Workflow Templates

Using the knowledge graphs instead of RAG vector stores This workflow creates an AI chatbot agent that has access to several knowledge bases at the same time (used as "experts"). These knowledge bases are provided using the InfraNodus GraphRAG using the knowledge graphs and providing high-quality responses without the need to set up complex RAG vector store workflows. The advantages of using GraphRAG instead of the standard vector stores for knowledge are: Easy and quick to set up (no complex data import workflows needed) A knowledge graph has a holistic view of your knowledge base Better retrieval of relations between the document chunks = higher quality responses How it works This template uses the n8n AI agent node as an orchestrating agent that decides which tool (knowledge graph) to use based on the user's prompt. Here's a description step by step: The user submits a question using the AI chatbot (n8n interface, in this case, which can be accessed via a URL or embedded to any website) The AI agent node checks a list of tools it has access to. Each tool has a description of the knowledge it has auto-generated by InfraNodus. The AI agent decides which tool should be used to generate a response. It may reformulate user's query to be more suitable for the expert. The query is then sent to the InfraNodus HTTP node endpoint, which will query the graph that corresponds to that expert. Each InfraNodus GraphRAG expert provides a rich response that takes the whole context into account and provides a response from each expert (graph) along with a list of relevant statements retrieved using a combination or RAG and GraphRAG. The n8n AI Agent node integrates the responses received from the experts to produce the final answer. The final answer is sent back to the user's chat (or a webhook endpoint) 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. Create a separate knowledge graph for each expert (using PDF / content import options) in InfraNodus For each graph, go to the workflow, paste the name of the graph into the body name field. Keep other settings intact or learn more about them at the InfraNodus access points page. Once you add one or more graphs as experts to your flow, add the LLM key to the OpenAI node and launch the workflow Requirements An InfraNodus account and API key An OpenAI (or any other LLM) API key Customizing this workflow You can use this same workflow with a Telegram bot, so you can interact with it using Telegram. There are many more customizations available. Check out the complete guide at https://support.noduslabs.com/hc/en-us/articles/20174217658396-Using-InfraNodus-Knowledge-Graphs-as-Experts-for-AI-Chatbot-Agents-in-n8n Also check out the video tutorial with a demo:

Build a Personalized Birthday AI Companion with GPT-4 and PostgreSQL

by Praveena

Idea The idea for app came since I wanted to build a unique gift for my niece because she gets excited for her birthday (which Im going to miss this year). The web app has a simple countdown (in html and JS) but more importantly, there is an AI agent that will answer some specific questions and know her preferences. How it works The questions from app are sent via web hook to N8N which has pulls preferences file (about her likes, dislikes, personality) from postgre and AI Agent that will answer questions/respond. The current status is stored back in postgre (especially about status of cat and universe happenings) before responding back. Features Integrated AI chatbot via N8N webhook Persistent conversation history Minimizable chat interface Fallback support for offline testing Features: -- Wheres Mittens - This is a query to track her lost cat in multiverse. -- Multiverse updates with recent update stored Pre Requisites Postgre SQL database is available. Alternatively, use any other database but change the N8N nodes. LLM Api Key. Step by Step Instructions Export this N8N Workflow. Modify LLM API Key, I used openAI, 4.1 For web app scofflding,you will need Node, HTML and Javascript. I've created a mini version using Node and JS with web app and N8N connection settings here: <https://github.com/productiser/FiBirthdayAgent> PostgreSQL Database Script (1 table for memory and context storage): CREATE TABLE fifi_world_context ( id TEXT PRIMARY KEY, -- e.g., 'agent_fifi' cat_location TEXT, -- e.g., "Bubble Nebula" cat_activity TEXT, -- e.g., "Playing laser tag with moon mice" fifi_preferences JSONB, -- e.g., likes/dislikes/foods/shows world_history TEXT, -- Summary of narrative events last_updated TIMESTAMP DEFAULT CURRENT_TIMESTAMP ); 5.Modify system prompt as per your needs. Built With N8N Self hosted Self hosted web app Hosted on Vercel Total spend = <£1 (AI costs only) Total Time = <1 day Support Watch this video for web app overview and how it looks. <https://youtu.be/e7PlrTdvwoM> Contact me on info@pankstr.com/ superllmuser@gmail.com for any queries Hope you enjoy!!

🤖AI & Machine Learning

intermediate

5 nodes5 views

Track Jura Coffee Machine Data with Webhook API and Google Sheets

by Halfbit 🚀

Jura Coffee Counter: Webhook API & Google Sheets Logger ☕️ Track how many coffees your Jura E8 espresso machine makes — fully automated via webhook and Google Sheets. This workflow exposes a custom API endpoint that can be called by smart devices, such as an ESP8266 or ESP32 reading data from a Jura E8 coffee machine via Bluetooth Low Energy (BLE). The incoming data (including total coffee count) is timestamped and appended to a Google Sheet, making it easy to visualize or analyze your machine usage. ☕ Originally built for a Jura E8, based on AlexxIT/Jura reverse-engineering project. > 📝 This workflow uses Google Sheets as a logging backend. You can easily switch it to Airtable, Notion, or a database of your choice. Live example available at: https://halfbitstudio.com/o-nas/ > 🖥️ In our setup, this workflow is used to provide real-time coffee consumption stats displayed directly on our website. > 🔌 Some Jura machines require an accessory Bluetooth transmitter to enable connectivity. Communication is based on the Bluetooth Low Energy (BLE) protocol. Use Case Tracking usage of a Jura coffee machine Logging IoT sensor data into Google Sheets Creating dashboards for daily consumption Smart office setups with coffee stats! Features ☁️ Two Webhook endpoints: POST /{{WEBHOOK_POST_PATH}} — receives JSON from ESP (coffee machine reader) GET /{{WEBHOOK_GET_PATH}} — returns latest records as JSON 📅 Timestamping via Date & Time node 🔹 Coffee counter extraction from incoming JSON 🧾 Appends structured rows to Google Sheets 📤 Webhook response for external status or dashboards Setup Instructions Jura Coffee Machine Integration (Hardware) Use an ESP device (e.g. ESP8266 or ESP32) to connect to the Jura E8 via Bluetooth Low Energy (BLE). Send POST requests with JSON payload: { "total_coffees": 123 } Reverse-engineered protocol reference: AlexxIT/Jura Google Sheets Configuration Create a new Google Sheet with column headers like: date | time | coffee counter Connect your Google account in n8n and authorize access to this sheet. Replace the documentId and sheetName fields in the Google Sheets nodes: Use full URL to your spreadsheet Use the actual sheet name (e.g. Sheet1) Environment Variables & Placeholders | Placeholder | Description | | ------------------------ | ----------------------------------------------- | | {{WEBHOOK_POST_PATH}} | Endpoint to receive coffee counter data | | {{WEBHOOK_GET_PATH}} | Endpoint to return latest data (for dashboards) | | {{SHEET_ID}} | Google Spreadsheet ID | | {{GOOGLE_CREDENTIALS}} | OAuth2 credentials for Google Sheets | | {{DATA_COLUMNS}} | Column names in the target sheet | Testing the Workflow Send test request: Use Postman or ESP to send a POST request to /{{WEBHOOK_POST_PATH}} Body should include total_coffees value Check Google Sheet: Open your sheet and verify that a new row was appended Test GET endpoint: Access the second webhook URL (e.g. /{{WEBHOOK_GET_PATH}}) in browser or fetch via API Optional: Use Respond to Webhook output in a dashboard or frontend Customization Tips Sheet format**: Add more columns if you want to track additional data (e.g. machine temperature, errors) Output format**: Replace Google Sheets with any other storage (e.g. MySQL, Notion) Auth layer**: Add basic auth or token verification if needed for public exposure Notifications**: Send alerts to Discord/Slack when reaching thresholds (e.g. 200 coffees brewed) Tags: google-sheets, iot, webhook, jura, coffee, api, automation

Automatic Lead Export from Fluentform to Google Sheets with Form Categorization

by Khairul Muhtadin

❓ What Problem Does It Solve? Manual exporting or copying of leads and newsletter signups from web forms to spreadsheets is time-consuming, error-prone, and delays follow-ups or marketing activities. Traditional workflows can lose data due to mistakes or lack of automation. The Fluentform Export workflow automates the capture and organization of form submissions and newsletter signups into Google Sheets 💡 Why Use this workflow? Save Time:** Automate tedious manual data entry for form leads and newsletter signups Avoid Data Loss:** Ensure all submissions are reliably logged with real-time updates Organized Data:** Separate sheets for newsletter and contact form data maintain clarity Easy Integration:** Works seamlessly with Fluentform submissions and Google Sheets Flexible & Scalable:** Quickly adapt to changes in form structure or spreadsheet columns ⚡ Who Is This For? Marketers & Growth Teams:** Automatically gather leads and newsletter contacts to fuel campaigns Small to Medium Businesses:** Reduce overhead from manual data management and errors Customer Support Teams:** Keep track of form submissions in a centralized, accessible place Website Admins:** Simplify data workflow from Fluentform plugins without coding 🔧 What This Workflow Does ⏱ Trigger:** Listens for incoming POST requests from Fluentform via webhook 📎 Step 2:** Evaluates if the submission is a newsletter signup or a form based on a specific token 🔄 Step 3 (Newsletter Path):** Maps email from newsletter submissions and appends/updates Google Sheets "News Letter" tab 🔄 Step 3 (Form Path):** Extracts full name, email, phone, subject, and message fields and appends/updates the Google Sheets "form" tab 💌 Step 4:** Sends a JSON success response back to Fluentform confirming receipt 🔐 Setup Instructions Import the provided .json workflow file into your n8n instance Set up credentials: Google Sheets OAuth2 credential with access to your target spreadsheets Customize workflow elements: Update Fluentform webhook URL in your Fluentform settings to the n8n webhook URL generated Adjust field names or spreadsheet columns if your form structure changes Update spreadsheet IDs and sheet names used in the Google Sheets nodes to match your own Sheets Test workflow thoroughly with actual Fluentform submissions to verify data flows correctly 🧩 Pre-Requirements Running n8n instance (Cloud or self-hosted) Google account with access to Google Sheets and OAuth credentials Fluentform installed on your website with ability to set webhook URL Target Google Sheets prepared with tabs named "News Letter" and "form" with expected columns 🧠 Nodes Used Webhook (POST - Retrieve Leads) If (Form or newsletter?) Set (newsletter and form data preparation) Google Sheets (Append/update for newsletter and form sheets) Respond to Webhook 📞 Support Made by: khaisa Studio Tag: automation, Google Sheets, Fluentform, Leads Category: Marketing Need a custom? Contact Me

1 nodes668 views

Convert Markdown content to Google Docs document with automatic formatting

by Roman Rozenberger

This workflow is perfect for technical writers, content creators, marketers, and developers who write in Markdown but need to collaborate or publish using Google Docs format. Ideal for teams that want to streamline their content creation and review process. What problem does this workflow solve? Manual conversion from Markdown to Google Docs is time-consuming and often loses formatting. This workflow eliminates the tedious copy-paste process, automatically preserves formatting, and creates organized, timestamped documents in your Google Drive. Perfect for content teams who write in Markdown but need Google Docs for collaboration and review. What this workflow does Converts Markdown to HTML** with proper formatting preservation (headers, lists, links, tables) Creates timestamped Google Docs** documents with automatic naming Adds Drive location metadata** for better organization and reference Maintains document structure** including emojis, tables, and text formatting Automates file creation** in specified Google Drive folders Setup Google Drive OAuth2 credentials configured in n8n Target Google Drive folder URL Input your content title and Markdown text in the "Set Input Data" node How to customize this workflow to your needs Modify HTML formatting options** in the Markdown conversion node Change file naming patterns** to match your organization system Adjust Drive folder structure** and metadata inclusion Update MIME type handling** for different output requirements Add additional processing steps** like notifications or integrations Perfect for technical documentation workflows, content publishing pipelines, blog preparation, and automated report generation. Setup Instructions - Markdown to Google Docs Converter Prerequisites n8n instance** (local or cloud) Google account** with Google Drive access Basic understanding** of n8n workflow configuration Step 1: Import the Workflow Open n8n and navigate to Workflows Click "Add workflow" → "Import from JSON" Upload the Export_Markdown_Content_do_Google_Docs_Document.json file Save the workflow with a descriptive name Step 2: Configure Google Drive Credentials Create Google Drive OAuth2 Credentials In n8n, go to Settings → Credentials Click "Add credential" → "Google Drive OAuth2 API" Follow the OAuth setup to authorize n8n access to Google Drive: Visit Google Cloud Console Create or select a project Enable Google Drive API Create OAuth2 credentials Add authorized redirect URI for your n8n instance Name the credential (e.g., "Google Drive - Markdown Converter") Configure Google Drive Nodes Update these nodes with your Google Drive credentials: Create Empty File Update Document with Correct HTML Formatting In each node: Select your Google Drive credential from the dropdown Test the connection to ensure it works properly Step 3: Prepare Your Google Drive Create Target Folder Go to Google Drive (drive.google.com) Create a new folder for your converted documents Copy the folder URL (will look like: https://drive.google.com/drive/folders/FOLDER_ID) Ensure the folder has proper permissions for your Google account Step 4: Configure Input Data Set Your Default Values Open the "Set Input Data" node Update the assignments with your preferences: Google Drive URL: Replace the example URL with your target folder URL Format: https://drive.google.com/drive/folders/YOUR_FOLDER_ID Content Title: Set a default title or leave placeholder text This will be used in the document filename Content in Markdown: Add your Markdown content or keep example for testing Supports standard Markdown syntax (headers, lists, links, tables) Step 5: Test the Workflow Initial Test Run Ensure all credentials are configured Click the "Test workflow" button on the Manual Trigger node Monitor the execution - check for any errors in node outputs Verify the result: Check your Google Drive folder Look for a new document with timestamp in the name Open the document to verify formatting Troubleshooting Common Issues Google Drive Permission Errors: Verify OAuth2 credentials are properly configured Check that the target folder exists and is accessible Ensure Google Drive API is enabled in Google Cloud Console Markdown Conversion Issues: Check that your Markdown syntax is valid Test with simple content first (headers, paragraphs, lists) Verify the "Change Markdown To HTML" node settings File Creation Problems: Confirm the Google Drive folder URL format is correct Check that the folder ID in the URL is valid Ensure your Google account has write permissions to the folder Step 6: Customize for Your Needs Modify HTML Formatting Options In the "Change Markdown To HTML" node: Enable/disable emoji support** (currently enabled) Adjust table formatting** (currently enabled) Modify header ID generation** (currently disabled) Configure space requirements** for headers Update File Naming Pattern In the "Create Empty File" node: Change the naming convention**: Currently uses _PUB {Content Title} {timestamp} Modify timestamp format**: Currently yyyy-MM-dd HH:mm:ss Add prefixes or suffixes** as needed for your organization Step 7: Production Usage Regular Workflow Execution Update the "Set Input Data" node with new content Execute the workflow manually or set up triggers Monitor execution logs for any issues Check Google Drive for generated documents Integration Options Webhook Integration: Add a Webhook trigger to accept external Markdown content Useful for automated content publishing workflows Email Integration: Add email notifications when documents are created Include links to generated Google Docs Advanced Configuration Error Handling Add error handling nodes after critical operations Implement retry logic for API failures Set up notifications for failed executions Performance Optimization Adjust the "Wait for Document Creation" timing if needed Consider file size limits for Google Docs Support and Troubleshooting Common Solutions Timeout errors**: Increase wait time in "Wait for Document Creation" Authentication failures**: Refresh Google OAuth2 credentials Formatting issues**: Test with simpler Markdown first Getting Help Check n8n community forums for Google Drive integration issues Review Google Drive API documentation for rate limits Test with minimal Markdown content to isolate problems Total setup time: ~15-20 minutes Difficulty level: Intermediate Requirements: Google account, n8n instance, basic OAuth2 setup knowledge

2 nodes469 views

AI-powered Student Assistant for Course Information via Twilio SMS

by Jimleuk

This n8n template offers a simple yet capable chatbot assistant who can answer course enquiries over SMS. Given the right access to data, AI Agents are capable of planning and performing relatively complex research tasks to get their answers. In this example, the agent must first understand the database schema, retrieve lists of values before generating it's own query to search over the database. Checkout the example database here - https://airtable.com/appO5xvP1aUBYKyJ7/shr8jSFDaghubDOrw How it works A Twilio trigger gives us the ability to receive SMS input into our workflow via webhook. The message is then directed to our AI agent who is instructed to assist the user and use the course database as reference. The database is an Airtable base. The agent autonomously figures out which tool it needs to use and generates it's own "filter_by_formula" query to search over the available courses. On successful search results, the Agent can then use this information to answer the user's query. The Agent's output is logged in a second sheet of the Airtable base. We can use this later for analysis and lead gen. Finally, the response is sent back to the user through SMS using Twilio. How to use Ensure your Twilio number is set to forward messages to this workflow's webhook URL. Configure and update the course database as required. If you're not interested in courses, you can swap this out for inventory, deliveries or any other data relevant to your business. Ask questions like: "Can you help me find suitable courses to fill my Wednesday mornings?" "Which courses are being instructed by profession Lee?" "I'm interested in creative arts. What courses are available which could be relevant to me?" Requirements Twilio for SMS receiving and sending OpenAI for LLM and Agent Airtable for Course Database Customising this workflow Add additional tools and expand the range of queries the agent is able to answer or assist with. Not using Airtable? This technique also works with SQL databases like PostgreSQL.

Calculate the Centroid of a Set of Vectors

by Mauricio Perera

n8n Workflow: Calculate the Centroid of a Set of Vectors Overview This workflow receives an array of vectors in JSON format, validates that all vectors have the same dimensions, and computes the centroid. It is designed to be reusable across different projects. Workflow Structure Nodes and Their Functions: Receive Vectors (Webhook): Accepts a GET request containing an array of vectors in the vectors parameter. Expected Input: vectors parameter in JSON format. Example Request: /webhook/centroid?vectors=[[2,3,4],[4,5,6],[6,7,8]] Output: Passes the received data to the next node. Extract & Parse Vectors (Set Node): Converts the input string into a proper JSON array for processing. Ensures vectors is a valid array. If the parameter is missing, it may generate an error. Expected Output Example: { "vectors": [[2,3,4],[4,5,6],[6,7,8]] } Validate & Compute Centroid (Code Node): Validates vector dimensions and calculates the centroid. Validation: Ensures all vectors have the same number of dimensions. Computation: Averages each dimension to determine the centroid. If validation fails: Returns an error message indicating inconsistent dimensions. Successful Output Example: { "centroid": [4,5,6] } Error Output Example: { "error": "Vectors have inconsistent dimensions." } Return Centroid Response (Respond to Webhook Node): Sends the final response back to the client. If the computation is successful, it returns the centroid. If an error occurs, it returns a descriptive error message. Example Response: { "centroid": [4, 5, 6] } Inputs JSON array of vectors, where each vector is an array of numerical values. Example Input { "vectors": [ [1, 2, 3], [4, 5, 6], [7, 8, 9] ] } Setup Guide Create a new workflow in n8n. Add a Webhook node (Receive Vectors) to receive JSON input. Add a Set node (Extract & Parse Vectors) to extract and convert the data. Add a Code node (Validate & Compute Centroid) to: Validate dimensions. Compute the centroid. Add a Respond to Webhook node (Return Centroid Response) to return the result. Function Node Script Example const input = items[0].json; const vectors = input.vectors; if (!Array.isArray(vectors) || vectors.length === 0) { return [{ json: { error: "Invalid input: Expected an array of vectors." } }]; } const dimension = vectors[0].length; if (!vectors.every(v => v.length === dimension)) { return [{ json: { error: "Vectors have inconsistent dimensions." } }]; } const centroid = new Array(dimension).fill(0); vectors.forEach(vector => { vector.forEach((val, index) => { centroid[index] += val; }); }); for (let i = 0; i < dimension; i++) { centroid[i] /= vectors.length; } return [{ json: { centroid } }]; Testing Use a tool like Postman or the n8n UI to send sample inputs and verify the responses. Modify the input vectors to test different scenarios. This workflow provides a simple yet flexible solution for vector centroid computation, ensuring validation and reliability.

Extract and Structure Invoice Data with DocSumo and Export to Excel

by Anurag

Description This workflow automates the extraction of structured data from invoices or similar documents using Docsumo's API. Users can upload a PDF via an n8n form trigger, which is then sent to Docsumo for processing and structured parsing. The workflow fetches key document metadata and all line items, reconstructs each invoice row with combined header and item details, and finally exports all results as an Excel file. Ideal for automating invoice data entry, reporting, or integrating with accounting systems. How It Works A user uploads a PDF document using the integrated n8n form trigger. The workflow securely sends the document to Docsumo via REST API. After uploading, it checks and retrieves the parsed document results. Header information and table line items are extracted and mapped into structured records. The complete result is exported as an Excel (.xls) file. Setup Steps Docsumo Account: Register and obtain your API key from Docsumo. n8n Credentials Manager: Add your Docsumo API key as an HTTP header credential (never hardcode the key in the workflow). Workflow Configuration: In the HTTP Request nodes, set the authentication to your saved Docsumo credentials. Update the file type or document type in the request (e.g., "type": "invoice") as needed for your use case. Testing: Enable the workflow and use the built-in form to upload a sample invoice for extraction. Features Supports PDF uploads via n8n’s built-in form or via API/webhook extension. Sends files directly to Docsumo for document data extraction using secure credentials. Extracts invoice-level metadata (number, date, vendor, totals) and full line item tables. Consolidates all data in easy-to-use Excel format for download or integration. Modular node structure, easily extensible for further automation. Prerequisites Docsumo account with API access enabled. n8n instance with form, HTTP Request, Code, and Excel/Convert to File nodes. Working Docsumo API Key stored securely in n8n’s credential manager. Example Use Cases | Scenario | Benefit | |---------------------|-----------------------------------------| | Invoice Automation | Extract line items and metadata rapidly | | Receipts Processing | Parse and digitize business receipts | | Bulk Bill Imports | Batch process bills for analytics | Notes Credentials Security:** Do not store your API key directly in HTTP Request nodes; always use n8n credentials manager. Sticky Notes:** The workflow includes sticky notes for setup, input, API call, extraction, and output steps to assist template users. Custom Columns:** You can customize header or line item extraction by editing the Code node as needed.

Conversational Lead Capture with Gemini 2.0 Flash AI and Google Sheets

by David Olusola

AI Lead Capture System - Complete Setup Guide Prerequisites n8n instance (cloud or self-hosted) Google AI Studio account (free tier available) Google account for Sheets integration Website with chat widget capability Phase 1: Core Infrastructure Setup Step 1: Set Up Google AI Studio Go to Google AI Studio Create account or sign in with Google Navigate to "Get API Key" Create new API key for your project Copy and securely store the API key Free tier limits: 15 requests/minute, 1 million tokens/month Step 2: Configure Google Sheets Create new Google Sheet for lead storage Add column headers (exact names): Full Name Company Name Email Address Phone Number Project Intent/Needs Project Timeline Budget Range Preferred Communication Channel How they heard about DAEX AI Copy the Google Sheet ID from URL (between /d/ and /edit) Ensure sheet is accessible to your Google account Step 3: Import n8n Workflow Open your n8n instance Create new workflow Click "..." menu → Import from JSON Paste the provided workflow JSON Workflow will appear with all nodes connected Phase 2: Credential Configuration Step 4: Set Up Google Gemini API In n8n, go to Credentials → Add Credential Search for "Google PaLM API" Enter your API key from Step 1 Test connection Link to the "Google Gemini Chat Model" node Step 5: Configure Google Sheets Access Go to Credentials → Add Credential Select "Google Sheets OAuth2 API" Follow OAuth flow to authorize your Google account Test connection with your sheet Link to the "Google Sheets" node Phase 3: Workflow Customization Step 6: Update Company Information Open the AI Agent node In the system message, replace all mentions of: Company name and description Service offerings and specializations FAQ knowledge base Typical project timelines and pricing ranges Adjust conversation tone to match your brand voice Step 7: Configure Lead Qualification Fields In the AI Agent system message, modify the required information list: Add/remove qualification questions Adjust budget ranges for your services Customize timeline options Update communication channel preferences In Google Sheets node, update column mappings if you changed fields Step 8: Set Up Sheet Integration Open Google Sheets node Click on Document ID dropdown Select your lead capture sheet Verify all column mappings match your sheet headers Test with sample data Phase 4: Website Integration Step 9: Get Webhook URL Open Webhook node in n8n Copy the webhook URL (starts with your n8n domain) Note: URL format is https://your-n8n-domain.com/webhook/[unique-id] Step 10: Connect Your Chat Widget Choose your integration method: Option A: Direct JavaScript Integration javascript// Add to your website function sendMessage(message, sessionId) { fetch('YOUR_WEBHOOK_URL', { method: 'POST', headers: { 'Content-Type': 'application/json' }, body: JSON.stringify({ message: message, sessionId: sessionId || 'visitor-' + Date.now() }) }) .then(response => response.json()) .then(data => { // Display AI response in your chat widget displayMessage(data.message); }); } Option B: Chat Platform Webhook Open your chat platform settings (Intercom, Crisp, etc.) Find webhook/integration section Add webhook URL pointing to your n8n endpoint Configure to send message and session data Option C: Zapier/Make.com Integration Create new Zap/Scenario Trigger: New chat message from your platform Action: HTTP POST to your n8n webhook Map message content and session ID Phase 5: Testing & Optimization Step 11: Test Complete Flow Send test message through your chat widget Verify AI responds appropriately Check conversation context is maintained Confirm lead data appears in Google Sheets Test with various conversation scenarios Step 12: Monitor Performance Check n8n execution logs for errors Monitor Google Sheets for data quality Review conversation logs for improvement opportunities Track response times and conversion rates Step 13: Fine-Tune Conversations Analyze real conversation logs Update system prompts based on common questions Add new FAQ knowledge to the AI agent Adjust qualification questions based on lead quality Optimize for your specific customer patterns Phase 6: Advanced Features (Optional) Step 14: Add Lead Scoring Create new column in Google Sheets for "Lead Score" Update AI agent to calculate scores based on: Budget range (higher budget = higher score) Timeline urgency (sooner = higher score) Project complexity (complex = higher score) Add conditional formatting in Google Sheets to highlight high-value leads Step 15: Set Up Notifications Add email notification node after Google Sheets Configure to send alerts for high-priority leads Include lead details and conversation summary Set up different notification rules for different lead scores Step 16: Analytics Dashboard Connect Google Sheets to Google Data Studio or similar Create dashboard showing: Daily lead volume Conversion rates by source Average qualification time Lead quality scores Revenue pipeline from captured leads Troubleshooting Common Issues AI Not Responding Check Google Gemini API key validity Verify API quota not exceeded Review n8n execution logs for errors Data Not Saving to Sheets Confirm Google Sheets permissions Check column name matching Verify sheet ID is correct Chat Widget Not Connecting Test webhook URL directly with curl/Postman Verify JSON format matches expected structure Check CORS settings if browser-based integration Conversation Context Lost Ensure sessionId is unique per visitor Check memory node configuration Verify sessionId is passed consistently

3 nodes89 views

Extract Amazon Best Seller Electronic Info with Bright Data and Google Gemini

by Ranjan Dailata

Who this is for? Extract Amazon Best Seller Electronic Info is an automated workflow that extracts best seller data from Amazon's Electronics section using Bright Data Web Unlocker, transform it into structured JSON using Google Gemini's LLM, and forwards a fully structured JSON response to a specified webhook for downstream use. This workflow is tailored for: eCommerce Analysts** Who need to monitor Amazon best-seller trends in the Electronics category and track changes in real-time or on a schedule. Product Intelligence Teams** Who want structured insights on competitor offerings, including rankings, prices, ratings, and promotions. AI-powered Chatbot Developers** Who are building assistants capable of answering product-related queries with fresh, structured data from Amazon. Growth Hackers & Marketers** Looking to automate competitive research and surface trending product data to inform pricing strategies. Data Aggregators and Price Trackers** Who need reliable and smart scraping of Amazon data enriched with AI-driven parsing. What problem is this workflow solving? Keeping up with Amazon's best sellers in Electronics is a time-consuming, error-prone task when done manually.This workflow automates the process, ensuring: Automating Data Extraction from Amazon Best Sellers using Bright Data, ensuring reliable access to real-time, structured data. Enhancing Raw Data with Google Gemini, turning product lists into structured JSON using the Google Gemini LLM. Sending Results to a Webhook, enabling seamless integration into dashboards, databases, or chatbots. What this workflow does The workflow performs the following steps: Extracts Amazon Best Seller Electronics page info using Bright Data's Web Unlocker API. Processes the unstructured content using Google Gemini's Flash Exp model to extract structured product data. Sends the structured information to a webhook endpoint. Setup Sign up at Bright Data. Navigate to Proxies & Scraping and create a new Web Unlocker zone by selecting Web Unlocker API under Scraping Solutions. In n8n, configure the Header Auth account under Credentials (Generic Auth Type: Header Authentication). The Value field should be set with the Bearer XXXXXXXXXXXXXX. The XXXXXXXXXXXXXX should be replaced by the Web Unlocker Token. In n8n, configure the Google Gemini(PaLM) Api account with the Google Gemini API key (or access through Vertex AI or proxy). Update the Amazon URL with the Bright Data zone by navigating to the Amazon URL with the Bright Data Zone node. Update the Webhook HTTP Request node with the Webhook endpoint of your choice. How to customize this workflow to your needs This workflow is built to be flexible - whether you're a market researcher, e-commerce entrepreneur, or data analyst. Here's how you can adapt it to fit your specific use case: Change the Amazon Category** Update the Amazon URL with the topic of your interest such as Computers & Accessories, Home Audio, etc. Customize the Gemini Prompt** Update the Gemini prompt to get different styles of output — comparison tables, summaries, feature highlights, etc. Send Output to Other Destinations** Replace the Webhook URL to forward output to: Google Sheets Airtable Slack or Discord Custom API endpoints

Track Student Attendance with Mobile App, Google Sheets, and Email Alerts

by Oneclick AI Squad

A lightweight no-code workflow that captures student check-in data via a mobile app or webhook, stores it in a Google Sheet, and instantly notifies the class teacher via email. 🎯 What This Does Students check in using a mobile app or QR code Their data is formatted and saved to a Google Sheet A notification email is sent to the class teacher in real time 🔧 Workflow Steps | Step | Description | | ------------------------------ | ----------------------------------------------------------- | | Student Check-in (Webhook) | Triggered via POST request from mobile app or QR scanner | | Format Data | Cleans and prepares incoming JSON into structured format | | Append or Update Row | Saves student check-in data into Google Sheets | | Email Teacher | Sends formatted check-in email to the class teacher | | Success Response | Returns a confirmation response to the mobile app or system | 📱 Example Check-in Input (Webhook Body) { "student_name": "Aarav Mehta", "student_id": "STU025", "class_name": "Grade 6B" } 📊 Google Sheets Format | Student Name | Student ID | Class | Date | Time | | ------------ | ---------- | -------- | ---------- | ----- | | Aarav Mehta | STU025 | Grade 6B | 2025-08-06 | 08:35 | Date and time are added dynamically in the workflow. ⚙️ Setup Requirements n8n Instance** – Deployed with public webhook support Google Sheets** – Sheet with columns as shown above Email SMTP Settings** – For sending teacher notification ✅ Quick Setup Instructions Import the workflow into your n8n instance Replace the webhook URL in your mobile app Set your Google Sheet ID and range Enter the teacher’s email in the “Email Teacher” node Test with mock data Deploy and use live!