Workflow Templates

RAG over a PDF with Weaviate This workflow allows you to upload a PDF file and ask questions about it using the Question and Answer Chain and the Weaviate Vector Store nodes. Who it's for This workflow is the simplest possible implementation of RAG with Weaviate in n8n. It's intended to act as an extendable template for RAG over your own documents. Prerequisites An existing Weaviate cluster. You can view instructions for setting up a local cluster with Docker here or a Weaviate Cloud cluster here. API keys to generate embeddings and power chat models. We use OpenAI, but feel free to switch out the models as you like. Self-hosted n8n instance. See this video for how to get set up in just three minutes. How it works Part 1: Manually upload data In this example, we manually upload a 100+ page article from arXiv called "A Survey of Large Language Models". But you can replace this with your own more advanced data pipeline, if you wish. Part 2: Embed and load data into Weaviate collection Here, we generate embeddings for the full-text of the article and store them in Weaviate. Part 3: Perform RAG over PDF file with Weaviate In this part of the workflow, you can enter your query by running the Chat Node and get a RAG response grounded in context via the Question and Answer Chain node. How to run the workflow Go through the prerequisites, creating a Weaviate cluster (can be local or cloud), downloading self-hosted n8n, and adding your API keys and other credentials. Select the embedding and chat models you'd like to use. Upload a PDF file you want to ask questions about. Execute the rest of the workflow.

This workflow converts any n8n workflow outputs into Markdown notes that are accessible in your Obsidian Vault through Google Drive synchronization. Setup Requirements Create a designated folder in Google Drive (Desktop). Create a symbolic link between this folder and a new target folder in your Obsidian Vault. Configure Google Drive n8n node settings. Send the output of any workflow to the trigger, and the notes will appear in your Vault folder. Optional Features You can use AI agents to: Write notes in your preferred format (e.g., Zettelkasten). Compose YAML front matter. Suggest tags. Use Cases Convert RSS feed items to notes. Create notes from YouTube video transcripts. Transform tasks in Slack messages into Obsidian tasks. (Requires setting up a corresponding workflow, e.g., RSS trigger, YouTube transcriber, or Slack bot.)

This is a simple webpage scraper that specifically grabs today's newest 4K Bluray Preorders as listed on the Blu-ray.com website. This is a scheduled workflow that can run every day and will post a formatted summary message of links to a Discord channel of your choice. Minimal setup required: Just create a webhook for the channel you want posted to in Discord and provide that in the final step. The timezone format step is set to East Coast (NYC) by default, feel free to change. No API keys or any special configuration needed (beyond your Discord webhook) Feel free to customize the formatting of the message that gets posted 👍 How it works: First format todays date to match the formatting used on the website Grab the HTML for the preorders page at www.blu-ray.com Filter only the hyperlinks for each Bluray on the page Then further filter only those with an html header matching today's date Format how you want the message to be sent to your Discord channel (in this case a simple list of Hyperlinks for each Title) Send to Discord! Disclaimer: This should be only for personal use.** The links go back to the blu-ray.com website, which is a good thing! Don't abuse this by slamming their site with some crazy level of automation frequency. Support the blu-ray.com website by using their affiliate links whenever you do want to preorder a title ;) This is one of my first shared templates, so it may not be super optimal or perfect but it works for my needs and hopefully you'll find some use out of it! Discord currently has a 2000 character limit on webhook messages. Some of the messages may get truncated as a result.

Who is this template for? This template is for learners, researchers, students and professionals who want to quickly capture the essence of a YouTube video. Steps in the workflow: Gets the transcript from any YouTube video through Supadata. Process the result from Supadata to one text Process the text with AI (any LLM of your choice) Final result: Produces a summary accompanied with the most important lessons and interesting facts mentioned in the video. The workflow automatically creates a new Google Doc wiht this output, in a folder of your choice on your Google Drive. (If you want to convert the markdown text to real markup after the Google Doc is created: just select all text (Ctrl-A or CMD-A), Cut the text (Ctrl-X or CMD-X and then go to Edit > Paste from Markdown.) Setup Edit your Supadata credentials in the second node (you can start for free) Choose your favourite LLM for AI processing Edit your Google Drive credentials. How to adjust it to your needs If you want the outcome to be different, edit the Prompt in "Proces transcript to summary template". The file name is a combination of ‘transcript ‘ and the date and time. You can change this to whatever you need in the Google Drive node. Supadata offers more details and options (or even translation) when working with transcripts. Check the options here: https://supadata.ai/documentation/youtube/get-transcript

How it works Behavioral analytics**: Real-time analysis of product usage and engagement signals Churn prediction**: Predictive model identifying at-risk customers 15 days before Smart upselling**: Personalized recommendations based on usage and profile Retention campaigns**: Automated retention campaigns with dynamic offers Set up steps Product analytics**: Connect Mixpanel, Amplitude or proprietary analytics Billing system**: Integrate Stripe, Chargebee, Recurly for billing data Customer data**: Synchronize your CRM with complete customer history Email/SMS platforms**: Configure SendGrid, Twilio for communications Pricing rules**: Define your pricing matrix and promotional offers ML pipeline**: Configure predictive model training Key Features 🔮 Churn prediction**: At-risk customer identification with 85% accuracy 💰 Smart upselling**: Personalized recommendations increasing ARPU by 35% ⚡ Proactive interventions**: Automated actions before customer churns 📊 Revenue optimization**: Price optimization based on willingness to pay 🎯 Dynamic segmentation**: Real-time customer groups updates 🔄 A/B testing**: Automated testing of retention strategies 📈 LTV maximization**: Customer lifetime value optimization 🛡️ Dunning management**: Automated payment failure handling

Description AI-Powered Multi-language Customer Support In this guide, we'll walk you through setting up a comprehensive AI-driven workflow that handles customer messages in any language through WhatsApp and email channels, providing intelligent translation, summarization, and automated responses. Ready to revolutionize your customer support? Let's get started! What's the Goal? Automatically handle customer messages** from WhatsApp and email in any language Translate and validate** incoming messages with smart language detection Generate intelligent summaries** with priority classification for support teams Provide automated responses** back to customers via their preferred channel Log all interactions** to database for tracking and analytics Send notifications** to admin team for high-priority cases Deliver 24/7 multilingual customer support** without manual effort Integrate seamlessly** with WhatsApp Business API and email systems By the end, you'll have a fully automated customer support system that handles multilingual communications, prioritizes urgent cases, and maintains comprehensive interaction logs. Why Does It Matter? Manual handling of multilingual customer support can be overwhelming and inefficient. Here's why this workflow is a game-changer: Break Global Language Barriers**: Handle customer inquiries in any language effortlessly Never Miss Important Messages**: Priority detection ensures urgent cases get immediate attention Save 80% of Manual Work**: Automation handles routine inquiries and escalates complex ones 24/7 Availability**: Respond to customers anytime, enhancing satisfaction and retention Professional Customer Experience**: Consistent, well-formatted responses in the customer's language Complete Audit Trail**: Database logging provides insights and accountability Scalable Solution**: Handle growing customer base without proportional staff increase Think of it as your always-on, multilingual customer support team that never sleeps and never misses a beat. How It Works Here's the step-by-step magic behind the automation: Step 1: Multi-Channel Message Capture WhatsApp Trigger**: Captures incoming WhatsApp messages via Business API webhook Email Trigger (IMAP)**: Monitors designated customer support email for new messages Both channels feed into the same processing pipeline for consistent handling Step 2: Data Normalization & Validation Data Normalizer & Validator**: Standardizes message format regardless of source channel Extracts key information: sender details, message content, timestamp, channel source Validates data integrity and handles malformed inputs gracefully Step 3: Smart Language Translation Smart Language Translator**: Automatically detects source language and translates to English Preserves original message context and cultural nuances Stores both original and translated versions for reference Step 4: Enhanced Summary & Priority Processing Enhanced Summary & Priority Processor**: Uses AI to analyze translated content Generates concise summaries highlighting key customer concerns Priority Classification**: Automatically tags messages as: 🔴 High Priority: Urgent issues, complaints, billing problems 🟡 Medium Priority: Product inquiries, general support 🟢 Low Priority: Thank you messages, general feedback Creates structured output with priority flags for support team triage Step 5: Message Source Intelligence Check Message Source**: Determines optimal response channel and method Routes WhatsApp messages back to WhatsApp, emails back to email Maintains conversation context and threading Step 6: Automated Customer Response Customer WhatsApp Auto-Response**: Sends acknowledgment via WhatsApp Customer Email Auto-Response**: Sends professional email replies Responses include: Confirmation of message receipt Estimated response time based on priority Reference number for tracking Next steps or immediate solutions for common issues Step 7: Database Logging & Analytics Log to Database**: Stores complete interaction history including: Original message and translation Priority classification and reasoning Response sent and timestamp Customer contact information Channel and source metadata Enables analytics, reporting, and quality assurance Step 8: Admin Notifications & Alerts Admin Email Notification**: Immediate email alerts for high-priority cases Admin WhatsApp Alert**: SMS/WhatsApp notifications for urgent escalations Workflow Completion & Metrics**: Performance tracking and completion confirmations Workflow Architecture ┌─────────────────┐ ┌──────────────────┐ │ WhatsApp │ │ Email Trigger │ │ Trigger │ │ (IMAP) │ └─────────┬───────┘ └─────────┬────────┘ │ │ └──────────┬───────────┘ │ ┌──────────▼──────────┐ │ Data Normalizer & │ │ Validator │ └──────────┬──────────┘ │ ┌──────────▼──────────┐ │ Smart Language │ │ Translator │ └──────────┬──────────┘ │ ┌──────────▼──────────┐ │ Enhanced Summary & │ │ Priority Processor │ └──────────┬──────────┘ │ ┌──────────▼──────────┐ │ Check Message │ │ Source │ └─────────┬┬──────────┘ ┌┘└┐ ┌──────────▼┐ ┌▼──────────┐ │ Customer │ │ Customer │ │ WhatsApp │ │ Email │ │ Response │ │ Response │ └──────────┬┘ └┬──────────┘ └┬─┬┘ ┌─────────▼─▼─────────┐ │ Log to Database │ └─────────┬───────────┘ │ ┌─────────▼───────────┐ │ Admin Email │ │ Notification │ └─────────┬───────────┘ │ ┌─────────▼───────────┐ │ Admin WhatsApp │ │ Alert │ └─────────┬───────────┘ │ ┌─────────▼───────────┐ │ Workflow Completion │ │ & Metrics │ └─────────────────────┘ How to Use the Workflow? Importing a workflow in n8n is straightforward and allows you to use pre-built or shared workflows to save time. Below is a step-by-step guide to importing the Multi-language Customer Support workflow in n8n. Steps to Import a Workflow in n8n 1. Obtain the Workflow JSON Source the Workflow: Workflows are typically shared as JSON files or code snippets. You might receive them from: The n8n community (e.g., n8n.io workflows page) A colleague or tutorial (e.g., a .json file or copied JSON code) Exported from another n8n instance Format**: Ensure you have the workflow in JSON format, either as a file (e.g., customer-support-workflow.json) or as text copied to your clipboard 2. Access the n8n Workflow Editor Log in to n8n: Open your n8n instance (via n8n Cloud or your self-hosted instance) Navigate to the Workflows tab in the n8n dashboard Open a New Workflow: Click Add Workflow to create a blank workflow, or open an existing workflow if you want to merge the imported workflow 3. Import the Workflow Option 1: Import via JSON Code (Clipboard): In the n8n editor, click the three dots (⋯) in the top-right corner to open the menu Select Import from Clipboard Paste the JSON code of the workflow into the provided text box Click Import to load the workflow into the editor Option 2: Import via JSON File: In the n8n editor, click the three dots (⋯) in the top-right corner Select Import from File Choose the .json file from your computer Click Open to import the workflow Configuration Requirements Essential Setup Notes: WhatsApp Integration: Configure WhatsApp Business API credentials in the WhatsApp Trigger node Set up webhook URL in your WhatsApp Business account Test connection with a sample message Email Configuration: Set up IMAP credentials for your customer support email in the Email Trigger node Configure SMTP settings for outbound email responses Ensure proper email authentication (SPF, DKIM records) Translation Services: Add Google Translate API credentials in the Smart Language Translator node Alternative: Configure Azure Translator or AWS Translate based on preference Set up language detection and translation parameters Database Connection: Configure database credentials in the "Log to Database" node Create required tables for storing customer interactions: CREATE TABLE customer_interactions ( id SERIAL PRIMARY KEY, customer_contact VARCHAR(255), channel VARCHAR(50), original_message TEXT, translated_message TEXT, summary TEXT, priority VARCHAR(20), response_sent TEXT, timestamp TIMESTAMP DEFAULT CURRENT_TIMESTAMP ); Admin Notifications: Set up admin email addresses in notification nodes Configure WhatsApp/SMS credentials for urgent alerts Customize notification templates and thresholds Priority Classification Rules: Customize JavaScript code in "Enhanced Summary & Priority Processor" node Define keywords and patterns for priority detection: // High Priority Keywords const urgentKeywords = ['urgent', 'emergency', 'billing issue', 'not working', 'broken', 'refund', 'complaint']; // Medium Priority Keywords const mediumKeywords = ['question', 'how to', 'support', 'help', 'information']; // Classification logic if (urgentKeywords.some(keyword => message.toLowerCase().includes(keyword))) { priority = 'HIGH'; } else if (mediumKeywords.some(keyword => message.toLowerCase().includes(keyword))) { priority = 'MEDIUM'; } else { priority = 'LOW'; } Response Templates: Customize auto-response templates in both WhatsApp and Email response nodes Include your company branding and contact information Set up response templates for different priority levels and common scenarios Testing and Deployment: Test Each Channel: Send test messages via WhatsApp and email to verify end-to-end flow Verify Translations: Test with messages in different languages Check Database Logging: Confirm all interactions are properly stored Test Admin Notifications: Verify alerts are sent for high-priority cases Monitor Performance: Set up workflow execution monitoring and error handling Your Multi-language Customer Support workflow is now ready to handle customer communications 24/7 across multiple channels with intelligent automation and human oversight where needed!

This n8n template watches a Gmail inbox for support messages and creates an equivalent issue item in Linear. How it works A scheduled trigger fetches recent Gmail messages from the inbox which collects support requests. These support requests are filtered to ensure they are only processed once and their HTML body is converted to markdown for easier parsing. Each support request is then triaged via an AI Agent which adds appropriate labels, assesses priority and summarises a title and description of the original request. Finally, the AI generated values are used to create an issue in Linear to be actioned. How to use Ensure the messages fetched are solely support requests otherwise you'll need to classify messages before processing them. Specify the labels and priorities to use in the system prompt of the AI agent. Requirements Gmail for incoming support messages OpenAI for LLM Linear for issue management Customising this workflow Consider automating more steps after the issue is created such as attempting issue resolution or capacity planning.

Video walkthrough https://www.youtube.com/watch?v=OwIFK-r-NtQ Summary of agent This agent can write and rewrite its own rules, allowing you to mold its behavior. It receives rules from a database as system instructions and has tools to create, edit, or delete them. This is a great baseline for new agent builds. You can tell it things like "Next time, use present tense when talking about this subject" and it will use a tool to save this as a rule, then receive that instruction in all future iterations. How to start using it Option 1: With a Postgres database (e.g., Supabase) Supabase Schema: Create a table (e.g., agent_rules) with the following columns: id: bigint (Primary Key, auto-incrementing) created_at: timestamp with time zone (Default: now()) rule_text: text agent: text Workflow Updates: Update the Postgres credentials in the "Get rules from database," "Insert rule into database," and "Execute query on rule database" nodes. Update the agent value (currently 'TestAgent') in the "Get rules from database" and "Insert rule into database" nodes if you want a different agent name. Update the Anthropic API credentials. Option 2: With Google Sheets Google Sheet Setup: Create a Google Sheet with columns for rule_text and agent. Workflow Updates: Example Google Sheets nodes are included. You will need to: Connect your Google Sheets credentials. Select your Google Sheet (with rule_text and agent columns) in all relevant Google Sheets nodes. Replace the existing Postgres nodes ("Get rules from database", "Insert rule into database", "Execute query on rule database") with the configured Google Sheets nodes. Update the agent value (currently 'TestAgent') in the Google Sheets nodes if you want a different agent name. Update the Anthropic API credentials. Agent Instructions: Update the agent's system message and remove the database schema section as it is no longer relevant

Automate Amazon searches to Telegram with AI-powered scraping This workflow connects Amazon product lookups to Telegram using AI-enhanced scraping and automation. It lets users send a product name to a Telegram bot and instantly receive pricing, discount, and product links — all pulled dynamically from Amazon. Who’s it for Amazon affiliates Telegram shopping groups Product reviewers & resellers Deal-focused communities Anyone wanting fast price checks without browsing How it works Telegram Trigger receives messages from the user. AI Classifier (via OpenRouter & LangChain) detects whether the user is asking for a product. If yes, it sends the query to Apify's Amazon Scraper to fetch real product listings. The scraped data (price, discount, rating, link) is formatted into a Telegram response. If not a product query, an AI fallback response is sent instead. Requirements Telegram Bot Token Apify API Token OpenRouter API Key (or compatible LLM provider)

Make OpenAI Citation for File Retrieval RAG Use case In this example, we will ensure that all texts from the OpenAI assistant search for citations and sources in the vector store files. We can also format the output for Markdown or HTML tags. This is necessary because the assistant sometimes generates strange characters, and we can also use dynamic references such as citations 1, 2, 3, for example. What this workflow does In this workflow, we will use an OpenAI assistant created within their interface, equipped with a vector store containing some files for file retrieval. The assistant will perform the file search within the OpenAI infrastructure and will return the content with citations. We will make an HTTP request to retrieve all the details we need to format the text output. Setup Insert an OpenAI Key How to adjust it to your needs At the end of the workflow, we have a block of code that will format the output, and there we can add Markdown tags to create links. Optionally, we can transform the Markdown formatting into HTML.

How it works It’s very important to come prepared to Sales calls. This often means a lot of manual research about the person you’re calling with. This workflow delivers a summary of the latest social media activity (LinkedIn + X) for businesses you are about to interact with each day. Scans Your Calendar**: Each morning, it reviews your Google Calendar for any scheduled meetings or calls with companies based on each attendee email address. Fetches Latest Posts**: For each identified company, it fetches recent LinkedIn and X posts and summerizes them using AI to deliver a qucik overview for a busy sales rep. Delivers Insights**: You receive personalized emails via Gmail, each dedicated to a company you’re meeting with that day, containing a reminder of the meeting and a summary of company's recent social media activity. Setup steps The workflow requires you to have the following accounts set up in their respective nodes: Google Calendar GMail Clearbit OpenAI Besides those, you will need an account on the RapidAPI platform and subscribe to the following APIs: Fresh LinkedIn Profile Data Twitter Email example

How it works It’s very important to come prepared to Sales calls. This often means a lot of manual research about the person you’re calling with. This workflow delivers the latest social media activity (LinkedIn + X) for businesses you are about to interact with each day. Scans Your Calendar**: Each morning, it reviews your Google Calendar for any scheduled meetings or calls with companies based on each attendee email address. Fetches Latest Posts**: For each identified company, it fetches recent LinkedIn and X posts Delivers Insight**s: You receive personalized emails via Gmail, each dedicated to a company you’re meeting with that day, containing a reminder of the meeting, list of posts categorized by the social media platform, and direct links to posts. Setup steps The workflow requires you to have the following accounts set up in their respective nodes: Google Calendar GMail Clearbit Besides those, you will need an account on the RapidAPI platform and subscribe to the following APIs: Fresh LinkedIn Profile Data Twitter Email example