Workflow Templates

4 nodes1291 views

Real-time Email RAG Assistant with Gmail, OpenAI GPT, and PGVector

by Zain Ali

💬Communication & Collaboration

🧠 Email real time RAG Assistant with Gmail, OpenAI & PGVector 📌 Who’s it for This workflow is ideal for: Professionals Project managers Sales and support teams Anyone managing high volumes of Gmail messages It enables fast and intelligent search through your email inbox using natural language queries. ⚙️ How it works / What it does Continuously monitors your Gmail inbox for new emails. Extracts email content and metadata (subject, body, sender, date). Converts email content into vector embeddings using OpenAI. Stores embeddings in a PostgreSQL database with PGVector. A conversational AI agent performs semantic search on your stored email history. Supports time-sensitive and context-aware responses via OpenAI Chat model. 🚀 How to set up Connect your Gmail account to the Gmail Trigger node (with API access enabled). Configure OpenAI credentials for the Embedding and Chat nodes. Set up a PostgreSQL database with the PGVector extension enabled. Import the workflow into your n8n instance (Cloud or Self-hosted). Customize parameters like polling frequency, embedding settings, or vector query depth. 📋 Requirements ✅ n8n instance (Self-hosted or Cloud) ✅ Gmail account with API access ✅ OpenAI API Key ✅ PostgreSQL database with PGVector extension installed 🛠️ How to customize the workflow Email Filtering**: Change filters in the Gmail Trigger to watch specific labels or senders. Text Splitting Granularity**: Adjust chunkSize and chunkOverlap in the text splitter node. Query Depth**: Modify topK in the vector search node to retrieve more or fewer similar results. Prompt Tuning**: Customize the system message or agent instructions in the RAG node. Workflow Extensions**: Add notifications, error logging, Slack/Telegram alerts, or data exports.

7 nodes7 views

Create OpenAI-Compatible API Using GitHub Models for Free AI Access

by Jimleuk

This n8n template shows you how to connect Github's Free Models to your existing n8n AI workflows. Whilst it is possible to use HTTP nodes to access Github Models, The aim of this template is to use it with existing n8n LLM nodes - saves the trouble of refactoring! Please note, Github states their model APIs are not intended for production usage! If you need higher rate limits, you'll need to use a paid service. How it works The approach builds a custom OpenAI compatible API around the Github Models API - all done in n8n! First, we attach an OpenAI subnode to our LLM node and configure a new OpenAI credential. Within this new OpenAI credential, we change the "Base URL" to point at a n8n webhook we've prepared as part of this template. Next, we create 2 webhooks which the LLM node will now attempt to connect with: "models" and "chat completion". The "models" webhook simply calls the Github Model's "list all models" endpoint and remaps the response to be compatible with our LLM node. The "Chat Completion" webhook does a similar task with Github's Chat Completion endpoint. How to use Once connected, just open chat and ask away! Any LLM or AI agent node connected with this custom LLM subnode will send requests to the Github Models API. Allowing your to try out a range of SOTA models for free. Requirements Github account and credentials for access to Models. If you've used the Github node previously, you can reuse this credential for this template. Customising this workflow This template is just an example. Use the custom OpenAI credential for your other workflows to test Github models. References https://docs.github.com/en/github-models/prototyping-with-ai-models https://docs.github.com/en/github-models

Generate & Schedule Social Posts with Gemini/OpenAI for X and LinkedIn

by Nurseflow

💬Communication & Collaboration

💼 LinkedIn Content Machine – AI-Powered Post Generator & Scheduler for X and LinkedIn How it works: This end-to-end workflow automates your personal or brand content strategy by: 🧠 Using Google Gemini or OpenAI to generate engaging LinkedIn/X content from a title or trending posts. 🗓️ Posting directly to LinkedIn and X (formerly Twitter). 📊 Pulling high-performing LinkedIn posts to inspire new ideas. ✍️ Saving AI-generated drafts to Google Sheets for review. 🔔 Notifying your team on Slack when drafts are ready. Steps to set up: Add your API keys for Google Gemini or OpenAI. Set up your LinkedIn, X (Twitter), Google Sheets, and Slack credentials. Customize prompt logic or post filters if needed. Schedule the idea generation module or trigger it manually. Start generating and posting consistent, high-quality content with zero manual effort!

9 nodes4 views

Extract Structured Data from Medical Documents with Google Gemini AI

by Louis Chan

How it works Transform medical documents into structured data using Google Gemini AI with enterprise-grade accuracy. Classifies document types (receipts, prescriptions, lab reports, clinical notes) Extracts text with 95%+ accuracy using advanced OCR Structures data according to medical taxonomy standards Supports multiple languages (English, Chinese, auto-detect) Tracks processing costs and quality metrics automatically Set up steps Prerequisites Google Gemini API key (get from Google AI Studio) Quick setup Import this workflow template Configure Google Gemini API credentials in n8n Test with a sample medical document URL Deploy your webhook endpoint Usage Send POST request to your webhook: { "image_url": "https://example.com/medical-receipt.jpg", "expected_type": "financial", "language_hint": "auto" } Get structured response: json{ "success": true, "result": { "documentType": "financial", "metadata": { "providerName": "Dr. Smith Clinic", "createdDate": "2025-01-06", "currency": "USD" }, "content": { "amount": 150.00, "services": [...] }, "quality_metrics": { "overall_confidence": 0.95 } } } Use cases Healthcare Organizations Medical billing automation - Process receipts and invoices automatically Insurance claim processing - Extract data from claim documents Clinical documentation - Digitize patient records and notes Data standardization - Consistent structured output format System Integrators EMR integration - Connect with existing healthcare systems Workflow automation - Reduce manual data entry by 90% Multi-language support - Handle international medical documents Quality assurance - Built-in confidence scoring and validation Supported Document Types Financial: Medical receipts, bills, insurance claims, invoices Clinical: Medical charts, progress notes, consultation reports Prescription: Prescriptions, medication lists, pharmacy records Administrative: Referrals, authorizations, patient registration Diagnostic: Lab reports, test results, screening reports Legal: Medical certificates, documentation forms

Automate Instagram Content Discovery & Repurposing w/ Apify, GPT-4o & Perplexity

by Nick Saraev

This workflow creates an end-to-end Instagram content pipeline that automatically discovers trending content from competitor channels, extracts valuable insights, and generates new high-quality scripts for your own content creation. The system helped scale an Instagram channel from 0 to 10,000 followers in just 15 days through intelligent content repurposing. Benefits: Complete Content Automation - Monitors competitor Instagram accounts, downloads new reels, and processes them without manual intervention AI-Powered Script Generation - Uses ChatGPT and Perplexity to analyze content, identify tools/technologies, and rewrite scripts with fresh angles Smart Duplicate Prevention - Automatically tracks processed content in a database to avoid redundant work Multi-Platform Intelligence - Combines Instagram scraping, AI transcription, web research, and content generation in one seamless flow Scalable Content Strategy - Process content from multiple niches and creators to fuel unlimited content ideas Revenue-Focused Approach - Specifically designed to identify monetizable tools and technologies for business-focused content How It Works: Instagram Content Discovery: Uses Apify's Instagram scraper to monitor specified creator accounts for new reels Automatically downloads video content and metadata from target accounts Filters content based on engagement metrics and relevance Intelligent Processing Pipeline: Transcribes video content using OpenAI Whisper for accurate text extraction Filters content using AI to identify tools, technologies, and automation opportunities Cross-references against existing database to prevent duplicate processing Enhanced Research & Analysis: Searches Perplexity AI for additional insights about discovered tools Generates step-by-step usage guides and implementation instructions Identifies unique angles and opportunities for content improvement Script Generation & Optimization: Creates new, original scripts optimized for your specific audience Maintains consistent brand voice while adding fresh perspectives Includes strategic call-to-action elements for audience engagement Required Google Sheets Database Setup: Before running this workflow, create a Google Sheets database with these exact column headers: Essential Columns: id - Unique Instagram post identifier (primary key for duplicate detection) timestamp - When the reel was posted caption - Original reel caption text hashtags - Hashtags used in the post videoUrl - Direct link to download the video file username - Account that posted the reel scrapedTranscript - Original transcript from video (added by workflow) newTranscript - AI-generated script for your content (added by workflow) Additional Tracking Columns: shortCode - Instagram's internal post code url - Public Instagram post URL commentsCount - Number of comments firstComment - Top comment on the post likesCount - Number of likes videoViewCount - View count metrics videoDuration - Length of video in seconds Setup Instructions: Create a new Google Sheet with these column headers in the first row Name the sheet "Reels" Connect your Google Sheets OAuth credentials in n8n Update the document ID in the workflow nodes The merge logic relies on the id column to prevent duplicate processing, so this structure is essential for the workflow to function correctly. Business Use Cases: Content Creators - Scale content production by 10x while maintaining quality and originality Marketing Agencies - Offer content research and ideation as a premium service Course Creators - Identify trending tools and technologies for educational content Revenue Potential: This exact system can be sold as a service for $3,000-$5,000 to growing channels or agencies. The automation saves 10+ hours weekly of manual research and content planning. Difficulty Level: Intermediate Estimated Build Time: 1-2 hours Monthly Operating Cost: ~$30 (API usage) Watch the Complete Build Process Want to see exactly how this system was built from scratch? Nick Saraev walks through the entire development process in this comprehensive tutorial, including all the debugging, dead ends, and problem-solving that goes into building real automation systems. 🎥 Watch: "The N8N Instagram Parasite System (10K Followers In 15 Days)" This 1.5-hour deep-dive shows the actual build process - not a polished demo, but real system development with all the thinking and iteration included. Set Up Steps: Configure Apify Integration: Sign up for Apify account and obtain API key Replace the bearer token in the "Run Actor Synchronously" node Customize the username array with your target Instagram accounts Set Up AI Services: Add OpenAI API credentials for transcription and content generation Configure Perplexity API for enhanced research capabilities Set up appropriate rate limiting for cost control Database Configuration: Create Google Sheets database with provided column structure Connect Google Sheets OAuth credentials Configure the merge logic for duplicate detection Content Filtering Setup: Customize the AI prompts for your specific niche and requirements Adjust the filtering criteria for tool/technology detection Set up the script generation template to match your brand voice Automation Schedule: Configure the schedule trigger for daily content monitoring Set optimal timing based on your content creation workflow Test the complete flow with a small number of accounts first Advanced Customization: Add additional content sources beyond Instagram Integrate with your existing content management systems Scale up monitoring to dozens of competitor accounts More AI Automation Systems:* For more advanced automation tutorials and business systems, check out My YouTube Channel where I share proven automation strategies that generate real revenue.

Build your own Google Drive MCP server

by Jimleuk

This n8n demonstrates how to build a simple Google Drive MCP server to search and get contents of files from Google Drive. This MCP example is based off an official MCP reference implementation which can be found here -https://github.com/modelcontextprotocol/servers/tree/main/src/gdrive How it works A MCP server trigger is used and connected to 1x Google Drive tool and 1x Custom Workflow tool. The Google Drive tool is set to perform a search on files within our Google Drive folder. The Custom Workflow tool downloads target files found in our drive and converts the binaries to their text representation. Eg. PDFs have only their text contents extracted and returned to the MCP client. How to use This Google Drive MCP server allows any compatible MCP client to manage a person or shared Google Drive. Simple select a drive or for better control, specify a folder within the drive to scope the operations to. Connect your MCP client by following the n8n guidelines here - https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-langchain.mcptrigger/#integrating-with-claude-desktop Try the following queries in your MCP client: "Please help me search for last month's expense reports." "What does the company policy document say about cancellations and refunds?" Requirements Google Drive for documents. OpenAI for image and audio understanding. MCP Client or Agent for usage such as Claude Desktop - https://claude.ai/download Customising this workflow Add additional capabilities such as renaming, moving and/or deleting files. Remember to set the MCP server to require credentials before going to production and sharing this MCP server with others!

Automated Bulk Cold Email Sender using Gmail, SMTP and Google Sheets

by Gain FLow AI

💬Communication & Collaboration

Overview This workflow automates the process of sending personalized cold email sequences to your prospects. It fetches un-emailed leads from your Google Sheet, validates their email addresses, and then dispatches tailored emails according to a predefined schedule. It updates your CRM (Google Sheet) with the status of each sent email, ensuring your outreach efforts are tracked and efficient. Use Case This workflow is perfect for: Sales Teams**: Automate the delivery of multi-stage cold email campaigns to a large volume of leads. Business Development**: Nurture prospects over time with a structured email sequence. Recruiters**: Send out introductory emails to potential candidates for open positions. Marketers**: Distribute personalized outreach for events, content, or product launches. Anyone doing cold outreach**: Ensure consistent follow-up and track email performance without manual effort. How It Works Scheduled Trigger: The workflow is set to run automatically at a defined interval (e.g., every 6 hours, as currently configured by the "Set Timer" node). This ensures regular outreach without manual intervention. Fetch Unsent Emails: The "Get Emails" node queries your Google Sheet to identify prospects who haven't yet received the current email in the sequence (i.e., "Email Sent " is "No"). Control Volume: A "Limit" node can be used to control the number of emails sent in each batch, preventing you from sending too many emails at once and potentially hitting sending limits. Loop Through Prospects: The "Loop Over Items" node processes each selected prospect individually. Email Validation (Conditional Send): An "If" node checks if the prospect's "Email Address" is valid and exists. This prevents sending emails to invalid addresses, improving deliverability. Send Email: "Send Email" Node: For valid email addresses, this node dispatches the personalized email to the prospect. It retrieves the recipient's email, subject, and body from your Google Sheet. "connect" Node: (Note: The provided JSON uses a generic emailSend node named "connect" that links to an SMTP credential. This represents the actual email sending mechanism, whether it's Gmail or a custom SMTP server.) Update CRM: After successfully sending an email, the "Update Records" node updates your Google Sheet. It marks the "Email Sent " column as "Yes" and records the "Sent on" timestamp and a "Message Id" for tracking. Delay Between Sends: A "Wait" node introduces a delay between sending emails to individual prospects. This helps mimic human sending behavior and can improve deliverability. How to Set It Up To set up your Automated Cold Email Sender, follow these steps: Google Sheet Setup: Duplicate the Provided Template: Make a copy of the Google Sheet Template (1TjXelyGPg5G8lbPDI9_XOReTzmU1o52z2R3v8dYaoQM) into your own Google Drive. This sheet should contain columns for "Name", "Email Address ", "Sender Email", "Email Subject", "Email Body", "Email Sent ", "Sent on", and "Message Id". Connect Google Sheets: Ensure your Google Sheets OAuth2 API credentials are set up in n8n and linked to the "Get Emails" and "Update Records" nodes. Update Sheet IDs: In both "Get Emails" and "Update Records" nodes, update the documentId with the ID of your copied template. Email Sending Service Credentials: Gmail: If using Gmail, ensure your Gmail OAuth2 credentials are configured and connected to the "Send Email" node (or the "connect" node, if that's your chosen sender). Other Email Services (SMTP): If you use a different email service, you'll need to set up an SMTP credential in n8n and connect it to the "connect" node. Refer to the "Sticky Note4" for guidance on non-Google email services. Configure Timer: In the "Set Timer" node, adjust the hoursInterval or other time settings to define how frequently you want the email sending process to run (e.g., every 6 hours, once a day, etc.). Control Volume (Optional): In the "Limit" node, you can set the maxItems to control how many emails are processed and sent in each batch. This is useful for managing email sending limits or gradual outreach. Import the Workflow: Import the provided workflow JSON into your n8n instance. Populate Your Sheet: Fill your copied Google Sheet with prospect data, including the email subject and body for each email you wish to send. Ensure the "Email Sent " column is initially "No". Activate and Monitor: Activate the workflow. It will begin fetching and sending emails based on your configured schedule. Monitor your Google Sheet to track the "Email Sent " status. This workflow provides a robust and automated solution for managing your cold email campaigns, saving you time and increasing your outreach efficiency.

beginner

3 nodes

Medical Q&A Chatbot for Urology using RAG with Pinecone and GPT-4o

by HoangSP

Medical Q&A Chatbot for Urology using RAG with Pinecone and GPT-4o This template provides an AI-powered Q&A assistant for the Urology domain using Retrieval-Augmented Generation (RAG). It uses Pinecone for vector search and GPT-4o for conversational responses. 🧠 Use Case This chatbot is designed for clinics or medical pages that want to automate question answering for Urology-related conditions. It uses a vector store of domain knowledge to return verified responses. 🔧 Requirements ✅ OpenAI API key (GPT-4o or GPT-4o-mini) ✅ Pinecone account with an active index ✅ Verified Urology documents embedded into Pinecone ⚙️ Setup Instructions Create a Pinecone vector index and connect it using the Pinecone credentials node. Upload Urology-related documents to embed using the Create Embeddings for Urology Docs node. Customize the chatbot system message to reflect your medical specialty. Deploy this chatbot on your website or link it with Telegram via the chat trigger node. 🛠️ Components chatTrigger: Listens for user messages and starts the workflow. Medical AI Agent: GPT-based agent guided by domain-specific instructions. RAG Tool Vector Store: Fetches relevant documents from Pinecone using vector search. Memory Buffer: Maintains conversation context. Create Embeddings for Urology Docs: Encodes documents into vector format. 📝 Customization You can replace the knowledge base with any other medical domain by: Updating the documents stored in Pinecone. Modifying the system prompt in the AI Agent node. 📣 CTA This chatbot is ideal for clinics, medical consultants, or educational websites wanting a reliable AI assistant in Urology.

🤖AI & Machine Learning

6 nodes2637 views

Web Site Scraper for LLMs with Airtop

by Airtop

Recursive Web Scraping Use Case Automating web scraping with recursive depth is ideal for collecting content across multiple linked pages—perfect for content aggregation, lead generation, or research projects. What This Automation Does This automation reads a list of URLs from a Google Sheet, scrapes each page, stores the content in a document, and adds newly discovered links back to the sheet. It continues this process for a specified number of iterations based on the defined scraping depth. Input Parameters: Seed URL: The starting URL to begin the scraping process. Example: https://example.com/ Links must contain: Restricts the links to those that contain this specified string. Example: https://example.com/ Depth: The number of iterations (layers of links) to scrape beyond the initial set. Example: 3 How It Works Starts by reading the Seed URL from the Google Sheet. Scrapes each page and saves its content to the specified document. Extracts new links from each page that match the Links must contain string, appends them to the Google Sheet. Repeats steps 2–3 for the number of times specified by Depth - 1. Setup Requirements Airtop API Key — free to generate. Credentials set up for Google Docs (requires creating a project on Google Console). Read how to. Credentials set up for Google Spreadsheet. Next Steps Add Filtering Rules**: Filter which links to follow based on domain, path, or content type. Combine with Scheduler**: Run this automation on a schedule to continuously explore newly discovered pages. Export Structured Data**: Extend the process to store extracted data in a CSV or database for analysis. Read more about website scraping for LLMS

Extract Person Data and Calculate ICP Score with Airtop

by Airtop

Automating LinkedIn Enrichment and ICP Scoring Use Case This automation enriches a person’s data using LinkedIn and calculates an Ideal Customer Profile (ICP) score based on their professional presence. It is particularly useful for lead qualification, contact research, and targeted outreach. What This Automation Does The automation processes the following input parameters: Person Name**: Full name of the individual. Work Email**: Business email address to validate corporate identity. Airtop Profile (connected to Linkedin)**: A LinkedIn-authenticated Airtop Profile for enrichment. How It Works Email Filtering: Checks if the email is corporate (excludes free and personal domains). LinkedIn Profile Discovery: Searches and verifies the correct LinkedIn URL using Airtop. Data Enrichment: Extracts professional details from the LinkedIn profile. ICP Scoring: Calculates an ICP score based on extracted data and profile context. Merge Outputs: Consolidates enriched profile data and ICP results into a single output. Setup Requirements Airtop API Key An Airtop Profile authenticated on LinkedIn. Next Steps Combine with CRM Integration**: Push enriched and scored data into CRMs like HubSpot or Salesforce. Batch Processing**: Automate for lists of leads using Airtop + n8n or Airtop SDK. Scoring Customization**: Adjust scoring logic to reflect your ideal customer attributes more precisely. Read more about data enrichment and ICP scoring

⚙️Business Automation

beginner

0 nodes167 views

Evaluation metric example: Categorization

by David Roberts

AI evaluation in n8n This is a template for n8n's evaluation feature. Evaluation is a technique for getting confidence that your AI workflow performs reliably, by running a test dataset containing different inputs through the workflow. By calculating a metric (score) for each input, you can see where the workflow is performing well and where it isn't. How it works This template shows how to calculate a workflow evaluation metric: whether a category matches the expected one. The workflow takes support tickets and generates a category and priority, which is then compared with the correct answers in the dataset. We use an evaluation trigger to read in our dataset It is wired up in parallel with the regular trigger so that the workflow can be started from either one. More info Once the category is generated by the agent, we check whether it matches the expected one in the dataset Finally we pass this information back to n8n as a metric

🤖AI & Machine Learning