Workflow Templates

This n8n workflow provides a ready-to-use API endpoint for extracting structured data from images. It processes an image URL using an AI-powered OCR model and returns the extracted details in a structured JSON format. Use Cases Document OCR** – Extract details from ID cards, invoices, receipts, etc. Text Extraction from Images** – Process screenshots, scanned documents, and photos. Automated Form Processing** – Digitize and capture information from paper forms. Business Card Data Extraction** – Extract names, emails, and phone numbers from business cards. How It Works Send a GET request with an image URL and define the required extraction parameters. The image is converted to base64 for processing. The AI model (Gemini API - Flash Lite) extracts relevant text. The response returns structured JSON data containing only the requested fields. Features ✔️ No-Code API Setup – Easily integrate into any application. ✔️ Customizable Extraction – Modify the request parameters to fit your needs. ✔️ AI-Powered OCR – Uses advanced models for accurate text recognition. ✔️ Automated Processing – Ideal for document processing and digitization. Integration Works with any frontend/backend system that supports API calls. Can be used for workflow automation in CRM, ERP, and document management solutions. Supports further customization based on specific OCR requirements.

Automate Telegram Chat Responses Using Google Gemini By WeblineIndia* ⚡ TL;DR (Quick Steps) Create a Telegram bot using @BotFather and copy the API Token. Obtain Google Gemini API Key via Google Cloud. Set up the n8n workflow: Trigger: Telegram message received. AI Model: Google Gemini generates response. Output: AI reply sent back to user via Telegram. Customize the system prompt, model, or message handling to suit your use case. 🧠 Description This n8n workflow enables seamless automation of real-time chat replies in Telegram by integrating with Google Gemini's Chat Model. Every time a user sends a message to your Telegram bot, the workflow routes it through the Gemini AI, which analyzes and crafts a professional response. This reply is then automatically delivered back to the user. The setup acts as a lightweight but powerful chatbot system — ideal for businesses, customer service, or even personal productivity bots. You can easily modify its tone, intelligence level, or logging mechanisms to cater to specific domains such as sales, tech support, or general Q&A. 🎯 Purpose of the Workflow The primary goal of this workflow is to automate intelligent, context-aware chat responses in Telegram using a robust AI model. It eliminates manual reply handling, enhances user engagement, and ensures 24/7 interaction capabilities — all through a no-code or low-code setup using n8n. 🛠️ Steps to Configure and Use ✅ Pre-Conditions / Requirements Telegram Bot Token**: Get it from @BotFather. Google Gemini API Key**: Available via Google Cloud PaLM/Gemini API access. n8n Instance**: Hosted or local instance with required nodes installed (Telegram, Basic LLM Chain, and Google Gemini support). 🔧 Setup Instructions Step 1: Telegram Trigger – Listen for Incoming Messages Add Telegram Trigger node. Select Trigger On: Message. Authenticate using your Telegram Bot Token. This will capture incoming messages from any user interacting with your bot. Step 2: Google Gemini AI – Generate a Smart Reply Add the Basic LLM Chain node. Connect the input message ({{$json.message.text}}) from the Telegram Trigger. System Prompt: > "You are an AI assistant. Reply to the following user message professionally:" Choose Google Gemini Chat Model (models/gemini-1.5-pro). Connect this node to receive the text input and pass it to Gemini for processing. Step 3: Telegram Reply – Send the AI Response Add a Telegram node (Operation: Send Message). Set Chat ID dynamically from the Telegram Trigger node. Input the generated message from the Gemini output. Enable Parse Mode as HTML for rich formatting. Final Step: Link All Nodes Receive Telegram Message → Generate AI Response → Send Telegram Reply. > Tip: Test the workflow by sending a message to your Telegram bot and ensure you receive an AI-generated reply. 🧩 Customization Guidance ✏️ Modify the AI tone by updating the system prompt. 🤖 Use other AI models (e.g., OpenAI GPT-4o). 🔍 Add filters to respond differently based on specific keywords. 📊 Extend the workflow to store chats in Google Sheets, Airtable, or databases for audit or analytics. 🌐 Multi-language support: Add translation layers before and after AI processing. 🛠️ Troubleshooting Guide No message received?** Check if your Telegram bot is active and webhook is working. AI not responding?** Validate your Google Gemini API key and usage quota. Wrong replies?** Refine the system prompt or validate message routing. Formatting issues?** Ensure Parse Mode is correctly set to HTML. 💡 Use Case Examples Customer Service Chatbot** for product queries. Educational Bots** for answering user questions on a topic. Mental Health Companion** that gives supportive replies. Event-based Announcers** or automatic responders during off-hours. > And many more! This workflow can be easily extended to support advanced use cases with just a few additional nodes. 👨‍💻 About the Creator This workflow is developed by WeblineIndia, a trusted provider of AI development services and process automation solutions. If you're looking to build or customize intelligent workflows like this, we invite you to get in touch with our team. We also offer specialized Python development and AI developer hiring services to supercharge your automation needs.

This n8n workflow shows how using multimodal LLMs with AI vision can tackle tricky image validation tasks which are near impossible to achieve with code and often impractical to be done by humans at scale. You may need image validation when users submitted photos or images are required to meet certain criteria before being accepted. A wine review website may require users only submit photos of wine with labels, a bank may require account holders to submit scanned documents for verification etc. In this demonstration, our scenario will be to analyse a set of portraits to verify if they meet the criteria for valid passport photos according to the UK government website (https://www.gov.uk/photos-for-passports). How it works Our set of portaits are jpg files downloaded from our Google Drive using the Google Drive node. Each image is resized using the Edit Image node to ensure a balance between resolution and processing speed. Using the Basic LLM node, we'll define a "user message" option with the type of binary (data). This will allow us to pass our portrait to the LLM as an input. With our prompt containing the criteria pulled off the passport photo requirements webpage, the LLM is able to validate the photo does or doesn't meet its criteria. A structured output parser is used to structure the LLM's response to a JSON object which has the "is_valid" boolean property. This can be useful to further extend the workflow. Requirements Google Gemini API key Google Drive account Customising this workflow Not using Gemini? n8n's LLM node works with any compatible multimodal LLM so feel free to swap Gemini out for OpenAI's GPT4o or Antrophic's Claude Sonnet. Don't need to validate portraits? Try other use cases such as document classification, security footage analysis, people tagging in photos and more.

Use case This automation is for teams working in Notion. When you have a lot of back and forth in the comment section, it’s easy to lose track of what is going on in the conversation. This automation relies on AI to generate a summary of the comment section. How it works Every hour (the trigger can be adapted to your need and usecase), the automation checks if new comments have been added to the pages of your Notion database. If there are new comments, the comments are sent to an AI model to write a summary. The summary is then added to a predefined page property. The automation also updates a “Last execution” property. This prevents to re-generate the AI summary when no new comments have been received. Setup Define your Notion variables: Notion database, property that will hold the AI summary, property that will hold the last execution date of the automation. Set up your Notion credentials. Set up your AI model credentials (API key). How to adjust it to your needs Use the LLM model of your choice. In this template, I used Gemini but you can easily replace it by ChatGPT, Claude, etc. Adapt the prompt to your use case to get better summaries: specify the maximum number of characters, give an example, etc. Adapt the trigger to your needs. You could use Notion webhooks as trigger in order to run the automation only when a new comment is added (this setup is advised if you’re on n8n cloud version).

This workflow automatically syncs Shopify orders with your Zendesk tickets. Using this workflow, Shopify orders will be added or have their information updated straight to your Zendesk tickets. Prerequisites Shopify account and Shopify credentials Zendesk account and Zendesk credentials How it works Shopify Trigger starts the workflow whenever an order is updated. Zendesk node finds if the order already exists and has a ticket assigned. Set node keeps and passes only ticket ID. Merge by Key node combines the Shopify order data with the Zendesk ticket data. If node splits the workflow conditionally, checks if the ticket already exists or not. If order is new, Zendesk node creates a new ticket for the order.

Company Website Chatbot Agent Overview This workflow implements a modular Website AI Chatbot Assistant capable of handling multiple types of customer interactions autonomously. Instead of relying on a single large agent to handle all logic and tools, this system routes user queries to specialized sub-agents—each dedicated to a specific function. By using a manager-style orchestration layer, this approach prevents overloading a single AI model with excessive context, leading to cleaner routing, faster execution, and easier scaling as your automation needs grow. How It Works 1. Chat Trigger The flow is initiated when a chat message is received via the website widget. 2. Manager Agent (Ultimate Website AI Assistant) The central LLM-based agent is responsible for parsing the message and deciding which specialized sub-agent to route it to. It uses an OpenAI GPT model for natural language understanding and a lightweight memory system to preserve recent context. 3. Sub-Agent Routing calendarAgent: Handles availability checks and books meetings on connected calendars. RAGAgent: Searches company documentation or FAQs to provide accurate responses from your internal knowledge base. ticketAgent: Forwards requests to human support by generating and sending support tickets to a designated email. Setup Instructions Embed the Chatbot Use a custom HTML widget or script to embed the chatbot interface on your website. Connect the frontend to the webhook that triggers the When chat message received node. Configure Your OpenAI Key Insert your API key in the OpenAI Chat Model node. Adjust the model parameters for temperature, max tokens, etc., based on how formal or creative you want the bot to be. Customize Sub-Agents calendarAgent: Connect to your Google or Outlook calendar. RAGAgent: Link to a vector store or document database via API or native integration. ticketAgent: Set the destination email and format for ticket generation (e.g. via SendGrid or SMTP). Deploy in Production Host on n8n Cloud or your self-hosted instance. Monitor usage through the Executions tab and refine prompts based on user behavior. Benefits Modular system with dedicated logic per function Reduces token bloat by offloading complexity to sub-agents Easy to scale by adding more tools (e.g. CRM, analytics) Fast and responsive user experience for customers on your site Cleaner code structure and easier debugging

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. 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. 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 Listens for incoming user questions (can be extended to webhook). Converts questions to vector embeddings and performs similarity search on MongoDB vector store. Uses OpenAI’s GPT-4o-mini model with retrieval-augmented generation to produce direct, context-aware answers. Maintains short-term conversation context using a memory buffer node. 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 Configure the AI system prompt in the “Knowledge Base Agent” node to reflect your company’s tone, answering style, and any business rules. Update the workflow description and instructions to help users understand the chat’s purpose and capabilities. Connect the MongoDB collection used for vector search in the chat workflow and update the vector search index if needed to match your setup. 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" } } } }

Who is this for? This workflow template is perfect for content creators, researchers, students, or anyone who regularly works with audio files and needs to transcribe and summarize them for easy reference and organization. What problem does this workflow solve? Transcribing audio files and summarizing their content can be time-consuming and tedious when done manually. This workflow automates the process, saving users valuable time and effort while ensuring accurate transcriptions and concise summaries. What this workflow does This template automates the following steps: Monitors a specified Google Drive folder for new audio files Sends the audio file to OpenAI's Whisper API for transcription Passes the transcribed text to GPT-4 for summarization Creates a new page in Notion with the summary Setup To set up this workflow: Connect your Google Drive, OpenAI, and Notion accounts to n8n Configure the Google Drive node with the folder you want to monitor for new audio files Set up the OpenAI node with your API key and desired parameters for Whisper and GPT-4 Specify the Notion database where you want the summaries to be stored How to customize this workflow Adjust the Google Drive folder being monitored Modify the OpenAI node parameters to fine-tune the transcription and summarization process Change the Notion database or page properties to match your preferred structure With this AI-powered workflow, you can effortlessly transcribe audio files, generate concise summaries, and store them in a structured manner within Notion. Streamline your audio content processing and organization with this automated template.

How it works Trigger: Listens for an incoming chat message Copy Assistant: Feeds the message (plus memory) into an OpenAI Chat Model and exposes two “tools” Cold Email Writer Tool Sales Letter Tool• Tool execution: Depending on the user’s intent, the appropriate tool generates the copy • Save output: Writes the generated email or sales letter into your target document via the Update a document node Set up steps • Configure your OpenAI Chat Model credentials in n8n (no hard-coded keys!) • Add and authenticate the Simple Memory credential (to keep context across messages) • Create Google Docs (or MS Word) credentials for the Update a document node • Ensure your Chat trigger is pointing at your incoming-message endpoint • Mandatory: Drop sticky-note annotations on each tool node explaining where to enter API keys and how to tweak prompts Once everything’s wired up, send a test chat message like “Write me a cold email for a fintech startup” and watch the workflow spin up a polished draft in your document. How to use Import the workflow JSON into n8n. Configure your Chat trigger (webhook or form) to receive incoming messages. Send a chat prompt like: “Write me a cold email for a B2B SaaS offering.” The “Copy Assistant” custom GPT picks the right tool (Cold Email or Sales Letter). Generated copy is written directly into your linked Google Doc or Word document. Requirements OpenAI API Key (with Chat Completions & Custom GPTs enabled) Custom Assistant created in your ChatGPT dashboard (Assistant ID pasted into the Chat Model node) n8n instance (Cloud or self-hosted) with credentials set up for: Simple Memory (to persist context) Google Docs or Microsoft Word (for document output) Customising this workflow Tweak system and user prompts inside the Copy Assistant node to fit your brand voice. Swap in Slack, Teams or email nodes instead of a document writer to deliver copy where you need it. Add or remove tools (e.g., “Follow-up Email Writer”) by duplicating the existing tool pattern. Use sticky-note annotations on every node to explain where to enter API keys, Assistant IDs, or prompt tweaks.

Workflow Documentation Description: This workflow is designed to optimize prompts by enhancing user inputs for clarity and specificity using AI. The workflow takes a user-provided prompt as input and uses a Natural Language Processing (NLP) model to refine and improve the prompt. The optimized prompt is then sent back to the user, ready for use in further workflows or processes. Setup: This workflow is suitable for users who want to improve their prompts for better communication and understanding in their workflows. The workflow utilizes an AI Agent powered by an OpenAI Chat Model to enhance user prompts. Expected Outcomes: Users can provide vague or imprecise prompts as input to the workflow. The AI Agent will refine and optimize the prompt, adding clarity and specific details. The optimized prompt will be delivered back to the user via Telegram or can be input for the next nodes. Extra Information: A. A Telegram node is used to deliver the optimized prompt back to the user. B. Ensure you have the necessary credentials set up for Telegram and OpenAI accounts. C. Customize the workflow's settings, such as the AI model used for prompt optimization, to suit your requirements. D. Activate the workflow once all configurations are set to start optimizing prompts efficiently.

This workflow automatically adds closed deals from Pipedrive as new customers into Stripe. Prerequisites Pipedrive account and Pipedrive credentials Stripe account and Stripe credentials How it works Pipedrive trigger node starts the workflow when a deal gets updated in Pipedrive. IF node checks that the current won time is not equal to the previuos one in the deal and continues the workflow if it's true. Pipedrive node extracts the organization's details to pass it further. HTTP Request node searches for the same organization's details within Stripe. If a customer doesn't exist within Stripe, Merge node passes a new customer details to Stripe. Stripe node creates a new customer.

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: N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_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.