Workflow Templates

Enterprise Knowledge Search with GPT-4 Turbo, Google Drive & Academic APIs This workflow provides an enterprise-grade RAG (Retrieval-Augmented Generation) system that intelligently searches multiple sources and generates AI-powered responses using GPT-4 Turbo. How it works This workflow provides an enterprise-grade RAG (Retrieval-Augmented Generation) system that intelligently searches multiple sources and generates AI-powered responses using GPT-4 Turbo. Key Steps Form Input - Collects user queries with customizable search scope, response style, and language preferences Intelligent Search - Routes queries to appropriate sources (web, academic papers, news, internal documents) Data Aggregation - Unifies and processes information from multiple sources with quality scoring AI Processing - Uses GPT-4 Turbo to generate context-aware, source-grounded responses Response Enhancement - Formats outputs in various styles (comprehensive, concise, technical, etc.) Multi-Channel Delivery - Delivers results via webhook, email, Slack, and optional PDF generation Data Sources & AI Models Search Sources Web Search**: Google, Bing, DuckDuckGo integration Academic Papers**: arXiv, PubMed, Google Scholar via Crossref API News Articles**: News API, RSS feeds, real-time news Technical Documentation**: GitHub, Stack Overflow, documentation sites Internal Knowledge**: Google Drive, Confluence, Notion integration AI Models GPT-4 Turbo**: Primary language model for response generation Embedding Models**: For semantic search and similarity matching Custom Prompts**: Specialized prompts for different response styles Set up steps Setup time: 15-20 minutes Configure API credentials - Set up OpenAI API, News API, Google Drive, and other service credentials Set up search sources - Configure academic databases, news APIs, and internal knowledge sources Connect analytics - Link Google Sheets for usage tracking and performance monitoring Configure notifications - Set up Slack channels and email templates for automated alerts Test the workflow - Run sample queries to verify all components are working correctly Keep detailed configuration notes in sticky notes inside your workflow

Description Automate the discovery and analysis of PDF files across a deeply nested OneDrive folder structure. This workflow recursively searches folders, filters for new or updated PDFs, extracts text, and uses a Mistral AI agent to generate a concise Executive Summary, Key Findings, and Structured Metadata (Date, Location, etc.), storing all insights into a n8n Data Table for easy access and further automation. Key Features & How It Works Scheduled Trigger & Recursive Folder Search: The workflow runs automatically (scheduled for 8 PM in this template) to monitor a specified main folder on OneDrive. It performs a deep, multi-level search (up to 8 layers) across subfolders to ensure no documents are missed. Smart Deduplication & Filtering: It checks new files against an internal n8n Data Table using the Compare Datasets node, ensuring only new or unique PDF files are processed, saving AI credits and processing time. A size check is also included, preventing attempts to process excessively large files. AI-Powered Document Intelligence (Mistral LLM): For each new PDF, the workflow extracts the text and passes it to a Mistral AI model for dual-stream analysis: Overview Agent: Generates an impartial, professional Executive Summary, a list of Key Findings & Data Points, and the document's Scope/Context. Document Information Agent: Extracts crucial metadata, including the single most relevant date, location (City/State/Country), and professional information (Name, Title, Organization). Structured Output and Archiving: AI outputs are meticulously validated and reformatted into a clean JSON object using Structured Output Parsers. The complete analysis, along with the original file name and path, is then logged as a new row in an n8n Data Table. Setup Notes OneDrive Folder: You must specify the exact name of your main folder in the 'Search for Main Folder' node. Data Table: Ensure your n8n Data Table exists with the required columns: Summary, Key_Findings, Scope, Date, Location, File_Name, and Path. Deep Folder Structure: The current configuration supports up to 8 levels of subfolders. If your files go deeper, you may need to add more "Get items in a folder" and "If" nodes. AI Customization: Review the AI agent prompts and the structured output schemas to customize the fields you want to extract or the summary style you require. Extend This Workflow The final output is organized data. You can easily extend this workflow to: Send daily/weekly digest emails with new summaries. Sync the extracted data to a Google Sheet, Airtable, or other database. Add a secondary AI agent to perform follow-up actions based on the "Key Findings."

Description Automates the forwarding of messages from WhatsApp (via Evolution API) to Chatwoot, enabling seamless integration between external WhatsApp users and internal Chatwoot agents. It supports both text and media messages, ensuring that customer conversations are centralized and accessible for support teams. What Problem Does This Solve? Managing conversations across multiple platforms can lead to fragmented support and lost context. This subworkflow bridges the gap between WhatsApp and Chatwoot, automatically forwarding messages received via the Evolution API to a Chatwoot inbox. It simplifies communication flow, centralizes conversations, and enhances the support team's productivity. Features Support for plain text messages Support for media messages: images, videos, documents, and audio Automatic media upload to Chatwoot with proper attachment rendering Automatic contact association using WhatsApp number and Chatwoot API Designed to work with Evolution API webhooks or any message source Prerequisites Before using this automate, make sure you have: Evolution API credentials with incoming message webhook configured A Chatwoot instance with access token and API endpoint An existing Chatwoot inbox (preferably API channel) A configured HTTP Request node in n8n for Chatwoot API calls Suggested Usage This subworkflow should be attached to a parent workflow that receives WhatsApp messages via the Evolution API webhook. Ideal for: Centralized customer service operations WhatsApp-to-CRM/chat routing Hybrid automation workflows where human agents need to reply from Chatwoot It ensures that all incoming WhatsApp messages are properly converted and forwarded to Chatwoot, preserving message content and structure.

Overview Healthcare organizations face significant challenges in digitizing and processing medical records while maintaining strict HIPAA compliance. This workflow provides a secure, automated solution for extracting clinical data from various medical documents including discharge summaries, lab reports, clinical notes, prescription records, and scanned medical images (JPG, PNG). What You Can Do Extract clinical data from medical documents while maintaining HIPAA compliance Process handwritten notes and scanned medical images with OCR Automatically identify and protect PHI (Protected Health Information) Generate structured data from various medical document formats Maintain audit trails for regulatory compliance Who It's For Healthcare providers, medical billing companies, clinical research organizations, health information exchanges, and medical practice administrators who need to digitize and extract data from medical records while maintaining HIPAA compliance. The Problem It Solves Manual medical record processing is time-consuming, error-prone, and creates compliance risks. Healthcare organizations struggle to extract structured data from handwritten notes, scanned documents, and various medical forms while protecting PHI. This template automates the extraction process while maintaining the highest security standards for Protected Health Information. Setup Instructions: Configure Google Drive credentials with proper medical record access controls Install the PDF Vector community node from the n8n marketplace Configure PDF Vector API credentials with HIPAA-compliant settings Set up secure database storage with encryption at rest Define PHI handling rules and extraction parameters Configure audit logging for regulatory compliance Set up integration with your Electronic Health Record (EHR) system Key Features: Secure retrieval of medical documents from Google Drive HIPAA-compliant processing with automatic PHI masking OCR support for handwritten notes and scanned medical images Automatic extraction of diagnoses with ICD-10 code validation Medication list processing with dosage and frequency information Lab results extraction with reference ranges and flagging Vital signs capture and normalization Complete audit trail for regulatory compliance Integration-ready format for EHR systems Customization Options: Define institution-specific medical terminology and abbreviations Configure automated alerts for critical lab values or abnormal results Set up custom extraction fields for specialized medical forms Implement medication interaction warnings and contraindication checks Add support for multiple languages and international medical coding systems Configure integration with specific EHR platforms (Epic, Cerner, etc.) Set up automated quality assurance checks and validation rules Implementation Details: The workflow uses advanced AI with medical domain knowledge to understand clinical terminology and extract relevant information while automatically identifying and protecting PHI. It processes various document formats including handwritten prescriptions, lab reports, discharge summaries, and clinical notes. The system maintains strict security protocols with encryption at rest and in transit, ensuring full HIPAA compliance throughout the processing pipeline. Note: This workflow uses the PDF Vector community node. Make sure to install it from the n8n community nodes collection before using this template.

Collaborate with an AI Agent on a joint document, e.g. for creating your content marketing strategy, a sales plan, project status updates, or market analysis. The AI Agent generates markdown text that you can review and edit it in gotoHuman, and only then is the existing Google Doc updated. In this example we use AI to update our company's content strategy for the next quarter. How It Works The AI Agent has access to other documents that provide enough context to write the content strategy. We ask it to generate the text in markdown format. To ensure our strategy document is not changed without our approval, we request a human review using gotoHuman. There the markdown content can be edited and properly previewed. Our workflow resumes once the review is completed. We check if the content was approved and then write the (potentially edited) markdown to our Google Docs file via the Google Drive node. How to set up Most importantly, install the verified gotoHuman node before importing this template! (Just add the node to a blank canvas before importing. Works with n8n cloud and self-hosted) Set up your credentials for gotoHuman, OpenAI, and Google Docs/Drive In gotoHuman, select and create the pre-built review template "Strategy agent" or import the ID: F4sbcPEpyhNKBKbG9C1d Select this template in the gotoHuman node Requirements You need accounts for gotoHuman (human supervision) OpenAI (Doc writing) Google Docs/Drive How to customize Let the workflow run on a schedule, or create and connect a manual trigger in gotoHuman that lets you capture additional human input to feed your agent Provide the agent with more context to write the content strategy Use the gotoHuman response (or a Google Drive file change trigger) to run additional AI agents that can execute on the new strategy

✅ What problem does this workflow solve? Sending a plain PDF resume doesn’t stand out anymore. This workflow allows candidates to convert their resume and photo into a personalized video resume. Recruiters get a more engaging first impression, while candidates showcase their profile in a modern, impactful way. ⚙️ What does this workflow do? Presents a form for uploading: 📄 Resume (PDF) 🖼 Photo (headshot) Extracts key details from the resume (education, experience, skills). Detects gender from the photo to choose a suitable voice/avatar. Generates a script (spoken resume summary) based on the extracted information. Uploads the photo to HeyGen to create an avatar. Requests video generation on HeyGen: Uses the avatar photo Uses gender-specific settings Uses the generated script as narration Monitors video generation status until completion. Stores the final video URL in a Google Sheet for easy access and tracking. 🔧 Setup Instructions Google Services Connect Google Sheets to n8n to store records with: Candidate name Resume link Video link HeyGen Setup Get an API key from HeyGen. Configure: Avatar upload endpoint (image upload) Video generation endpoint (image ID + script) Form Setup Use the n8n Form Trigger to allow candidates to upload: Resume (PDF) Photo (JPEG/PNG) 🧠 How it Works – Step-by-Step 1. Candidate Submission A candidate fills out a form and uploads: Resume (PDF) Photo 2. Extract Resume Data The resume PDF is processed using OCR/AI to extract: Name Experience Skills Education highlights 3. Gender Detection The uploaded photo is analyzed to detect gender (used for voice/avatar selection). 4. Script Generation Based on the extracted resume info, a concise, natural script is generated automatically. 5. Avatar Upload & Video Creation The photo is uploaded to HeyGen to create a custom avatar. A video generation request is made using: The script The avatar (image ID) A matching voice for the detected gender 6. Video Status Monitoring The workflow polls HeyGen’s API until the video is ready. 7. Save Final Video URL Once complete, the video link is added to a Google Sheet alongside the candidate’s details. 👤 Who can use this? This workflow is ideal for: 🧑‍🎓 Students and job seekers looking to stand out 🧑‍💼 Recruitment agencies offering modern resume services 🏢 HR teams wanting engaging candidate submissions 🎥 Portfolio builders for professionals 🚀 Impact Instead of a static PDF, you can now send a dynamic video resume that captures attention, adds personality, and makes a lasting impression.

Harness OpenAI's Sora 2 for instant video creation from text or images using fal.ai's API—powered by GPT-5 for refined prompts that ensure cinematic quality. This template processes form submissions, intelligently routes to text-to-video (with mandatory prompt enhancement) or image-to-video modes, and polls for completion before redirecting to your generated clip. 📋 What This Template Does Users submit prompts, aspect ratios (9:16 or 16:9), models (sora-2 or pro), durations (4s, 8s, or 12s), and optional images via a web form. For text-to-video, GPT-5 automatically refines the prompt for optimal Sora 2 results; image mode uses the raw input. It calls one of four fal.ai endpoints (text-to-video, text-to-video/pro, image-to-video, image-to-video/pro), then loops every 60s to check status until the video is ready. Handles dual modes: Text (with GPT-5 enhancement) or image-seeded generation Supports pro upgrades for higher fidelity and longer clips Auto-uploads images to a temp host and polls asynchronously for hands-free results Redirects directly to the final video URL on completion 🔧 Prerequisites n8n instance with HTTP Request and LangChain nodes enabled fal.ai account for Sora 2 API access OpenAI account for GPT-5 prompt refinement 🔑 Required Credentials fal.ai API Setup Sign up at fal.ai and navigate to Dashboard → API Keys Generate a new key with "sora-2" permissions (full access recommended) In n8n, create "Header Auth" credential: Name it "fal.ai", set Header Name to "Authorization", Value to "Key [Your API Key]" OpenAI API Setup Log in at platform.openai.com → API Keys (top-right profile menu) Click "Create new secret key" and copy it (store securely) In n8n, add "OpenAI API" credential: Paste key, select GPT-5 model in the LLM node ⚙️ Configuration Steps Import the workflow JSON into your n8n instance via Settings → Import from File Assign fal.ai and OpenAI credentials to the relevant HTTP Request and LLM nodes Activate the workflow—the form URL auto-generates in the trigger node Test by submitting a sample prompt (e.g., "A cat chasing a laser"); monitor executions for video output Adjust polling wait (60s node) for longer generations if needed 🎯 Use Cases Social Media Teams**: Generate 9:16 vertical Reels from text ideas, like quick product animations enhanced by GPT-5 for professional polish Content Marketers**: Animate uploaded images into 8s promo clips, e.g., turning a static ad graphic into a dynamic story for email campaigns Educators and Trainers**: Create 4s explainer videos from outlines, such as historical reenactments, using pro mode for detailed visuals App Developers**: Embed as a backend service to process user prompts into Sora 2 videos on-demand for creative tools ⚠️ Troubleshooting API quota exceeded**: Check fal.ai dashboard for usage limits; upgrade to pro tier or extend polling waits Prompt refinement fails**: Ensure GPT-5 credential is set and output matches JSON schema—test LLM node independently Image upload errors**: Confirm file is JPG/PNG under 10MB; verify tmpfiles.org endpoint with a manual curl test Endless polling loop**: Add an IF node after 10 checks to timeout; increase wait to 120s for 12s pro generations

The Prompt converter workflow tackles the challenge of turning your natural language video ideas into perfectly formatted JSON prompts tailored for Veo 3 video generation. By leveraging Langchain AI nodes and Google Gemini, this workflow automates and refines your input to help you create high-quality videos faster and with more precision—think of it as your personal video prompt translator that speaks fluent cinematic! 💡 Why Use Prompt Converter? Save time: Automate converting complex video prompts into structured JSON, cutting manual formatting headaches and boosting productivity. Avoid guesswork: Eliminate unclear video prompt details by generating detailed, cinematic descriptions that align perfectly with Veo 3 specs. Improve output quality: Optimize every parameter for Veo 3's video generation model to get realistic and stunning results every time. Gain a creative edge: Turn vague ideas into vivid video concepts with AI-powered enhancement—your video project's secret weapon. ⚡ Perfect For Video creators: Content developers wanting quick, precise video prompt formatting without coding hassles. AI enthusiasts: Developers and hobbyists exploring Langchain and Google Gemini for media generation. Marketing teams: Professionals creating video ads or visuals who need consistent prompt structuring that saves time. 🔧 How It Works ⏱ Trigger: User submits a free text prompt via message or webhook. 📎 Process: The text goes through an AI model that understands and reworks it into detailed JSON parameters tailored for Veo 3. 🤖 Smart Logic: Langchain nodes parse and optimize the prompt with cinematic details, set reasonable defaults, and structure the data precisely. 💌 Output: The refined JSON prompt is sent to Google Gemini for video generation with optimized settings. 🔐 Quick Setup Import the JSON file to your n8n instances Add credentials: Azure OpenAI, Gemini API, OpenRouter API Customize: Adjust prompt templates or default parameters in the Prompt converter node Test: Run your workflow with sample text prompts to see videos come to life 🧩 You'll Need Active n8n instances Azure OpenAI API Gemini API Key OpenRouter API (alternative AI option) 🛠️ Level Up Ideas Add integration with video hosting platforms to auto-upload generated videos 🧠 Nodes Used Prompt Input** (Chat Trigger) OpenAI** (Azure OpenAI GPT model) Alternative** (OpenRouter API) Prompt converter** (Langchain chain LLM for JSON conversion) JSON parser** (structured output extraction) Generate a video** (Google Gemini video generation) Made by: Khaisa Studio Tags: video generation, AI, Langchain, automation, Google Gemini Category: Video Production Need custom work? Contact me

Automated TikTok Repurposing & Video Generation Workflow Who’s it for This workflow is designed for content creators, social media managers, and marketers—specifically those in the career, recruitment, or "job change" (転職/就職) niches. It is ideal for anyone looking to automate the process of finding trending short-form content concepts and converting them into fresh AI-generated videos. How it works / What it does This workflow automates the pipeline from content research to video creation: Scrape Data: It triggers an Apify actor (clockworks/tiktok-scraper) to search and scrape TikTok videos related to "Job Change" (転職) and "Employment" (就職). Store Raw Data: It saves the scraped TikTok metadata (text, stats, author info) into a Google Sheet. AI Analysis & Prompting: An AI Agent (via OpenRouter) analyzes the scraped video content and creates a detailed prompt for a new video (concept, visual cues, aspect ratio). Log Prompts: The generated prompt is saved to a separate tab in the Google Sheet. Video Generation: The prompt is sent to Fal AI (Veo3 model) to generate a new 8-second, vertical (9:16) video with audio. Wait & Retrieve: The workflow waits for the generation to complete, then retrieves the video file. Cloud Storage: Finally, it uploads the generated video file to a specific Google Drive folder. How to set up Credentials: Configure the following credentials in n8n: Apify API: (Currently passed via URL query params in the workflow, recommended to switch to Header Auth). Google Sheets OAuth2: Connect your Google account. OpenRouter API: For the AI Agent. Fal AI (Header Auth): For the video generation API. Google Drive OAuth2: For uploading the final video. Google Sheets: Create a spreadsheet. Note the documentId and update the Google Sheets nodes. Ensure you have the necessary Sheet names (e.g., "シート1" for raw data, "生成済み" for prompts) and columns mapped. Google Drive: Create a destination folder. Update the Upload file node with the correct folderId. Apify: Update the token in the HTTP Request and HTTP Request1 URLs with your own Apify API token. Requirements n8n Version:** 1.x or higher (Workflow uses version 4.3 nodes). Apify Account:** With access to clockworks/tiktok-scraper and sufficient credits. Fal.ai Account:** With credits for the fal-ai/veo3 model. OpenRouter Account:** With credits for the selected LLM. Google Workspace:** Access to Drive and Sheets. How to customize the workflow Change the Niche:* Update the searchQueries JSON body in the first *HTTP Request** node (e.g., change "転職" to "Cooking" or "Fitness"). Adjust AI Logic:* Modify the *AI Agent** system prompt to change the style, tone, or structure of the video prompts it generates. Video Settings:* In the *Fal Submit** node, adjust bodyParameters to change the duration (e.g., 5s), aspect ratio (e.g., 16:9), or disable audio. Scale:* Increase the amount in the *Limit** node to process more than one video per execution.

Super simple workflow to convert image URLs to an uploaded attachment in Airtable. You'll need to adjust the field names to match your specific data, including in the filter formula where it says "Cover image URL". Just replace that with the field name where you are storing the image URL.

This is an example of how you can make Merge by Key work. The “Data 1” and “Data 2” nodes simply provide mock data. You can replace them with your own data sources. Then the “Convert Data” nodes are important. They make sure that the different array items are actually different items in n8n. After that, you have then the merge with the merged data.

Video Processing Pipeline with Thumbnail Generation and CDN Distribution Summary Automated video processing system that monitors S3 for new uploads, generates thumbnails and preview clips, extracts metadata, transcodes to multiple formats, and distributes to CDN with webhook notifications. Detailed Description A comprehensive video processing workflow that receives S3 events or manual triggers, validates video files, extracts metadata via FFprobe, generates thumbnails at key frames, creates animated GIF previews, transcodes to multiple resolutions, invalidates CDN cache, and sends completion notifications. Key Features S3 Event Monitoring**: Automatic detection of new video uploads Thumbnail Generation**: Multiple sizes at key frame intervals Video Metadata**: FFprobe extraction of duration, resolution, codec info Preview GIF**: Animated preview clips for video galleries Multi-Format Transcoding**: Convert to 1080p, 720p, 480p CDN Distribution**: Cloudflare cache invalidation and signed URLs Webhook Callbacks**: Notify origin system on completion Use Cases Video hosting platforms Media asset management systems Content delivery networks Video streaming services Social media platforms E-learning video processing User-generated content platforms Required Credentials AWS S3 Credentials (for video storage) FFmpeg API credentials (via HTTP) Cloudflare API Token (for CDN) Slack Bot Token (for notifications) Google Sheets OAuth (for logging) Node Count: 24 (19 functional + 5 sticky notes) Unique Aspects Uses Webhook for S3 event notifications Uses Code nodes for S3 info extraction and URL generation Uses If node for video format validation Uses HTTP Request nodes for FFprobe, FFmpeg, and CDN APIs Uses Aggregate node for collecting parallel processing results Uses Merge nodes for multiple workflow path consolidation Implements parallel processing for thumbnails, GIF, and transcoding Workflow Architecture [S3 Event Webhook] [Manual Webhook] | | +--------+----------+ | v [Merge Triggers] | v [Extract S3 Info] (Code) | v [Check Is Video] (If) / \ Yes No | | v v [Get Video Metadata] [Invalid Response] (FFprobe) | | | v | [Parse Video Metadata] | (Code) | /|\ | / | \ | v v v | Thumbs[Transcode] | \ | / | \ | / | v v | [Aggregate Results] | | | v | [Invalidate CDN Cache] | | | v | [Generate Signed URLs] | / \ | / \ | v v | [Log Sheet] [Slack] | \ / | \ / | v | [Merge Output Paths] | | | +---------+-------+ | v [Merge All Paths] | v [Respond to Webhook] Configuration Guide S3 Event: Configure S3 bucket notification to send events to webhook FFmpeg API: Use a hosted FFmpeg service (e.g., api.ffmpeg-service.com) Cloudflare: Set zone ID and API token for cache invalidation Slack Channel: Set #video-processing for notifications Google Sheets: Connect for processing metrics logging Supported Video Formats | Extension | MIME Type | |-----------|----------| | .mp4 | video/mp4 | | .mov | video/quicktime | | .avi | video/x-msvideo | | .mkv | video/x-matroska | | .webm | video/webm | | .m4v | video/x-m4v | Thumbnail Generation | Size | Dimensions | Suffix | |------|------------|--------| | Large | 1280x720 | _large | | Medium | 640x360 | _medium | | Small | 320x180 | _small | Thumbnails generated at: 10%, 30%, 50%, 70%, 90% of video duration Transcoding Presets | Preset | Resolution | Bitrate | Codec | |--------|------------|---------|-------| | 1080p | 1920x1080 | 5000k | H.264 | | 720p | 1280x720 | 2500k | H.264 | | 480p | 854x480 | 1000k | H.264 | Output Structure { "job_id": "job_1705312000_abc123", "status": "completed", "original": { "filename": "video.mp4", "resolution": "1920x1080", "duration": "00:05:30" }, "thumbnails": { "large": "https://cdn/thumbnails/job_id/thumb_0_large.jpg", "medium": "https://cdn/thumbnails/job_id/thumb_0_medium.jpg", "small": "https://cdn/thumbnails/job_id/thumb_0_small.jpg" }, "preview_gif": "https://cdn/previews/job_id/preview.gif", "transcoded": { "1080p": "https://cdn/transcoded/job_id/video_1080p.mp4", "720p": "https://cdn/transcoded/job_id/video_720p.mp4", "480p": "https://cdn/transcoded/job_id/video_480p.mp4" } } `