Agents & Automations

Use AI to convert text to speech, send audio via email, and upload files to FTP using HTTP and ElevenLabs.

This n8n workflow illustrates how to convert PDF files into text with the PDF Toolkit from www.customjs.space. What this workflow does: - Change the requested HTML to PDF. - Extract text from the PDF. - Use a Code node to handle URLs that point to PDF files. - Convert the PDF to text. Requirements: - Self-hosted n8n instance. - CustomJS API key for converting PDF to text. - HTML Data to convert PDF files. - Code node for handling URL that indicates PDF file. Workflow Steps: 1. Manual Trigger: Runs with user interaction. 2. HTML to PDF: Request HTML Data Convert HTML to PDF 3. Convert PDF to Text: Convert the generated Text from PDF Usage: 1. Get API key from CustomJS: - Sign up to CustomJS platform. - Navigate to your profile page. - Press "Show" button to get API key. 2. Set Credentials for CustomJS API on n8n: Copy and paste your API key generated from CustomJS here. 3. Design workflow: - A Manual Trigger for starting workflow. - HTTP Request Nodes for downloading PDF files. - Code node for handling URL that indicates PDF file. - Convert PDF to Text. You can replace logic for triggering and returning results. For example, you can trigger this workflow by calling a webhook and get a result as a response from webhook. Simply replace Manual Trigger and Write to Disk nodes.

Overview This workflow template automates lead management and customer inquiry processing by integrating ERPNext, AI agents, and email notifications. It streamlines the process of capturing leads, analyzing inquiries, and generating actionable responses. The workflow uses ERPNext to capture inquiries, analyzes them with AI, and notifies the appropriate team or individual, all while maintaining a professional approach. What This Template DoesERPNext Webhook Integration: - Captures leads and inquiries through ERPNext webhooks. - Triggers the workflow when a new lead is created. AI-Powered Inquiry Analysis: - Uses AI to extract key details from lead notes (e.g., customer name, organization, inquiry summary). - Classifies inquiries as valid or invalid based on relevance to products, services, or solutions. Contact Assignment: - Matches inquiries to the appropriate contact(s) using a Google Sheets database or ERPNext contact information. - Handles multiple contacts if required. Email Notifications: - Generates professional email notifications for valid inquiries. - Sends emails to the appropriate contact(s) with inquiry details and action steps. Invalid Lead Handling: - Identifies invalid inquiries (e.g., unrelated to products or services) and flags them for follow-up or dismissal. Custom Email Formatting: - Converts plain text into professionally formatted HTML emails. - Ensures that communication is clear, concise, and visually appealing. How It WorksStep 1: Capture Lead Data - Webhook in ERPNext: Create a webhook in ERPNext for the "Lead" DocType. Set the trigger to on_insert to capture new leads in real-time. - Lead Details: The workflow fetches lead details, including notes, contact information, and the source of the lead. Step 2: Validate and Analyze Inquiry - AI Agent for Analysis: An AI agent analyzes the lead notes to extract key details and classify the inquiry as valid or invalid. The analysis includes checking the relevance of the inquiry to products, services, or solutions offered by the company. - Invalid Leads: If the inquiry is invalid, the workflow flags it and stops further processing. Step 3: Assign Contact(s) - Google Sheets Integration: Uses a Google Sheets database to map products, services, or solutions to responsible contacts. Ensures that inquiries are directed to the right person or team. - Multiple Contacts: Handles cases where multiple contacts are responsible for a particular product or service. Step 4: Generate and Send Email Notifications - AI-Generated Emails: The workflow generates a professional email summarizing the inquiry. Emails include details like customer name, organization, inquiry summary, and action steps. - Custom HTML Formatting: Emails are converted to HTML for a polished and professional appearance. - Send Notifications: Sends email notifications through Microsoft Outlook or another configured email client. Optionally, notifies via WhatsApp or SMS for urgent inquiries. Step 5: Post-Inquiry Actions - ERPNext Record Updates: Updates the lead record in ERPNext with relevant details, including inquiry status and contact information. Setup InstructionsPrerequisites - ERPNext: A configured ERPNext instance with lead data and a webhook for the "Lead" DocType. - Google Sheets: A sheet mapping products, services, or solutions to responsible contacts. - AI Integration: Credentials for OpenAI or other supported AI platforms. - Email Client: Credentials for Microsoft Outlook or another email client. Step-by-Step Setup - ERPNext Configuration: Create a webhook for the "Lead" DocType in ERPNext. Test the webhook with sample data to ensure proper integration. - Workflow Import: Import the workflow template into n8n. Configure nodes with your API credentials for ERPNext, Google Sheets, and AI tools. - Google Sheets Integration: Prepare a Google Sheet with columns for product, service, or solution and the responsible contact(s). Link the sheet to the workflow. - AI Agent Configuration: Customize the AI agent’s prompts to align with your business’s products and services. Adjust criteria for valid and invalid inquiries as needed. - Email Setup: Configure the email client node with your email service credentials. Customize the email template for your organization. - Testing: Run the workflow with sample leads to validate the entire process. Check email notifications, contact assignments, and record updates in ERPNext. Dos and Don’tsDos: - Test Thoroughly: Test the workflow with various scenarios before deploying in production. - Secure Credentials: Keep API and email credentials secure to avoid unauthorized access. - Customize Prompts: Tailor AI prompts to match your business needs and language style. - Use Professional Email Templates: Ensure emails are clear and well-formatted. Don’ts: - Skip Validation: Always validate inquiry data to avoid sending irrelevant notifications. - Overload the Workflow: Avoid adding unnecessary nodes that can slow down processing. - Ignore Errors: Monitor logs and address errors promptly for a smooth workflow.

How It Works: • Scrapes company review data from Glassdoor using ScrapingBee. • Extracts demographic-based ratings using AI-powered text analysis. • Calculates workplace disparities with statistical measures like z-scores, effect sizes, and p-values. • Generates visualizations (scatter plots, bar charts) to highlight patterns of discrimination or bias. Set Up Steps:Estimated time: ~20 minutes. • Replace ScrapingBee and OpenAI credentials with your own. • Input the company name you want to analyze (best results with large U.S.-based organizations). • Run the workflow and review the AI-generated insights and visual reports. This workflow empowers users to identify potential workplace discrimination trends, helping advocate for greater equity and accountability.

This n8n template combines an AI agent with n8n's multi-page forms to create a novel interaction that allows automated question-and-answer sessions. One of the more obvious use-cases of this interaction is what I'm calling the AI interviewer. A form trigger is used to start the interview, and a new session is created in Redis to capture the transcript. An AI agent is then tasked to ask questions to the user regarding the topic of the interview. This is set up as a loop so the questions never stop unless the user wishes to end the interview. Each answer is recorded in our session set up earlier between questions. When the user requests to end the interview, we break the loop and show the interview completion screen. Finally, the session is then saved in a Google Sheet, which can then be shared with team members and for the purpose of data analysis. You'll need to be on an n8n instance that is accessible to your target audience. Not technical enough to set up your own server? Try out n8n cloud and instantly deploy the template! Remember to activate the workflow so the form trigger is published and available for users to use. Requirements: - Groq LLM for AI agent. Feel free to swap this out for any other LLM. - Redis(-compatible) storage for capturing sessions. The next step would be adding tools! AI interviews with knowledge retrieval could definitely open up other possibilities, e.g., an onboarding wizard generating questions by pulling facts from an internal knowledge base.

Automatically log new email summaries in Google Sheets using ChatGPT. Streamline email management and response creation effortlessly.

Enhance your ad campaigns by easily generating compelling Google Ads copy through the integration of Google Sheets and ChatGPT, maximizing the effectiveness of your ads.

This n8n workflow automates the process of parsing and extracting data from PDF invoices. With this workflow, accounts and finance people can realize huge time and cost savings in their busy schedules. How it works This workflow will watch an email inbox for incoming invoices from suppliers. It will download the attached PDFs and process them through a third-party service called LlamaParse. LlamaParse is specifically designed to handle and convert complex PDF data structures such as tables to markdown. Markdown is easy to process for LLM models, making the data extraction by our AI agent more accurate and reliable. The workflow exports the extracted data from the AI agent to Google Sheets once the job is complete. Requirements - The criteria of the email trigger must be configured to capture emails with attachments. - The Gmail label "invoice synced" must be created before using this workflow. - A LlamaIndex.ai account to use the LlamaParse service. - An OpenAI account to use GPT for AI work. - Google Sheets to save the output of the data extraction process, although this can be replaced with whatever your needs. Customizing this workflow This workflow uses Gmail and Google Sheets, but these can easily be swapped out for equivalent services such as Outlook and Excel. Not using Excel? Simply redirect the output of the AI agent to your accounting software of choice.

Video Guide I prepared a detailed guide that shows the whole process of building an AI tool to analyze Instagram Reels using n8n. Who is this for? This workflow is ideal for social media analysts, digital marketers, and content creators who want to leverage data-driven insights from their Instagram Reels. It's particularly useful for those looking to automate the analysis of video performance to inform strategy and content creation. What problem does this workflow solve? Analyzing video performance on Instagram can be tedious and time-consuming, requiring multiple steps and data extraction. This workflow automates the process of fetching, analyzing, and recording insights from Instagram Reels, making it simpler for users to track engagement metrics without manual intervention. What this workflow does This workflow integrates several services to analyze Instagram Reels, allowing users to: - Automatically fetch recent Reels from specified creators. - Analyze the most-watched videos for insights. - Store and manage data in Airtable for easy access and reporting. Setup 1. Create accounts: Set up Airtable, Edify, n8n, and Gemini accounts. 2. Prepare triggers and modules: Replace credentials in each node accordingly. 3. Configure data flow: Ensure modules are set to fetch and analyze the correct data fields as outlined in the guide. 4. Test the workflow: Run the scenario manually to confirm that data is fetched and analyzed correctly.

Import the search queries related to your keyword combinations to understand what people are searching for. Identify the main topics, keywords, and gaps, and generate content ideas that bridge those gaps. For support and other questions, please reach out to [email protected].

Use this automation to update records between two different tables in Airtable. Watch new records, search records in another table, generate completions, and update records in the desired table.

This workflow automates voice reminders for upcoming appointments by generating a professional audio message and sending it to clients via email with the voice file attached. It integrates Google Calendar to track appointments, ElevenLabs to generate high-quality voice messages, and Gmail to deliver them efficiently. Who Needs Automated Voice Appointment Reminders? This automated voice appointment reminder system is ideal for businesses that rely on scheduled appointments. It helps reduce no-shows, improve client engagement, and streamline communication. - Medical Offices & Clinics – Ensure patients receive timely appointment reminders. - Real Estate Agencies – Keep potential buyers and renters informed about property visits. - Service-Based Businesses – Perfect for salons, consultants, therapists, and coaches. - Legal & Financial Services – Help clients remember important meetings and consultations. If your business depends on scheduled appointments, this workflow saves time and enhances client satisfaction. 🚀 Why Use This Workflow? - Ensures clients receive timely reminders. - Reduces appointment no-shows and scheduling issues. - Automates the process with a personalized voice message. Step-by-Step: How This Workflow Automates Voice Reminders 1. Trigger the Workflow – The system runs manually or on a schedule to check upcoming appointments in Google Calendar. 2. Retrieve Appointment Data – It fetches event details (client name, time, and location) from Google Calendar. The workflow uses the summary, start.dateTime, location, and attendees[0].email fields from Google Calendar to personalize and send the voice reminders. 3. Generate a Voice Reminder – Using ElevenLabs, the workflow converts the appointment details into a natural-sounding voice message. 4. Send via Email – The generated audio file is attached to an email and sent to the client as a reminder. Customization: Tailor the Workflow to Your Business Needs - Adjust Trigger Frequency – Modify the scheduling to run daily, hourly, or at specific intervals. - Customize Voice Message Format – Change the script structure and voice tone to match your business needs. - Change Notification Method – Instead of email, integrate SMS or WhatsApp for delivery. 🔑 Prerequisites - Google Calendar Access – Ensure you have access to the calendar with scheduled appointments. - ElevenLabs API Key – Required for generating voice messages (you can start for free). - Gmail API Access – Needed for sending reminder emails. - n8n Setup – The workflow runs on an n8n instance (self-hosted or cloud). 🚀 Step-by-Step Installation & Setup 1. Set Up Google Calendar API - Go to Google Cloud Console. - Create a new project and enable Google Calendar API. - Generate OAuth 2.0 credentials and save them for n8n. 2. Get an ElevenLabs API Key - Sign up at ElevenLabs. - Retrieve your API key from the dashboard. 3. Configure Gmail API - Enable Gmail API in Google Cloud Console. - Create OAuth credentials and authorize your email address for sending. 4. Deploy n8n & Install the Workflow - Install n8n (Installation Guide). - Add the required Google Calendar, ElevenLabs, and Gmail nodes. - Import or build the workflow with the correct credentials. - Test and fine-tune as needed. ⚠ Important: The LangChain Community node used in this workflow only works on self-hosted n8n instances. It is not compatible with n8n Cloud. Please ensure you are running a self-hosted instance before using this workflow. This workflow ensures a professional and seamless experience for your clients, keeping them informed and engaged. 🚀🔊

Pizza Ordering Chatbot with OpenAI - Menu, Orders & Status Tracking This workflow template is designed to automate order processing for a pizza store using OpenAI and n8n. The chatbot acts as a virtual assistant to handle customer inquiries related to menu details, order placement, and order status tracking. Features The chatbot provides an interactive experience for customers by performing the following functions: - Menu Inquiry: When a customer asks about the menu, the chatbot responds with a list of available pizzas, prices, and additional options. - Order Placement: If a customer places an order, the chatbot confirms order details, provides a summary, informs the customer that the order is being processed, and expresses gratitude. - Order Status Tracking: If a customer asks about their order status, the chatbot retrieves details such as order date, pizza type, and quantity, providing real-time updates. Prerequisites Before setting up the workflow, ensure you have the following: - OpenAI account - OpenAI API key to interact with GPT-3.5 - n8n instance running locally or on a server Configuration StepsStep 1: Set Up OpenAI API Credentials - Log in to OpenAI's website. - Navigate to API Keys under your account settings. - Click Create API Key and copy the key for later use. Step 2: Configure OpenAI Node in n8n - Open n8n and create a new workflow. - Click Add Node and search for OpenAI. - Select OpenAI from the list. - In the OpenAI node settings, click "Create New" under the Credentials section. - Enter a name for the credentials (e.g., "PizzaBot OpenAI Key"). - Paste your API Key into the field. - Click Save. Step 3: Set Up the Chatbot Logic - Connect the AI Agent Builder Node to the OpenAI Node and HTTP Request Node. - Configure the OpenAI Node with the following settings: - Model: gpt-3.5-turbo - Prompt: Provide dynamic text based on customer inquiries (e.g., "List available pizzas," "Place an order for Margherita pizza," "Check my order status"). - Temperature: Adjust based on desired creativity (recommended: 0.7). - Max Tokens: Limit response length (recommended: 150). - Add multiple HTTP Request Nodes: - For Get Products: Fetch stored menu data and return details. - For Order Product: Capture order details, generate an order ID, and confirm with the customer. - For Get Order: Retrieve order details based on the order ID and display progress. Step 4: Testing and Deployment - Click Execute Workflow to test the chatbot. - Open the Chat Message node, then copy the chat URL to access the chatbot in your browser. - Interact with the chatbot by asking different queries (e.g., "What pizzas do you have?" or "I want to order a Pepperoni pizza"). - Verify responses and adjust prompts or configurations as needed. - Deploy the workflow and integrate it with a messaging platform (e.g., Telegram, WhatsApp, or a website chatbot). Conclusion This n8n workflow enables a fully functional pizza ordering chatbot using OpenAI's GPT-3.5. Customers can view menus, place orders, and track their order status efficiently. You can further customize the chatbot by refining prompts, adding new features, or integrating with external databases for order management. 🚀 Happy automating!

AI Chatbot for Collecting Leads for Travel Agencies. This automation uses Voiceflow, so you’ll need to import the template directly into Voiceflow.

Gain full visibility into decentralized exchanges using CoinMarketCap’s DEXScan API—powered by AI. This workflow is part of the CoinMarketCap AI Analyst system and delivers real-time and historical insights on spot trading pairs, DEX liquidity, trading activity, and OHLCV data across chains like Ethereum, Polygon, Solana, and more. Use this workflow as a sub-agent triggered by a parent supervisor workflow, or run it manually with inputs sessionId and message. 🔧 Supported Tools (8 Total) - DEX Metadata → Static info (name, launch date, logo, URLs) - DEX Networks List → All supported DEX chains + network metadata - DEX Listings Quotes → Ranked list of DEXs with live trading volume, market share - DEX Pair Quotes (Latest) → Real-time liquidity, price, and buy/sell stats - DEX OHLCV Historical → Time-series data (daily/hourly/1m) - DEX OHLCV Latest → Today’s price, volume, open/close for pairs - DEX Trades Latest → Up to 100 recent trades for any DEX pair - DEX Spot Pairs Latest → Active token pairs across DEXs + filters (volume, liquidity, volatility) 💡 Use Cases - Find top DEXs by 24h volume - Get spot pairs with highest liquidity on a specific network - Track historical OHLCV for Uniswap pairs - View latest trades for SOL/USDC pool - Analyze tax, pooled % and holders for specific pairs - Filter pairs by 24h volume, percent change, liquidity, or number of transactions ✅ Example Queries - "Top 5 DEXs by 24h volume on Ethereum" - "Get historical OHLCV for SOL-USDC on Solana" - "Latest trades for a PancakeSwap pair" - "Show all spot pairs with over $500K in liquidity on Polygon" - "Retrieve metadata for Uniswap and SushiSwap" 🛠️ Setup Instructions 1. Get a CoinMarketCap API Key 2. Sign up at: https://coinmarketcap.com/api/ 3. Add API Key to Credentials in n8n 4. Use HTTP Header Auth method 5. Trigger from Parent Workflow (Optional) 6. Use Execute Workflow and pass message and sessionId Test Prompt Ideas Try: "Compare liquidity of Uniswap and Curve pairs on Ethereum" Sticky Notes Included - DEXScan Agent Guide – Workflow architecture + supported tools - Usage & API Call Examples – Prompts, test inputs, setup flow - Error Codes + Licensing – 400/401/429/500 troubleshooting, IP rights ✅ Final Notes This agent is part of the CoinMarketCap AI Analyst System, which includes multiple specialized agents for cryptocurrencies, exchanges, and community data. Master DEX analytics with AI—get powerful liquidity, trading, and pair insights in seconds.

Summary Engage multiple, uniquely configured AI agents (using different models via OpenRouter) in a single conversation. Trigger specific agents with @mentions or let them all respond. Easily scalable by editing simple JSON settings. Overview This workflow is for users who want to experiment with or utilize multiple AI agents with distinct personalities, instructions, and underlying models within a single chat interface, without complex setup. It solves the problem of managing and interacting with diverse AI assistants simultaneously for tasks like brainstorming, comparative analysis, or role-playing scenarios. It enables dynamic conversations with multiple AI assistants simultaneously within a single chat interface. You can: - Define multiple unique AI agents. - Configure each agent with its own name, system instructions, and LLM model (via OpenRouter). - Interact with specific agents using @AgentName mentions. - Have all agents respond (in random order) if no specific agents are mentioned. - Maintain conversation history across multiple turns. It's designed for flexibility and scalability, allowing you to easily add or modify agents without complex workflow restructuring. Key Features - Multi-Agent Interaction: Chat with several distinct AI personalities at once. - Individual Agent Configuration: Customize name, system prompt, and LLM for each agent. - OpenRouter Integration: Access a wide variety of LLMs compatible with OpenRouter. - Mention-Based Triggering: Direct messages to specific agents using @AgentName. - All-Agent Fallback: Engages all defined agents randomly if no mentions are used. - Scalable Setup: Agent configuration is centralized in a single Code node (as JSON). - Conversation Memory: Remembers previous interactions within the session. How to Set Up 1. Configure Settings (Code Nodes): - Open the Define Global Settings Code node: Edit the JSON to set user details (name, location, notes) and add any system message instructions that all agents should follow. - Open the Define Agent Settings Code node: Edit the JSON to define your agents. Add or remove agent objects as needed. For each agent, specify: - "name": The unique name for the agent (used for @mentions). - "model": The OpenRouter model identifier (e.g., "openai/gpt-4o", "anthropic/claude-3.7-sonnet"). - "systemMessage": Specific instructions or persona for this agent. 2. Add OpenRouter Credentials: - Locate the AI Agent node. - Click the OpenRouter Chat Model node connected below it via the Language Model input. - In the 'Credential for OpenRouter API' field, select or create your OpenRouter API credentials. How to Use - Start a conversation using the Chat Trigger input. - To address specific agents, include @AgentName in your message. Agents will respond sequentially in the order they are mentioned. Example: "@Gemma @Claude, please continue the count: 1" will trigger Gemma first, followed by Claude. If your message contains no @mentions, all agents defined in Define Agent Settings will respond in a randomized order. Example: "What are your thoughts on the future of AI?" will trigger Chad, Claude, and Gemma (based on your default settings) in a random sequence. The workflow will collect responses from all triggered agents and return them as a single, formatted message. How It Works (Technical Details) - Settings Nodes: Define Global Settings and Define Agent Settings load your configurations. - Mention Extraction: The Extract mentions Code node parses the user's input (chatInput) from the When chat message received trigger. It looks for @AgentName patterns matching the names defined in Define Agent Settings. - Agent Selection: - If mentions are found, it creates a list of the corresponding agent configurations in the order they were mentioned. - If no mentions are found, it creates a list of all defined agent configurations and shuffles them randomly. - Looping: The Loop Over Items node iterates through the selected agent list. - Dynamic Agent Execution: Inside the loop: - An If node (First loop?) checks if it's the first agent responding. If yes (true path -> Set user message as input), it passes the original user message to the Agent. If no (false path -> Set last Assistant message as input), it passes the previous agent's formatted output (lastAssistantMessage) to the next agent, creating a sequential chain. - The AI Agent node receives the input message. Its System Message and the Model in the connected OpenRouter Chat Model node are dynamically populated using expressions referencing the current agent's data from the loop ({{ $('Loop Over Items').item.json.* }}). - The Simple Memory node provides conversation history to the AI Agent. - The agent's response is formatted (e.g., AgentName:\\n\\nResponse) in the Set lastAssistantMessage node. - Response Aggregation: After the loop finishes, the Combine and format responses Code node gathers all the lastAssistantMessage outputs and joins them into a single text block, separated by horizontal rules (---), ready to be sent back to the user. Benefits - Scalability & Flexibility: Instead of complex branching logic, adding, removing, or modifying agents only requires editing simple JSON in the Define Agent Settings node, making setup and maintenance significantly easier, especially for those managing multiple assistants. - Model Choice: Use the best model for each agent's specific task or persona via OpenRouter. - Centralized Configuration: Keeps agent setup tidy and manageable. Limitations - Sequential Responses: Agents respond one after another based on mention order (or randomly), not in parallel. - No Direct Agent-to-Agent Interaction (within a turn): Agents cannot directly call or reply to each other during the processing of a single user message. Agent B sees Agent A's response only because the workflow passes it as input in the next loop iteration. - Delayed Output: The user receives the combined response only after all triggered agents have completed their generation.

This n8n template demonstrates how to get started with Gemini 2.0's new Bounding Box detection capabilities in your workflows. The key difference being this enables prompt-based object detection for images, which is powerful for things like contextual search over an image. For example, "Put a bounding box around all adults with children in this image" or "Put a bounding box around cars parked out of bounds of a parking space." How it works An image is downloaded via the HTTP node, and an "Edit Image" node is used to extract the file's width and height. The image is then given to the Gemini 2.0 API to parse and return coordinates of the bounding box of the requested subjects. In this demo, we've asked for the AI to identify all bunnies. The coordinates are then rescaled with the original image's width and height to correctly align them. Finally, to measure the accuracy of the object detection, we use the "Edit Image" node to draw the bounding boxes onto the original image. How to use It's really up to your imagination! Perhaps a form of grounding for evidence-based workflows or a higher form of image search can be built. Requirements - Google Gemini for LLM Customizing the workflow This template is just a demonstration of an experimental version of Gemini 2.0. It is recommended to wait for Gemini 2.0 to come out of this stage before using it in production.

The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message is turned into a vector and compared to the vectors in Pinecone. The most similar vectors are retrieved and passed to OpenAI for generating a chat response. Note: To use this template, you need to be on n8n version 1.19.4 or later.

🤖 AI-Powered RAG Chatbot with Google Drive Integration This workflow creates a powerful RAG (Retrieval-Augmented Generation) chatbot that can process, store, and interact with documents from Google Drive using Qdrant vector storage and Google's Gemini AI. How It WorksDocument Processing & Storage 📚 - Retrieves documents from a specified Google Drive folder - Processes and splits documents into manageable chunks - Extracts metadata using AI for enhanced search capabilities - Stores document vectors in Qdrant for efficient retrieval Intelligent Chat Interface 💬 - Provides a conversational interface powered by Google Gemini - Uses RAG to retrieve relevant context from stored documents - Maintains chat history in Google Docs for reference - Delivers accurate, context-aware responses Vector Store Management 🗄️ - Features secure delete operations with human verification - Includes Telegram notifications for important operations - Maintains data integrity with proper version control - Supports batch processing of documents Setup Steps 1. Configure API Credentials: - Set up Google Drive & Docs access - Configure Gemini AI API - Set up Qdrant vector store connection - Add Telegram bot for notifications - Add OpenAI Api Key to the 'Delete Qdrant Points by File ID' node 2. Configure Document Sources: - Set Google Drive folder ID - Define Qdrant collection name - Set up document processing parameters 3. Test and Deploy: - Verify document processing - Test chat functionality - Confirm vector store operations - Check notification system This workflow is ideal for organizations needing to create intelligent chatbots that can access and understand large document repositories while maintaining context and providing accurate responses through RAG technology.

Workflow Overview This workflow automates the process of scraping Trustpilot reviews, extracting key details, analyzing sentiment, and saving the results to Google Sheets. It uses OpenAI for sentiment analysis and HTML parsing for review extraction. --- How It Works 1. Scrape Trustpilot Reviews - HTTP Request: Fetches review pages from Trustpilot (https://it.trustpilot.com/review/{{company_id}}). - Paginates through pages (up to max_page limit). - HTML Parsing: Extracts review URLs using CSS selectors and splits the URLs into individual review links. 2. Extract Review Details - Information Extractor: Uses DeepSeek to extract structured data from the review: - Author: Name of the reviewer. - Rating: Numeric rating (1-5). - Date: Review date in YYYY-MM-DD format. - Title: Review title. - Text: Full review text. - Total Reviews: Number of reviews by the user. - Country: Reviewer’s country (2-letter code). 3. Sentiment Analysis - Sentiment Analysis Node: Uses OpenAI to classify the review text as Positive, Neutral, or Negative. - Example output: { "category": "Positive", "confidence": 0.95 } 4. Save to Google Sheets - Google Sheets Node: Appends or updates the extracted data to a Google Sheet. --- Set Up Steps 1. Configure Trustpilot Scraping - Edit Fields1 Node: Set company_id to the Trustpilot company name and set max_page to limit the number of pages scraped. 2. Configure Google Sheets - Google Sheets Node: Update the documentId with your Google Sheet ID and ensure the sheet has the required columns (Id, Data, Nome, etc.). 3. Configure OpenAI - OpenAI Chat Model Node: Add your OpenAI API key. - Sentiment Analysis Node: Ensure the categories match your desired sentiment labels (Positive, Neutral, Negative). --- Key Components - Nodes: - HTTP Request/HTML: Scrape and parse Trustpilot reviews. - Information Extractor: Extract structured review data using DeepSeek. - Sentiment Analysis: Classify review sentiment. - Google Sheets: Save and update review data. - Credentials: - OpenAI API key. - DeepSeek API key. - Google Sheets OAuth2.

This n8n template extends the idea of follow-up reminders by having an AI agent suggest and book the next call or message to re-engage prospects which have been ignored. What makes this template particularly interesting and actually usable is that it uses the Human-in-the-loop approach to wait for a user's approval before actually making the booking or otherwise not if the user declined. A twist on a traditional idea where we can reduce the number of actionable tasks a human has to make by delegating them to AI. How it works A scheduled trigger checks your Google Calendar for sales meetings which happened a few days ago. For each event, Gmail search is used to figure out if a follow-up message has been sent or received from the other party since the meeting. If none, it might mean the user needs a reminder to follow-up. For leads applicable for follow-up, we first get an AI Agent to find available meeting slots in the calendar. These slots and reminders are sent to the user via send-and-approval mode of the Gmail node. The user replies in natural language either picking a slot, suggesting an entirely new slot, or declining the request. When accepted, another AI Agent books the meeting in the calendar with the proposed dates and lead. When declined, no action is taken. How to use Update all calendar nodes (+subnodes) to point to the right calendar. If this is a shared-purpose calendar, you may need to either filter or create a new calendar. Update the Gmail nodes to point to the right accounts. Requirements - Google OAuth for Email and Calendar - OpenAI for LLM Customizing the template Not using Google? Swap out for Microsoft Outlook/Calendar or something else. Try swapping out or adding in additional send-for-approval methods such as Telegram or WhatsApp.