Workflow Templates

Overview This workflow leverages the KIE. AI Veo3 model to generate AI videos from simple text descriptions. Users interact via a form interface, inputting a prompt (e.g., a scene description), and the system automatically submits the request to the KIE. AI API, monitors the generation status in real time, and retrieves the final video output. It's ideal for content creators, marketers, or developers exploring text-to-video AI creation, supporting intelligent video generation with minimal setup. Prerequisites A KIE. AI account and API key: Sign up at KIE.AI to obtain your free or paid API key. An active n8n instance (cloud or self-hosted) with HTTP Request and form submission capabilities. Basic knowledge of AI prompts for video generation to achieve optimal results. Setup Instructions Obtain API Key: Register at KIE. AI and generate your API key. Store it securely—do not share it publicly. Configure the Form: In the "On Form Submission" node, ensure fields like "prompt" (for video description) and "api_key" are set up. Example prompt: "A serene mountain landscape at sunset with birds flying." Test the Workflow: Click "Execute Workflow" in n8n. Access the generated form URL, submit your prompt and API key. The workflow will poll the API every 10 seconds until the video is ready, then display the results. Handle Outputs: The final node formats and displays the video file URL for download or embedding. Customization Tips Enhance Prompts**: Include specifics like duration, style (e.g., realistic, animated), actions, and visual elements to improve AI video quality. Keywords for SEO**: This template focuses on AI video generation, text-to-video models, Veo3 API integration, and automated workflows.

This workflow is designed to generate prompts for AI agents and store them in Airtable. It starts by receiving a chat message, processes it to create a structured prompt, categorizes the prompt, and finally stores it in Airtable. 2. Setup Instructions Prerequisites AI model eg Gemini, openAI etc** Airtable base and table or other storage tool** Step-by-Step Guide Clone the Workflow Copy the provided workflow JSON and import it into your n8n instance. Configure Credentials Set up the Google Gemini(PaLM) API account credentials. Set up the Airtable Personal Access Token account credentials. Map Airtable Base and Table Create a copy of the Prompt Library in Airtable. Map the Airtable base and table in the Airtable node. Customize Prompt Template Edit the 'Create prompt' node to customize the prompt template as needed. Configuration Options Prompt Template:** Customize the prompt template in the 'Create prompt' node to fit your specific use case. Airtable Mapping:** Ensure the Airtable base and table are correctly mapped in the Airtable node. 4. Running and Troubleshooting Running the Workflow Trigger the Workflow: Send a chat message to trigger the workflow. Monitor Execution: Use the n8n interface to monitor the workflow execution. Check Completion: Verify that the prompt is stored in Airtable and check the chat interface for the result. Troubleshooting Tips API Issues:** Ensure that the APIs and Airtable credentials are correctly configured. Data Mapping:** Verify that the Airtable base and table are correctly mapped. Prompt Template:** Check the prompt template for any errors or inconsistencies. Use Case Examples This workflow is particularly useful in scenarios where you want to automate the generation and management of AI agent prompts. Here are some examples: Rapid Prototyping of AI Agents: Quickly generate and test different prompts for AI agents in various applications. Content Creation:** Generate prompts for AI models that create blog posts, articles, or social media content. Customer Service Automation:** Develop prompts for AI-powered chatbots to handle customer inquiries and support requests. Educational Tools:** Create prompts for AI tutors or learning assistants. Industries/Professionals: Software Development:** Developers building AI-powered applications. Marketing:** Marketers automating content creation and social media management. Customer Service:** Customer service managers implementing AI-driven chatbots. Education:** Educators creating AI-based learning tools. Practical Value: Time Savings:** Automates the prompt generation process, saving significant time and effort. Improved Prompt Quality:** Leverages Google Gemini and structured prompt engineering principles to generate more effective prompts. Centralized Prompt Management:** Stores prompts in Airtable for easy access, organization, and reuse. 4. Running and Troubleshooting Running the Workflow:** Activate the workflow in n8n. Send a chat message to the webhook URL configured in the "When chat message received" node. Monitor the workflow execution in the n8n editor. Monitoring Execution:** Check the execution log in n8n to see the data flowing through each node and identify any errors. Checking for Successful Completion:** Verify that a new record is created in your Airtable base with the generated prompt, name, and category. Confirm that the "Return results" node sends back confirmation of the prompt in the chat interface. Troubleshooting Tips:** Error:** 400: Bad Request in the Google Gemini nodes: Cause:** Invalid API key or insufficient permissions. Solution:** Double-check your Google Gemini API key and ensure that the API is enabled for your project. Error:** Airtable node fails to create a record: Cause:** Invalid Airtable credentials, incorrect Base ID or Table ID, or mismatched column names. Solution:** Verify your Airtable API key, Base ID, Table ID, and column names. Ensure that the data types in n8n match the data types in your Airtable columns. Follow me on Linkedin for more

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

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Description This workflow automates document processing and structured table extraction using the Nanonets API. You can submit a PDF file via an n8n form trigger or webhook—the workflow then forwards the document to Nanonets, waits for asynchronous parsing to finish, retrieves the results (including header fields and line items/tables), and returns the output as an Excel file. Ideal for automating invoice, receipt, or order data extraction with downstream business use. How It Works A document is uploaded (via n8n form or webhook). The PDF is sent to the Nanonets Workflow API for parsing. The workflow waits until processing is complete. Parsed results are fetched. Both top-level fields and any table rows/line items are extracted and restructured. Data is exported to Excel format and delivered to the requester. Setup Steps Nanonets Account: Register for a Nanonets account and set up a workflow for your specific document type (e.g., invoice, receipt). Credentials in n8n: Add HTTP Basic Auth credentials in n8n for the Nanonets API (never store credentials directly in node parameters). Webhook/Form Configuration: Option 1: Configure and enable the included n8n Form Trigger node for document uploads. Option 2: Use the included Webhook node to accept external POSTs with a PDF file. Adjust Workflow: Update any HTTP nodes to use your credential profile. Insert your Nanonets Workflow ID in all relevant nodes. Test the Workflow: Enable the workflow and try with a sample document. Features Accepts documents via n8n Form Trigger or direct webhook POST. Securely sends files to Nanonets for document parsing (credentials stored in n8n credentials manager). Automatically waits for async processing, checking Nanonets until results are ready. Extracts both header data and all table/line items into a tabular format. Exports results as an Excel file download. Modular nodes allow easy customization or extension. Prerequisites Nanonets account** with workflow configured for your document type. n8n** instance with HTTP Request, Webhook/Form, Code, and Excel/Spreadsheet nodes enabled. Valid HTTP Basic Auth credentials** saved in n8n for API access. Example Use Cases | Scenario | Benefit | |-----------------------|--------------------------------------------------| | Invoice Processing | Automated extraction of line items and totals | | Receipt Digitization | Parse amounts and charges for expense reports | | Purchase Orders | Convert scanned POs into structured Excel sheets | Notes You must set up credentials in the n8n credentials manager—do not store API keys directly in nodes. All configuration and endpoints are clearly explained with inline sticky notes in the workflow editor. Easily adaptable for other document types or similar APIs—just modify endpoints and result mapping.

Markdown to Notion Blocks Converter Transform markdown-formatted text into properly structured Notion page content with this comprehensive workflow. Overview This workflow automatically converts markdown text into Notion's block format and inserts it directly into a Notion page. Perfect for content creators, documentation teams, and anyone who needs to migrate markdown content to Notion. Features Complete Markdown Support**: Handles headers (H1-H4), paragraphs, lists, quotes, code blocks, and horizontal rules Rich Text Formatting**: Preserves bold, italic, and link formatting Smart Text Processing**: Generates plain text excerpts and maintains original content structure Direct Notion Integration**: Automatically inserts converted blocks into your specified Notion page Batch Processing**: Efficiently handles large content blocks What It Does Takes markdown-formatted text as input Parses and converts it to Notion's block structure Handles complex formatting including: Headers and subheaders Bulleted and numbered lists Code blocks with syntax highlighting Blockquotes Bold and italic text Links Horizontal dividers Uploads the converted content directly to your Notion page Use Cases Content Migration**: Move existing markdown documentation to Notion Automated Publishing**: Convert blog posts or articles from markdown to Notion Documentation Workflows**: Streamline technical documentation processes Content Syndication**: Publish the same content across multiple platforms Requirements Notion API credentials Target Notion page ID Markdown-formatted source content Setup Configure your Notion API credentials Replace the page ID in the HTTP request node with your target Notion page Connect your markdown data source (replace the mock data node) Execute the workflow

What this workflow does This workflow extracts product details—like name, price, discount, and rating— from website screenshots using Dumpling AI. It starts when a new product page URL is added to a Google Sheet, captures a screenshot of that page, extracts visible product info from the image, and writes the results back into the sheet. What problem is this workflow solving? Many product pages block traditional scraping tools or use unstructured layouts. This workflow bypasses HTML limitations by using visual AI extraction, making it reliable even when content is embedded in images or hard to parse with code. Who is this for? This is ideal for eCommerce researchers, pricing analysts, marketers, or anyone building a product database from websites without needing to code or maintain complex scrapers. Setup Create a Google Sheet with a column named "Site" (or update the trigger). Add your product page URLs in this column—one per row. Connect your Google Sheets and Dumpling AI credentials in n8n. Ensure your Dumpling AI account has API access for screenshots and extraction. How to customize the workflow Prompt adjustment**: In the “Extract Text from Screenshot” node, you can modify the prompt to extract other information like brand name, delivery time, or availability. Add more fields**: After the extraction, edit the “Format Extracted Data” node to map additional fields from the response to your Google Sheet columns. Change output destination**: You can easily replace the Google Sheets module with Airtable, Notion, or another app if preferred. > ⚠️ This works best when the product data is clearly visible in the screenshot. > It won’t extract info that’s hidden behind popups or loaded via user interaction.

Automate Customer Feedback Analysis with Google Sheets, WhatsApp, and Email Introduction: Drowning in Data, Starving for Insight? Imagine this: Your team launches a new feature. Feedback starts pouring in emails, support tickets, social media mentions, and survey responses. You know gold is buried in there, but manually reading, tagging, and summarising hundreds, maybe thousands, of comments? It takes days, maybe weeks. By the time you have a clear picture, the moment might have passed. Sounds exhausting, right? What if you could have an AI assistant tirelessly working 24/7, instantly analysing every piece of feedback the moment it arrives? This isn't science fiction anymore. AI-powered automation can transform this slow, manual chore into a real-time insight engine, giving you the pulse of your customer base almost instantly. Let's explore how. What's the Goal? Understanding the Workflow Objective The core challenge is transforming raw, unstructured customer feedback into actionable intelligence quickly and efficiently. The Problem: Manual Overload: Sifting through vast amounts of feedback manually is incredibly time-consuming and prone to human error or bias. Delayed Insights: The lag between receiving feedback and understanding it means missed opportunities and slow responses to critical issues. Inconsistent Analysis: Different team members might interpret or categorize feedback differently, leading to unreliable trend spotting. The AI Solution: Automated Data Collection: Connects directly to feedback sources (surveys, social media, review sites, helpdesks). AI-Powered Analysis: Uses Large Language Models (LLMs) like GPT-4 or Claude to analyze sentiment, extract key topics, and summarize comments. Intelligent Categorization: Automatically tags feedback based on predefined or dynamically identified themes (e.g., "bug report," "feature request," "pricing issue"). Real-time Reporting: Pushes structured insights into dashboards, databases, or triggers notifications for immediate awareness. Outcome: You move from reactive problem-solving based on stale data to proactive, strategic decisions driven by a near real-time understanding of customer sentiment and needs. Why Does It Matter? Achieving 100X Productivity and Efficiency Look, automating feedback isn't just about saving time; it's about scaling your ability to listen and respond smarter, not harder. When you leverage AI, the gains aren't incremental - they're exponential. Here’s why this is a game changer: Blazing Speed: Analyse feedback 100x Faster (or more!) than manual methods. Insights appear in minutes or hours, not days or weeks. Unhuman Scalability: Process virtually unlimited volumes of feedback without needing to scale your human team proportionally. AI doesn't get tired or bored. Consistent Accuracy: AI applies analysis rules consistently, reducing human bias and ensuring reliable categorisation and sentiment scoring over time. Proactive Trend Spotting: Identify emerging issues or popular requests much earlier by analysing aggregated data automatically. Spot patterns humans might miss. Free Up Your Team: Let your talented team focus on acting on insights – improving products, fixing issues, engaging customers – instead of drowning in data entry. How It Works: AI Automation Step by Step Getting this set up is more straightforward than you might think, especially with tools like n8n acting as the central hub. Automated Feedback Triggering CRM/Website Event Node Trigger feedback requests after: Purchases (eCommerce) Support ticket resolution Feature usage (SaaS) Time-Based Node Schedule recurring NPS surveys Customer health check-ups Chat App Node (WhatsApp/Telegram/Messenger) Send conversational feedback prompts: "How was your recent experience with [specific interaction]?" Multi-Channel Feedback Collection Email Node (SendGrid/Mailchimp) Send personalized feedback requests Embed 1-5 rating widgets SMS Node (Twilio) Short mobile surveys: "Reply 1-5: How satisfied with your purchase?" Webhook Node Capture in-app feedback Process chatbot responses Social Media Node Monitor Twitter/X, Instagram mentions Analyze comments for unsolicited feedback AI-Powered Real-Time Analysis OpenAI/ChatGPT Node (Sentiment Analysis) Prompt: "Analyze sentiment (positive/neutral/negative) and key themes from: [customer feedback]" Output fields: Sentiment score (1-5) Urgency flag (high/medium/low) Key topics (billing, support, product, etc.) Translation Node (Optional) Convert multilingual feedback into a consistent language Instant AI Response System Conditional Node (Routing Logic) Positive feedback → Send thank-you + referral ask Neutral feedback → Follow-up question for details Negative feedback → Escalate to the human team AI Response Generator Node Prompt: "Create a personalized response to [feedback type] about [topic] with sentiment [score]" Adjust tone (professional/friendly/empathetic) Escalation Node Route critical issues to the support team with full context Automated Insights & Alerts Dashboard Node Real-time sentiment tracking Emerging issue detection Alert Node (Slack/Teams/Email) Notify teams of negative trends: "3+ complaints about checkout flow in the past hour!" Report Node Auto-generate weekly/monthly summaries: "Top 5 customer pain points this week" Product Board Integration Auto-create feature requests Prioritize based on feedback volume Tools of the Trade: AI & Automation Tech Stack You don't need a massive, complex tech stack. Focus on a few core, powerful tools: n8n: The workflow automation platform. This is the 'glue' that connects everything and orchestrates the process without needing deep coding knowledge. Honestly, it's incredibly versatile. OpenAI (GPT-4/GPT-4o): State-of-the-art LLM for high-quality text analysis, summarization, and classification. Great for complex understanding. Anthropic (Claude 3 Sonnet/Opus): Another top-tier LLM, known for strong performance in analysis and handling large contexts. Often, a great alternative or complement to GPT models. Feedback Sources APIs: Connectors for where your feedback lives (e.g., Typeform, SurveyMonkey, Twitter API, Zendesk API, Google Play/App Store review APIs). Data Storage/Destination: Where the processed insights go (e.g., Google Sheets, Airtable, Notion, PostgreSQL database, BigQuery). (Optional) Visualization Tool: Tools like Metabase, Grafana, Looker Studio, or Power BI to create dashboards from your structured feedback data. What's the Cost? Estimated Budget Let's talk investment. You're mainly looking at: Setup Costs: Primarily your time (or a consultant's) to design and build the initial workflow in n8n. Depending on complexity, this could range from a few hours to a few days. No major software licenses are usually needed upfront if using self-hosted n8n or starting with free/low-tier cloud plans. AI API Calls: You pay per usage to OpenAI/Anthropic. Costs depend heavily on volume but can start from $20-$50/month for moderate usage and scale up. Newer models are getting more cost-effective. n8n Hosting: Free if self-hosted (requires a server), or tiered cloud pricing starting around $20/month. Feedback Source APIs: Some platforms might have API access costs or rate limits on free tiers. Total Estimated Monthly Cost: For many businesses, ongoing costs can range from $50 - $500+ per month, highly dependent on feedback volume and AI model choice. The Return on Investment (ROI) is typically rapid. Consider the hours saved from manual analysis, the value of faster issue resolution, preventing churn, and the benefits of making product decisions based on real-time data. It often pays for itself very quickly. Who Benefits? Target Users and Industries This automated feedback loop isn't niche; it's valuable across many sectors and roles: Top Industries: SaaS (Software as a Service): Understanding user friction, feature requests, bug reports. E-commerce & Retail: Analyzing product reviews, post-purchase surveys, and support chats. Hospitality & Travel: Processing guest reviews, survey feedback. Mobile Apps: Monitoring app store reviews, in-app feedback. Financial Services: Gauging customer satisfaction with services, identifying pain points. Key Roles: Product Managers: Prioritizing features, understanding user needs, tracking launch reception. Customer Experience (CX) / Success Managers: Monitoring customer health, identifying churn risks, and improving support processes. Marketing Teams: Understanding brand perception, campaign feedback, and voice of the customer. Support Leads: Identifying recurring issues, measuring support quality, spotting training needs. This approach works for businesses of all sizes, from startups wanting to stay lean and agile to large enterprises needing to manage massive feedback volumes. How to use workflow? Importing a workflow in n8n is a straightforward process that allows you to use pre-built or shared workflows to save time. Below is a step-by-step guide to import a workflow in n8n, based on the official documentation and community resources. 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 (see export instructions below if needed). Format:** Ensure you have the workflow in JSON format, either as a file (e.g., 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. Note: If the workflow includes nodes for apps requiring credentials (e.g., Google Sheets), you’ll need to configure those credentials separately after importing.

Automated monitoring system that sends instant alerts when target companies make technology changes, delivered directly to your inbox or Slack. 🚀 What It Does Monitors technology stack changes Sends real-time email alerts Posts updates to Slack Tracks historical changes Filters by technology type 🎯 Perfect For Sales teams IT departments Competitive intelligence Technology vendors Market researchers ⚙️ Key Benefits ✅ Instant technology change alerts ✅ Multiple notification channels ✅ Historical tracking ✅ Customizable filters ✅ Team collaboration 🔧 What You Need BuiltWith API access Email service (SMTP/SendGrid) Slack workspace (optional) n8n instance 📊 Alerts Include Company name Technology changes Timestamp Impact assessment Direct links 🛠️ Setup & Support Quick Setup Get alerts in 15 minutes with our step-by-step guide 📺 Watch Tutorial 💼 Get Expert Support 📧 Direct Help Stay informed about technology changes that matter to your business with automated monitoring alerts and notifications.

Auto-generate & post content using AI This workflow helps you create daily content using just a topic prompt. It writes a tweet, generates an image, and publishes across Twitter, Facebook, and LinkedIn — all on autopilot. How it works Triggers daily at 10 PM to start the flow Uses OpenAI to generate a niche topic title Writes a short-form post (tweet style) with hashtags Generates a Japanese anime-style image for visual context Saves everything in Google Sheets Publishes automatically on Twitter, LinkedIn, and Facebook Set up steps You’ll need OpenAI, Google Sheets, and social media credentials (Twitter, Facebook, LinkedIn) Takes about 10–15 minutes to configure if you already have the credentials ready Make sure your Sheet and API keys are properly linked before activating 📝 Keep detailed notes inside the workflow with sticky notes for easier handoff or collaboration.

This workflow analyzes images submitted via a form using OpenAI Vision, then delivers the analysis result directly to your Telegram chat. ✅ Use case examples: • Users submit screenshots for instant AI interpretation • Automated document or receipt analysis with Telegram delivery • Quick OCR or image classification workflows ⸻ ⚙️ Setup Guide Form Submission Trigger • Connect your form app (e.g. Typeform, Tally, or n8n’s own webhook form) to the On form submission trigger node. • Ensure it sends the image file or URL as input. OpenAI Vision Analysis • In the OpenAI node, select Analyze Image operation. • Provide your OpenAI API key and configure the prompt to instruct the model on what to analyze (e.g. “Describe this receipt in detail”). Set Telegram Chat ID • Use this manual node to input your Telegram Chat ID for delivery. • Alternatively, automate this with a database lookup or user session if building for multiple users. Telegram Delivery Node • Connect your Telegram Bot to n8n using your bot token. • Set up the sendMessage operation, using the analysis result from the previous node as the message text. Testing • Click Execute workflow. • Submit an image via your form and confirm it delivers to your Telegram as expected.

How it works This workflow automatically scrapes real estate listings from Zillow and sends them to a Telegram channel. Key Steps Scheduled Trigger - Runs the workflow at specified intervals to find new listings. AI-Powered Scraping - Uses ScrapeGraphAI to extract property information from Zillow. Data Formatting - Processes and structures the scraped data for Telegram messages. Telegram Integration - Sends formatted listing details to your specified Telegram channel. Set up steps Setup time: 5-10 minutes Configure ScrapeGraphAI credentials - Add your ScrapeGraphAI API key. Set up Telegram connection - Connect your Telegram account and specify the target channel. Customize the Zillow URL - Update the URL to target specific locations or search criteria. Adjust schedule - Modify the trigger timing based on how frequently you want to check for new listings.

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. This workflow provides a complete, ready-to-use template for a Retrieval-Augmented Generation (RAG) system. It allows you to build a powerful AI chatbot that can answer questions based on the content of PDF documents you provide, using a modern and powerful stack for optimal performance. Good to know Costs:** This workflow uses paid services (OpenAI, Pinecone, Cohere). Costs will be incurred based on your usage. Please review the pricing pages for each service to understand the potential expenses. Video Tutorial (Bahasa Indonesia):** For a step-by-step guide on how this workflow functions, you can watch the accompanying video tutorial here: N8N Tutorial: Membangun Chatbot RAG dengan Pinecone, OpenAI, & Cohere How it works This workflow operates in two distinct stages: 1. Data Ingestion & Indexing: It begins when a .pdf file is uploaded via the n8n Form Trigger. The Default Data Loader node processes the PDF, and the Recursive Character Text Splitter breaks down the content into smaller, manageable chunks. The Embeddings OpenAI node converts these text chunks into vector embeddings (numerical representations). Finally, the Pinecone Vector Store node takes these embeddings and stores (upserts) them into your specified Pinecone index, creating a searchable knowledge base. 2. Conversational AI Agent: A user sends a message through the Chat Trigger. The AI Agent receives the message and uses its VectorDB tool to search the Pinecone index for relevant information. The Reranker Cohere node refines these search results, ensuring only the most relevant context is selected. The user's original question and the refined context are sent to the OpenAI Chat Model (gpt-4.1), which generates a helpful, context-aware answer. The Simple Memory node maintains conversation history, allowing for natural, multi-turn dialogues. How to use Using this workflow is a two-step process: Populate the Knowledge Base: First, you need to add documents. Trigger the workflow by using the Form Trigger and uploading a PDF file. Wait for the execution to complete. You can do this for multiple documents. Start Chatting: Once your data has been ingested, open the Chat Trigger's interface and start asking questions related to the content of your uploaded documents. The Form Trigger is just an example. Feel free to replace it with other triggers, such as a node that watches a Google Drive or Dropbox folder for new files. Requirements To run this workflow, you will need active accounts and API keys for the following services. OpenAI Account & API Key:** Function: Powers text embedding and the final chat generation. Required for the Embeddings OpenAI and OpenAI Chat Model nodes. Pinecone Account & API Key:** Function: Used to store and retrieve your vector knowledge base. Required for the Pinecone Vector Store and VectorDB nodes. You also need to provide your Pinecone Environment. Cohere Account & API Key:** Function: Improves the accuracy of your chatbot by re-ranking search results for relevance. Required for the Reranker Cohere node. Customising this workflow This template is a great starting point. Here are a few ways you can customize it: Change the AI Personality:* Edit the *System Message** in the AI Agent node to change the bot's behavior, tone, or instructions. Use Different Models:** You can easily swap the OpenAI model for another one (e.g., gpt-3.5-turbo for lower costs) in the OpenAI Chat Model node. Adjust Retrieval:** In the VectorDB tool node, you can modify the Top K parameter to retrieve more or fewer document chunks to use as context. Automate Ingestion:** Replace the manual Form Trigger with an automated one, like a node that triggers whenever a new file is added to a specific cloud storage folder.