Meelioo
AI Developer & Automation Consultant
Templates by Meelioo
Pdf RAG agent with Telegram chat & auto-ingestion from Google Drive
How it works This workflow creates an intelligent document assistant called "Mookie" that can answer questions based on your uploaded documents. Here's how it operates: Document Ingestion: The system can automatically load PDF files from Google Drive or accept PDFs uploaded directly through Telegram, then processes and stores them in a PostgreSQL vector database using Mistral embeddings Smart Retrieval: When users ask questions via Telegram or a web chat interface, the AI agent searches through the stored documents to find relevant information using vector similarity matching Contextual Responses: Using GPT-4 and the retrieved document context, Mookie provides accurate answers based solely on the ingested documents, avoiding hallucination by refusing to answer questions not covered in the stored materials Memory & Conversation: The system maintains conversation history for each user, allowing for natural follow-up questions and contextual discussions Set up steps Estimated setup time: 30-45 minutes You'll need to configure several external services and credentials: Set up a PostgreSQL database with PGVector extension for document storage Create accounts and API keys for Azure OpenAI (GPT-4), Mistral Cloud (embeddings), and Google Drive access Connect your own LLM's if you don't have these credentials. Configure a Telegram bot and obtain API credentials for chat functionality Update webhook URLs throughout the workflow to match your n8n instance Test the document ingestion pipeline with sample PDFs Verify the chat interfaces (both Telegram and web) are responding correctly >The workflow includes approval mechanisms for PDF ingestion and handles both automated bulk processing from Google Drive and real-time document uploads through Telegram. Read the sticky notes provided in the template code for clear instructions.
By MeeliooBeginner's Guide to Workflow Automation with OpenAI, LangChain & API Integrations
How it works This beginner-friendly workflow demonstrates the core building blocks of n8n. It guides you through: Triggers – Start workflows manually, on a schedule, via webhooks, or through chat. Data processing – Use Set and Code nodes to create, transform, and enrich data. Logic and branching – Apply conditions with IF nodes and merge different branches back together. API integrations – Fetch external data (e.g., users from an API), split arrays into individual items, and extract useful fields. AI-powered steps – Connect to OpenAI for generating fun facts or build interactive assistants with chat triggers, memory, and tools. Responses – Return structured results via webhooks or summary nodes. By the end, it demonstrates a full flow: creating data → transforming it → making decisions → calling APIs → using AI → responding with outputs. Set up steps Time required: 5–10 minutes. What you need: An n8n instance (cloud or self-hosted). Optional: API credentials (e.g., OpenAI) if you want to test AI features. Setup flow: Import this workflow. Add your API keys where needed (OpenAI, etc.). Trigger the workflow manually or test with webhooks. >👉 Detailed node explanations and examples are already included as sticky notes inside the workflow itself, so you can learn step by step as you explore.
By MeeliooCategorize emails & get Telegram alerts with Azure OpenAI & Google Sheets
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Understanding This Workflow In simple terms, this workflow triggers when you receive an e-mail in your inbox; classifies this e-mail based on the subject and notifies you using Telegram. It's fully customizable so you can change, add categoies and continue each data flow separately. E-Mails can hold pretty important information. But one can forget to check-up or rather not prefer to do so. This workflow keeps you updated of what's most important to you. Not only that, you can always talk to the bot to checkup on E-Mails you've missed. Set Up Overview IMAP E-Mail Trigger: You can switch to a Gmail node aswell. Google Sheets: Google Sheets is easy to use so I recommend you to keep it. AI Model: Use any model of your preferance. As long as it is smart and uses less tokens. Telegram: Refer to documentation to understand how to create a bot. > There is no correct line of setting up these credentials, as the workflow needs all to work; as long as you don't change the logic of the workflow. Note Please refer to the sticky notes in the workflow for a clear guide on setup, workflow description etc. If you need any help or need a hand, you can always message me. >https://community.n8n.io/u/mookie_lian
By MeeliooAutomate Telegram support handover from AI to humans with GPT4 and email alerts
How it Works This is a Telegram AI-to-Human Handover System that seamlessly transitions customer support conversations between an AI agent and human operators: AI-First Response: When users message the Telegram bot, an AI agent handles the conversation initially, using memory to maintain context across messages. Smart Handover Detection: The AI recognizes when users request human assistance and triggers a two-step confirmation process (user approval, then operator availability check). Topic-Based Routing: Once confirmed, the system creates a dedicated Telegram Forum topic named after the user's ID, where operators can respond. Messages are automatically forwarded between the user's private chat and the operator's topic. Session Management: A data table tracks conversation states ('ai', 'human', 'open', 'closed'), ensuring messages route correctly and maintaining conversation history. Clean Closure: Operators type "exit" in the topic to close conversations, updating the database and closing the forum topic. Set-up Steps Estimated Time: 30-45 minutes (first-time setup) You'll need to: Create and configure a Telegram bot via BotFather Set up a Telegram group with Topics enabled and add your bot as admin Configure SMTP credentials (Gmail app password recommended) Create an n8n Data Table with specific columns (type, status, topic, user) Add your bot token to multiple HTTP Request nodes Set up AI model credentials (OpenRouter or Azure OpenAI) Fill in the Configuration node with your IDs and email addresses Test the flow using the included Personal Trigger to capture your group/user IDs Note: The template includes detailed video guides (1-minute overview and 10-minute setup walkthrough) plus extensive documentation in sticky notes covering every node and credential setup.
By Meelioo