Gmail AI Auto-Responder: Create Draft Replies to incoming emails
This workflow automatically generates draft replies in Gmail. It's designed for anyone who manages a high volume of emails or often face writer's block when crafting responses. Since it doesn't send the generated message directly, you're still in charge of editing and approving emails before they go out. How It Works: Email Trigger: activates when new emails reach the Gmail inbox Assessment: uses OpenAI gpt-4o and a JSON parser to determine if a response is necessary. Reply Generation: crafts a reply with OpenAI GPT-4 Turbo Draft Integration: after converting the text to html, it places the draft into the Gmail thread as a reply to the first message Set Up Overview (~10 minutes): OAuth Configuration (follow n8n instructions here): Setup Google OAuth in Google Cloud console. Make sure to add Gmail API with the modify scope. Add Google OAuth credentials in n8n. Make sure to add the n8n redirect URI to the Google Cloud Console consent screen settings. OpenAI Configuration: add OpenAI API Key in the credentials Tweaking the prompt: edit the system prompt in the "Generate email reply" node to suit your needs Detailed Walkthrough Check out this blog post where I go into more details on how I built this workflow. Reach out to me here if you need help building automations for your business.
By Nicolas ChourroutTransform product photos into social media videos with Gemini AI, Kling & LATE
👥 Who is this for? Creators, marketers, and brands that want to turn a single product photo into premium motion clips, then optionally publish to Instagram/TikTok/YouTube via LATE. No editing skills required. --- ❓ What problem does it solve? Producing short vertical ads from a static packshot takes time (retouching, motion design, soundtrack, publishing). This workflow automates the entire process: image enhancement → cinematic motion → optional upscale → soundtrack → share. --- 🛠️ What this workflow does Collects a product photo via Telegram. Generates two refined edit prompts + two motion prompts using multi-agent Gemini orchestration. Creates two edited images with Fal.ai Gemini-Flash (image edit). Renders two 5s vertical videos with Kling (via fal.run queue). Auto-stitches them (FFmpeg API) and optionally upscales with Topaz. Generates a clean ambient soundtrack with MMAudio. Sends previews + final links back on Telegram. Optionally publishes to Instagram, TikTok, YouTube Shorts, and more via LATE. --- ⚡ Setup Telegram: Bot token (Telegram node). Fal.ai: HTTP Header Auth (Authorization: Bearer <FALAPIKEY>) for Gemini-Flash edit, Kling queue, FFmpeg compose, Topaz upscale, and MMAudio. Google Gemini (PaLM credential) for AI agents. ImgBB: API key for uploading original/edited images. LATE: create an account at getlate.dev and use your API key for publishing (optional). --- ▶️ How to use Start the workflow and DM your bot a clear product photo (jpg/jpeg/webp). Approve the two still concepts when prompted in Telegram. The orchestrator generates cinematic motion prompts and queues Kling renders. Receive two motion previews, then a stitched final (upscaled + soundtrack). Choose to auto-publish to Instagram/TikTok/YouTube via LATE (optional). --- 🎨 How to customize Art Direction → tweak the “Art Director” system message (lighting, backgrounds, grading). Motion Flavor → adjust the “Motion Designer” vocabulary for different camera moves/dynamics. Durations/Aspect → default is 9:16, 5s; you can change Kling duration. Soundtrack → edit the MMAudio prompt to reflect your brand’s sonic identity. Publishing → enable/disable LATE targets; customize captions/hashtags. --- ✅ Prerequisites A Telegram bot created via @BotFather. A Fal.ai account + API key. An ImgBB account + API key. (Optional) a LATE account with connected social profiles — sign up at getlate.dev. --- 💡 Detailed technical notes, architecture, and step-by-step flow explanation are included as sticky notes inside this workflow. 🆘 Support If you need help setting up or customizing this workflow: 📧 Email: bilsimaging@gmail.com 🌐 Website: bilsimaging.com I can provide guidance, troubleshooting, or custom extra workflow adaptations.
By Bilel ArouaGemini-powered Facebook comment & DM assistant with Notion
What Problem Does It Solve? Customers often ask product questions or prices in comments. Businesses waste time replying manually, leading to delays. Some comments only need a short thank-you reply, while others need a detailed private response. This workflow solves these by: Replying with a friendly public comment. Sending a private message with details when needed. Handling compliments, complaints, and unclear comments in a consistent way. How to Configure It Facebook Setup Connect your Facebook Page credentials in n8n. Add the webhook URL from this workflow to your Facebook App/Webhook settings. AI Setup Add your Google Gemini API key (or swap for OpenAI/Claude). The included prompt is generic — you can edit it to match your brand tone. Optional Logging If you want to track processed messages, connect a Notion database or another CRM. How It Works Webhook catches new Facebook comments. AI Agent analyzes the comment and categorizes it (question, compliment, complaint, unclear, spam). Replying: For questions/requests → public reply + private message with full details. For compliments → short thank-you reply. For complaints → apology reply + private message for clarification. For unclear comments → ask politely if they need help. For spam/offensive → ignored (no reply). Replies and messages are sent instantly via the Facebook Graph API. Customization Ideas Change the AI prompt to match your brand voice. Add forwarding to Slack/Email if a human should review certain replies. Log conversations in Notion, Google Sheets, or a CRM for reporting. Expand to Instagram or WhatsApp with small adjustments. If you need any help Get In Touch
By Abdullah AlshiekhAutomate a 'Chat with your PDF' Bot on Telegram with Google Gemini & Pinecone
This n8n template from Intuz provides a complete solution to automate a powerful, AI-driven 'Chat with your PDF' bot on Telegram. It uses Retrieval-Augmented Generation (RAG) to allow users to upload documents, which are then indexed into a vector database, enabling the bot to answer questions based only on the provided content. Who's this workflow for? Researchers & Students Legal & Compliance Teams Business Analysts & Financial Advisors Anyone needing to quickly find information within large documents How it works This workflow has two primary functions: indexing a new document and answering questions about it. Uploading & Indexing a Document: A user sends a PDF file to the Telegram bot. n8n downloads the document, extracts the text, and splits it into small, manageable chunks. Using Google Gemini, each text chunk is converted into a numerical representation (an "embedding"). These embeddings are stored in a Pinecone vector database, making the document's content searchable. The bot sends a confirmation message to the user that the document has been successfully saved. Asking a Question (RAG): A user sends a regular text message (a question) to the bot. n8n converts the user's question into an embedding using Google Gemini. It then searches the Pinecone database to find the most relevant text chunks from the uploaded PDF that match the question. These relevant chunks (the "context") are sent to the Gemini chat model along with the original question. Gemini generates a new, accurate answer based only on the provided context and sends it back to the user in Telegram. Key Requirements to Use This Template n8n Instance & Required Nodes: An active n8n account (Cloud or self-hosted). This workflow uses the official n8n LangChain integration (@n8n/n8n-nodes-langchain). If you are using a self-hosted version of n8n, please ensure this package is installed. Telegram Account: A Telegram bot created via the BotFather, along with its API token. Google Gemini AI Account: A Google Cloud account with the Vertex AI API enabled and an associated API Key. Pinecone Account: A Pinecone account with an API key. You must have a vector index created in Pinecone. For use with Google Gemini's embedding-001 model, the index must be configured with 768 dimensions. Setup Instructions Telegram Configuration: In the "Telegram Message Trigger" node, create a new credential and add your Telegram bot's API token. Do the same for the "Telegram Response" and "Telegram Response about Database" nodes. Pinecone Configuration: In both "Pinecone Vector Store" nodes, create a new credential and add your Pinecone API key. In the "Index" field of both nodes, enter the name of your pre-configured Pinecone index (e.g., telegram). Google Gemini Configuration: In all three Google Gemini nodes (Embeddings Google Gemini, Embeddings Google Gemini1, and Google Gemini Chat Model), create a new credential and add your Google Gemini (Palm) API key. Activate and Use: Save the workflow and toggle the "Active" switch to ON. To use: First, send a PDF document to your bot. Wait for the confirmation message. Then, you can start asking questions about the content of that PDF. Connect with us Website: https://www.intuz.com/services Email: getstarted@intuz.com LinkedIn: https://www.linkedin.com/company/intuz Get Started: https://n8n.partnerlinks.io/intuz For Custom Workflow Automation Click here- Get Started
By Intuz