise summaries. Each of these enhanced memory chunks is then converted into a high-dimensional vector embedding using OpenAI Embeddings. 4. Persistent Storage & Recall (MongoDB Atlas Vector Search) 💾🔍 These vector embeddings, along with their original content, metadata, and tags, are stored in your MongoDB Atlas cluster, which is configured with Atlas Vector Search. This allows for highly efficient and semantically relevant retrieval of memories based on user queries, forming the core of your "smart recall" system. 5. AI Agent & External Tools (Gmail Integration) 🤖🛠️ When you ask a question, the AI Agent (powered by GPT-4o) acts as the central intelligence. It uses the MongoDB Chat Memory to maintain conversational context and, crucially, queries the MongoDB Atlas Vector Search store to retrieve relevant past memories. The agent also has access to Gmail tools, enabling it to send emails on your behalf or search your past emails to find information or context that might not be in your personal memory store. 6. Smart Response Generation & Delivery 💬➡️📱 Finally, using the retrieved context from MongoDB and the conversational history, GPT-4o synthesizes a concise, accurate, and contextually aware answer. This response is then delivered back to you via your Telegram bot. How to set it up (~20 Minutes) Getting this powerful workflow running requires a few key configurations and external service dependencies. Telegram Bot Setup: Use BotFather in Telegram to create a new bot and obtain its API Token. In your n8n instance, add a new Telegram API credential. Give it a clear name (e.g., "My AI Memory Bot") and paste your API Token. OpenAI API Key Setup: Log in to your OpenAI account and generate a new API key. Within n8n, create a new OpenAI API credential. Name it appropriately (e.g., "My OpenAI Key for GPT-4o") and paste your API key. This credential will be used by the OpenAI Chat Model (GPT-4o for processing, chunking, and RAG), Analyze Image, and Transcribe Audio nodes. MongoDB Atlas Setup: If you don't have one, create a free-tier or paid cluster on MongoDB Atlas. Create a database and a collection within your cluster to store your memory chunks and their vector embeddings. Crucially, configure an Atlas Vector Search index on your chosen collection. This index will be on the field containing your embeddings (e.g., embedding field, type knnVector). Refer to MongoDB Atlas documentation for detailed instructions on creating vector search indexes. In n8n, add a new MongoDB credential. Provide your MongoDB Atlas connection string (ensure it includes your username, password, and database name), and give it a clear name (e.g., "My Atlas DB"). This credential will be used by the MongoDB Chat Memory node and for any custom HTTP requests you might use for Atlas Vector Search insertion/querying. Gmail Account Setup: Go to Google Cloud Console, enable the Gmail API for your project, and configure your OAuth consent screen. Create an OAuth 2.0 Client ID for a Desktop app (or Web application, depending on your n8n setup and redirect URI). Download the JSON credentials. In n8n, add a new Gmail OAuth2 API credential. Follow the n8n instructions to configure it using your Google Client ID and Client Secret, and authenticate with your Gmail account, ensuring it has sufficient permissions to send and search emails. External API Services: If your Extract from File node relies on an external service for robust PDF/DocX text extraction, ensure you have an API key and the service is operational. The current flow uses ConvertAPI. Add the necessary credential (e.g., ConvertAPI) in n8n. How you could enhance it ✨ This workflow offers numerous avenues for advanced customization and expansion: Expanded Document Type Support: Enhance the "Document Processing" section to handle a wider range of document types beyond just PDFs (e.g., .docx, .xlsx, .pptx, markdown, CSV) by integrating additional conversion APIs or specialized parsing libraries (e.g., using a custom code node or dedicated third-party services like Apache Tika, Unstructured.io). Fine-tuned Memory Chunks & Metadata: Implement more sophisticated chunking strategies for very long documents, perhaps based on semantic breaks or document structure (headings, sections), to improve recall accuracy. Add more metadata fields (e.g., original author, document date, custom categories) to your MongoDB entries for richer filtering and context. Advanced AI Prompting: Allow users to dynamically set parameters for their memory inputs (e.g., "This is a high-priority meeting note," "This image contains sensitive information") which can influence how GPT-4o processes, tags, and stores the memory, or how it's retrieved later. n8n Tool Expansion for Proactive Actions: Significantly expand the AI Agent's capabilities by providing it with access to a wider range of n8n tools, moving beyond just information retrieval and email External Data Source Integration (APIs): Expand the AI Agent's tools to query other external APIs (e.g., weather, stock prices, news, CRM systems) so it can provide real-time information relevant to your memories. Getting Assistance & More Resources Need assistance setting this up, adapting it to a unique use case, or exploring more advanced customizations? Don't hesitate to reach out! You can contact me directly at nanabrownsnr@gmail.com. Also, feel free to check out my Youtube Channel where I discuss other n8n templates, as well as Innovation and automation solutions.

This workflow gathers papers in Arxiv and specific arxiv category AI helps to make summarized form of newsletter and send it to subscriber using gmail Arxive paper trend newsletter Setup Supabase Table schema user_email: Text - Mandatory arxiv_cat: [Text] interested_papers: [Text] keyword: [Text] Example { "id": 8, "created_at": "2024-09-24T12:31:17.09491+00:00", "user_email": "test@test.com", "arxiv_cat": [ "cs.AI", "cs.LG,cs.AR" ], "interested_papers": null, "keyword": [ "AI architecture which includes long context problem" ] } Qdrant vector store default setup Setup for sub workflows Get arxiv category by AI for given keyword Get arxiv categories Get arxiv papers this week and scoring by AI Filter by keyword within given documents Extract paper information Write newsletter by AI

The Ultimate Gmail Analysis and Visual Summarization Template This workflow showcases various useful Gmail search, filter, and AI categorization operations and generates a knowledge graph for your mail using the InfraNodus GraphRAG API, which you can use to reveal the main topics and blind spots in your correspondence. InfraNodus will then target those blind spots to generate interesting research questions for you and send the topical summary and insights via Telegram. You can also click the generated graph and explore the blind spots inside InfraNodus using the interactive visual interface: What is it useful for? Learn about advanced Gmail search, filtering, and AI categorization functions** that can be useful for your other workflows Analyze all your personal messages for the last week to get an overview of the main topics Analyze all your Sent messages to find recurrent topics and gaps and generate ideas based. on those gaps Generate ideas based on specific message filters (Personal, Promos, from a specific person, AI-defined criteria, e.g. urgency) Get an overview of an interaction with a specific person / company Get an overview of your notes Generate new ideas based on your correspondence on a certain topic (e.g. "business") Learn about various n8n nodes useful for email processing, filtering, and data conversion Never miss important topics, use AI filter to get notified of the urgent and important emails via Telegram How it works This template can be triggered in multiple ways: automatically in regular intervals (daily, weekly), manually in n8n, or via a private password-protected URL form where you can specify your search and filtering criteria When you start the workflow, you specify: your Gmail search filters (can be combined, e.g. after:2025/06/01 label:personal business to search for all emails received after 1 June 2025, filed in the Personal category containing the word "business". (optional, if empty, will retrieve all the emails or limited to the number you set in the Gmail node) Additional Gmail labels (e.g. SENT or CATEGORY_PERSONAL or your custom categories). Use the search filter for faster processing (e.g. prefer label:person to CATEGORY_PERSONAL, but labels can be useful for additional filtering for your search queries) (optional, if empty, will retrieve all the emails) AI filtering criteria** — set an additional classification criteria used to filter out the emails, e.g. "Only the urgent, personal emails" — in that case, AI classification node working with Google's Gemini AI will be activated and will only pass through the email based on the criteria you specify. Whether you want to build a text graph or a social graph — see the workflow for detailed explanation of each Use snippets of emails (default) or full text (for thorough analysis). We prefer snippets as it's faster and your graph context doesn't get biased towards longer emails this way. Once you set up your search parameters in Steps 1 and 2, the template will follow the following steps: Step 3 — retrieve Google emails that satisfy your filter criteria. Filter them by additional labels provided if applicable. Step 4 - if the user chooses to analyze full text, use additional Gmail node that retrieves the full text of the email message Step 5 — if AI filter rule is provided, use the AI Classifier node with Google Gemini Pro 2.5 model to classify the email based on the rule provided. Bypass if empty. Step 6 - format the text or the email snippets to add the sender meta-data and category and to prepare to submit to InfraNodus Step 7 - submit the data to the InfraNodus HTTP graphAndEntries endpoint and generate a knowledge graph Step 8 - access this graph via the graphAndAdvice endpoint) and generate a topical summary based on the GraphRAG representation and insight questions bridging the gaps identified. Send the results via a Telegram bot. We use Telegram, because it takes only 30 seconds to set up a bot with an API, unlike Discord or Slack, which is long and cumbersome to set up. You can also attach a Gmail send node and generate an email instead. How to use You need an InfraNodus GraphRAG API account and key to use this workflow. Create an InfraNodus account Get the API key at https://infranodus.com/api-access and create a Bearer authorization key for the InfraNodus HTTP nodes. Add this Authorization code in Steps 7 and 8 of the workflow. Come up with the name of the graph and change it in the HTTP InfraNodus nodes in the steps 7 and 8 and also in the Telegram nodes that send a link to the graph. For additional settings you can use in the HTTP InfraNodus nodes, see the InfraNodus access points page. Authorize your Gmail account for Steps 2 and 3 Gmail nodes. The easiest way to set it up is to open a free Google Console API account and to create an OAuth access point for n8n. You can then reuse it with other Google services like Google Sheets, Drive, etc. So it's a useful thing to have in general. Set up the Gemini AI API key using the instructions in the Step 5 Gemini AI node. Set up the Telegram node bot for the Step 8. It takes only 30 seconds: just go to @botfather and type in /newbot and you'll have an API key ready. To get the conversation ID, follow the n8n / Telegram instructions in the node itself. Once everything is ready, try to run the default automated workflow to test if everything works well, then use the Form for playing around with specific filters that you may find useful. Requirements An InfraNodus account and API key An Google Cloud API OAuth client and key for Gmail access A Gemini AI API key A Telegram bot API key FAQ 1. What's the best search query to use? I personally like starting with analyzing the messages Gmail tags as "personal" from the last week (using the after:2025/05/28 label:personal search query) using the social graph settings. It helps me see who I interacted with, what it was about, and gives me a good bird's eye view into my last week's interactions, helping me see if I didn't miss anything. I also find it useful to analyze the sent messages (using the after:2025/05/28 label:sent search filter or SENT category filter) as it helps me see what I was writing about recently and understand some recurrent topics and gaps in my interactions. Finally, I also like to analyze notes (label:notes) or specific correspondence (from:your_friend@gmail.com) to get an overview and find gaps in the conversations. 2. Why use InfraNodus and not an AI summarization module? You probably get a lot of spam, so your AI will get overwhelmed with the content that's not really useful. The InfraNodus graph helps you see the important patterns and discover what's missing by focusing on the gaps. You can use the interactive graph to quickly remove the stuff you don't need and to focus on the most relevant topics and conversations. Customizing this workflow You can connect a Gmail node instead of the Telegram one if you prefer to receive notifications directly by email. I don't like using Slack and Discord because their bots are too difficult to set up and take too long. Check out the complete setup guide for this workflow at https://support.noduslabs.com/hc/en-us/articles/20394884531996-Build-a-Knowledge-Graph-and-Extract-Insights-from-Gmail-Emails-with-n8n-and-InfraNodus with a video tutorial coming soon and the links to other n8n workflows. Check our other n8n workflows at https://n8n.io/creators/infranodus/ for useful content gap analysis, expert panel, and marketing, and research workflows that utilize GraphRAG for better AI generation. Finally, check out https://infranodus.com to learn more about our network analysis technology used to build knowledge graphs from text.

This workflow will allow you to use OpenAI Assistant API together with a chatting platform. This version is configured to work with Hubspot, however, the Hubspot modules can be replaced by other platform and it will work similarly. Prerequisites: Create a Hubspot Chat (Live chat available on free plan) or Chatflow (paid hubspot only) and configure it to send all replies toward an n8n webhook (you need to create a custom app for that. I will create a separate article on how to do it, meanwhile, feel free to message me if you need support. Setup: Create a OpenAI Assistant, define its functionality and functions Update the Hubspot modules with the Hubspot API Key Update the OpenAI modules with OpenAI API Key Create an Airtable or any other database where you keep a reference between the thread id in Hubspot and Assistant API If you need help deploying this solution don't hesitate to email me or schedule a call here.

Generate AI videos with Seedance & Blotato, upload to TikTok, YouTube & Instagram Who is this for? This template is ideal for creators, content marketers, social media managers, and AI enthusiasts who want to automate the production of short-form, visually captivating videos for platforms like TikTok, YouTube Shorts, and Instagram Reels — all without manual editing or publishing. What problem is this workflow solving? Creating engaging videos requires: Generating creative ideas Writing detailed scene prompts Producing realistic video clips and sound effects Editing and stitching the final video Publishing across multiple platforms This workflow automates the entire process, saving hours of manual work and ensuring consistent, AI-driven content output ready for social distribution. What this workflow does This end-to-end AI video automation workflow: Generates a creative idea using OpenAI and LangChain Creates detailed video prompts with Seedance AI Generates video clips via Wavespeed AI Generates sound effects with Fal AI Stitches the final video using Fal AI’s ffmpeg API Logs metadata and video links to Google Sheets Uploads the video to Blotato Auto-publishes to TikTok, YouTube, Instagram, and other platforms Setup Add your OpenAI API key in the LLM nodes Set up Seedance and Wavespeed AI credentials for video prompt and clip generation Add your Fal AI API key for sound and stitching steps Connect your Google Sheets account for tracking ideas and outputs Set your Blotato API key and fill in the platform account IDs in the Assign Social Media IDs node Adjust the Schedule Trigger to control when the automation runs How to customize this workflow to your needs Change the AI prompts** to target your niche (e.g., ASMR, product videos, humor) Add a Telegram or Slack step** for video preview before publishing Tweak scene structure** or video duration to match your style Disable platforms** you don’t want by turning off specific HTTP Request nodes Edit the sound generation prompts** for different moods or effects 📄 Documentation: Notion Guide Need help customizing? Contact me for consulting and support : Linkedin / Youtube

AI-Powered Lead Generation with Apollo, GPT-4, and Telegram to Database Overview This intelligent lead generation workflow transforms voice commands or text input into verified prospect lists through automated Apollo.io scraping. The system processes natural language requests, extracts search parameters using AI, and delivers clean, verified contact data directly to your database. Key Features 🎤 Voice & Text Input Processing Voice Recognition**: Converts audio messages to text using OpenAI's transcription API Natural Language Processing**: AI agent interprets requests and extracts search criteria Flexible Input**: Supports both voice commands and text messages 🔍 Smart Lead Scraping Apollo.io Integration**: Automated scraping using official Apollo.io API Dynamic URL Generation**: Builds search URLs based on extracted parameters Intelligent Parsing**: Processes location, industry, and job title criteria ✅ Email Verification & Filtering Verified Emails Only**: Filters results to include only verified email addresses Duplicate Prevention**: Compares against existing database to avoid duplicates Data Quality Control**: Ensures high-quality prospect data 📊 Automated Data Management Database Integration**: Automatic storage in PostgreSQL/Supabase Structured Data**: Organizes contacts with complete profile information Real-time Updates**: Instant database updates with new prospects How It Works Input Processing: Receive voice message or text command AI Analysis: Extract search parameters (location, industry, job titles) URL Construction: Build Apollo.io search URL with extracted criteria Data Scraping: Retrieve prospect data via Apollo.io API Email Verification: Filter for verified email addresses only Duplicate Check: Compare against existing database records Data Storage: Save new prospects to database Confirmation: Send success notification with count of new leads Supported Search Parameters Location**: City, state, country combinations Industry**: Business sectors and verticals Job Titles**: Executive roles, departments, seniority levels Company Size**: Organization scale and employee count Data Fields Extracted Contact Information First Name & Last Name Email Address (verified only) LinkedIn Profile URL Phone Number (when available) Professional Details Current Job Title Company Name Industry Seniority Level Employment History Location Data City & State Country Full Location String Company Information Website URL Business Industry Organization Details Technical Architecture Core Components n8n Workflow Engine**: Orchestrates the entire process OpenAI Integration**: Powers voice transcription and AI analysis Apollo.io API**: Source for prospect data PostgreSQL/Supabase**: Database storage and management API Integrations OpenAI Whisper API for voice transcription OpenAI GPT for natural language processing Apollo.io API for lead data retrieval Supabase API for database operations Use Cases Sales Teams Quickly build prospect lists for outreach campaigns Target specific industries or job roles Maintain clean, verified contact databases Marketing Professionals Generate targeted lead lists for campaigns Research prospects in specific markets Build comprehensive contact databases Business Development Identify potential partners or clients Research competitive landscapes Generate contact lists for networking Recruitment Find candidates in specific locations Target particular job roles or industries Build talent pipeline databases Benefits ⚡ Speed & Efficiency Voice commands for instant lead generation Automated processing eliminates manual work Batch processing for large prospect lists 🎯 Precision Targeting AI-powered parameter extraction Flexible search criteria combinations Industry and role-specific filtering 📈 Data Quality Verified email addresses only Duplicate prevention Structured, consistent data format 🔄 Automation End-to-end automated workflow Real-time database updates Instant confirmation notifications Setup Requirements Prerequisites n8n workflow platform OpenAI API access Apollo.io API credentials PostgreSQL or Supabase database Messaging platform integration Configuration Steps Import workflow into n8n Configure API credentials Set up database connections Customize search parameters Test with sample voice/text input Customization Options Search Parameters Modify location formats Add custom industry categories Adjust job title variations Set result limits Data Processing Customize field mappings Add data validation rules Implement additional filters Configure output formats Integration Options Connect to CRM systems Add email marketing tools Integrate with sales platforms Export to various formats Success Metrics Processing Speed**: Voice-to-database in under 30 seconds Data Accuracy**: 95%+ verified email addresses Automation Level**: 100% hands-free operation Scalability**: Process 500+ leads per request Transform your lead generation process with intelligent automation that understands natural language and delivers verified prospects directly to your database.

Empower Your AI Chatbot with Long-Term Memory and Dynamic Tool Routing This n8n workflow equips your AI agent with long-term memory and a dynamic tools router, enabling it to provide intelligent, context-aware responses while managing tasks across multiple tools. By combining persistent memory and modular task routing, this workflow makes your AI smarter, more efficient, and highly adaptable. 👥 Who Is This For? AI Developers & Automation Enthusiasts: Integrate advanced AI features like long-term memory and task routing without coding expertise. Businesses & Teams: Automate tasks while maintaining personalized, context-aware interactions. Customer Support Teams: Improve user experience with chatbots that remember past interactions. Marketers & Content Creators: Streamline communication across platforms like Gmail and Telegram. AI Researchers: Experiment with persistent memory and multi-tool integration. 🚀 What Problem Does This Solve? This workflow simplifies the creation of intelligent AI systems that retain memory, manage tasks dynamically, and automate notifications across tools like Gmail and Telegram—saving time and improving efficiency. 🛠️ What This Workflow Does Save & Retrieve Memories**: Uses Google Docs for long-term storage to recall past interactions or user preferences. Dynamic Task Routing**: Routes tasks to the right tools (e.g., saving/retrieving memories or sending notifications). AI-Powered Context Understanding**: Combines OpenAI GPT-based short-term memory with long-term memory for smarter responses. Multi-Channel Notifications**: Sends updates via Gmail or Telegram. 🔧 Setup API Credentials: Connect to OpenAI (AI processing), Google Docs (memory storage), Gmail/Telegram (notifications). Customize Parameters: Adjust the AI agent's system message for your use case. Define task-routing rules in the tools router node. Test & Deploy: Verify memory saving/retrieval, task routing, and notification delivery. 💡 How to Customize Modify the system message in the OpenAI node to tailor your agent’s behavior. Add or adjust routing rules for additional tools. Update notification settings to match your communication preferences.

🤖 AI-Powered RAG Chatbot with Google Drive Integration This workflow creates a powerful RAG (Retrieval-Augmented Generation) chatbot that can process, store, and interact with documents from Google Drive using Qdrant vector storage and Google's Gemini AI. How It Works Document Processing & Storage 📚 Retrieves documents from a specified Google Drive folder Processes and splits documents into manageable chunks Extracts metadata using AI for enhanced search capabilities Stores document vectors in Qdrant for efficient retrieval Intelligent Chat Interface 💬 Provides a conversational interface powered by Google Gemini Uses RAG to retrieve relevant context from stored documents Maintains chat history in Google Docs for reference Delivers accurate, context-aware responses Vector Store Management 🗄️ Features secure delete operations with human verification Includes Telegram notifications for important operations Maintains data integrity with proper version control Supports batch processing of documents Setup Steps Configure API Credentials: Set up Google Drive & Docs access Configure Gemini AI API Set up Qdrant vector store connection Add Telegram bot for notifications Add OpenAI Api Key to the 'Delete Qdrant Points by File ID' node Configure Document Sources: Set Google Drive folder ID Define Qdrant collection name Set up document processing parameters Test and Deploy: Verify document processing Test chat functionality Confirm vector store operations Check notification system This workflow is ideal for organizations needing to create intelligent chatbots that can access and understand large document repositories while maintaining context and providing accurate responses through RAG technology.

How it works • Automates multi-platform social media posting (Instagram, YouTube, TikTok, etc.) using AI-generated content • Integrates Airtable, n8n, and Blotato for full content scheduling and publishing • Supports both image and video uploads with dynamic text and account routing Set up steps • Takes ~15–30 minutes to set up depending on how many platforms you connect • Requires Airtable personal access token and Blotato API key • Uses sticky notes throughout the workflow to explain config, tokens, and troubleshooting clearly