by Don Jayamaha Jr
Analyze exchange data, market indexes, and community sentiment from CoinMarketCap—powered by AI. This sub-agent provides access to exchange listings, token holdings, metadata, and high-level metrics like the CMC 100 Index and the Fear & Greed Index. It’s designed for use within your larger CoinMarketCap AI Analyst system or as a standalone workflow. This agent can be triggered by a supervisor or manually used with message and sessionId inputs. Supported Tools (5 Total) 🔍 Exchange Map Get CoinMarketCap IDs, names, and slugs for exchanges (used as lookup before deeper queries). 🧾 Exchange Info Metadata including launch date, social links, country, and operational status. 💰 Exchange Assets Token balances, wallet addresses, and total USD value held by a specific exchange. 📈 CoinMarketCap 100 Index Constituents and weights of the CMC 100 Index, updated live. 😱 Fear & Greed Index Market sentiment score updated daily, ranging from Extreme Fear to Extreme Greed. What You Can Do with This Agent 🔹 Map exchanges to retrieve their ID and slug 🔹 Analyze exchange holdings by token and blockchain 🔹 Pull metadata for major CEXs like Binance or Coinbase 🔹 Compare global sentiment using the Fear & Greed Index 🔹 Access index data to understand CMC’s top 100 crypto asset breakdown Example Queries You Can Use ✅ "What is the latest Fear and Greed Index reading?" ✅ "Get a list of all exchanges on CoinMarketCap." ✅ "What tokens are held by Binance?" ✅ "Retrieve metadata for Coinbase." ✅ "Show me the top assets in the CMC 100 Index." Agent Architecture AI Brain**: GPT-4o-mini Memory**: Window buffer memory using sessionId Tools**: 5 API-connected nodes Trigger**: External input via message and sessionId Setup Instructions Get a CoinMarketCap API Key Apply here: https://coinmarketcap.com/api/ Configure n8n Credentials Use HTTP Header Auth to store your CoinMarketCap API key. Optional: Trigger from a Supervisor Connect to a parent agent using Execute Workflow with message and sessionId inputs. Test Sample Prompts “Get all exchanges”, “Fetch CMC index”, “Show Binance token holdings” Sticky Notes Included Exchange & Community Guide – Explains agent purpose and component connections Usage & Examples – Walkthrough for sample use cases Error Handling & Licensing – Includes API error code reference and licensing details ✅ Final Notes This agent is part of a broader CoinMarketCap AI Analyst System. Visit my Creator profile to download all available sub-agents and supervisor flows. Understand exchange behavior and community sentiment—automated with AI and CoinMarketCap.
by Don Jayamaha Jr
Access real-time cryptocurrency prices, market rankings, metadata, and global stats—powered by GPT-4o and CoinMarketCap! This modular AI-powered agent is part of a broader CoinMarketCap multi-agent system designed for crypto analysts, traders, and developers. It uses the CoinMarketCap API and intelligently routes queries to the correct tool using AI. This agent can be used standalone or triggered by a supervisor AI agent for multi-agent orchestration. Supported API Tools (6 Total) This agent intelligently selects from the following tools to answer your crypto-related questions: 🔍 Tool Summary Crypto Map – Lookup CoinMarketCap IDs and active coins Crypto Info – Get metadata, whitepapers, and social links Crypto Listings – Ranked coins by market cap CoinMarketCap Price – Live prices, volume, and supply Global Metrics – Total market cap, BTC dominance Price Conversion – Convert between crypto and fiat What You Can Do with This Agent 🔹 Get live prices and volume for tokens (e.g., BTC, ETH, SOL) 🔹 Convert crypto → fiat or fiat → crypto instantly 🔹 Retrieve whitepapers, logos, and website links for any token 🔹 Analyze total market cap, BTC dominance, and circulating supply 🔹 Discover new tokens and track their CoinMarketCap IDs 🔹 View the top 100 coins ranked by market cap or volume Example Queries ✅ "What is the CoinMarketCap ID for PEPE?" ✅ "Show me the top 10 cryptocurrencies by market cap." ✅ "Convert 5 ETH to USD." ✅ "What’s the 24h volume for ADA?" ✅ "Get the global market cap and BTC dominance." AI Architecture AI Brain**: GPT-4o-mini Memory**: Session buffer with sessionId Agent Type**: Subworkflow AI tool Connected APIs**: 6 CoinMarketCap endpoints Trigger Mode**: Executes when called by a supervisor (via message and sessionId inputs) Setup Instructions Get a CoinMarketCap API Key Register here: https://coinmarketcap.com/api/ Configure Credentials in n8n Use HTTP Header Auth with your API key for each connected endpoint Connect This Agent to a Supervisor Workflow (Optional) Trigger this agent using Execute Workflow with inputs message and sessionId Test Prompts Try asking: “Convert 1000 DOGE to BTC” or “Top 5 coins in EUR” Included Sticky Notes Crypto Agent Guide – Agent overview, node map, and endpoint details Usage Instructions – Step-by-step usage and sample prompts Error Handling & Licensing – Troubleshooting and IP rights ✅ Final Notes This agent is part of the CoinMarketCap AI Analyst System, which includes multiple specialized agents for cryptocurrencies, exchanges, community data, and DEX insights. Visit my Creator profile to find the full suite of tools. Get smarter about crypto—analyze the market in real time with AI and CoinMarketCap.
by Don Jayamaha Jr
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) Agent Architecture AI Model**: gpt-4o-mini Context Memory**: Window buffer using sessionId Trigger Input**: message, sessionId Execution**: Via Execute Workflow or parent AI supervisor Design**: Tool-based LangChain agent with CMC DEXScan endpoints 💡 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 Get a CoinMarketCap API Key Sign up at: https://coinmarketcap.com/api/ Add API Key to Credentials in n8n Use HTTP Header Auth method Trigger from Parent Workflow (Optional) 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. Visit my Creator profile to find the full suite of tools. Master DEX analytics with AI—get powerful liquidity, trading, and pair insights in seconds.
by irfan saeed
Auto-Generate YouTube Chapters with AI-Powered Transcript Analysis Overview This workflow uses YouTube Data API v3 and Google Gemini 1.5 Flash AI to automatically generate timestamped chapters for videos by analyzing SRT captions. It enhances viewer navigation, improves SEO , and saves creators time by automating manual tasks. Prerequisites YouTube API Setup Create a Google Cloud Project Go to the Google Cloud Console. Click Select a project > New Project and name it (e.g., "YouTube Chapters Automation") . Enable YouTube Data API v3 Navigate to APIs & Services > Library. Search for "YouTube Data API v3" and click Enable . Configure OAuth Consent Screen Go to APIs & Services > OAuth consent screen. Select External (public) or Internal (testing), then add required details (app name, support email) . Generate OAuth 2.0 Credentials Under Credentials, click Create Credentials > OAuth client ID. Choose Web app, then download the JSON key file . Add Credentials to n8n Other Requirements Google Gemini API**: Configure access for the gemini-1.5-flash-8b-exp-0924 model by getting the api key. Workflow Steps Set Video ID Input the target video ID (e.g., r1wqsrW2vmE) using the Set Video ID node. Fetch Video Metadata Use the YouTube API node to retrieve the video’s title, category, and existing description . Download SRT Captions Get Caption ID: Call https://www.googleapis.com/youtube/v3/captions to fetch the caption track ID . Download Transcript: Use the ID to retrieve SRT data via https://www.googleapis.com/youtube/v3/captions/{{ID}}?tfmt=srt . Analyze Transcript with Gemini AI Process the SRT file with Google Gemini AI to identify chapters using a prompt like: "Classify this transcript into timestamped chapters (e.g., 00:00 - Introduction)." Validate output with a structured parser (e.g., Structured Captions node) . Update Video Description Append chapters to the description using the YouTube API’s videos.update method . Value Proposition Viewer Experience**: Chapters improve navigation and reduce drop-off rates . SEO Benefits**: Structured descriptions enhance search visibility . Time Savings**: Eliminates manual chapter creation .
by Amjid Ali
Automated Weekly Project Cost Reports with MySQL and Outlook HTML Emails 🧠 Use Case Need to keep your finance or operations team updated on missing project costs? This practical automated report workflow does the job without AI — and saves hours weekly. Runs on a weekly schedule Queries your MySQL database for projects missing cost data Filters by budgeted_project_cost IS NULL Generates a clean HTML email report Sends it through Microsoft Outlook to relevant teams 🚀 How It Works Schedule Trigger – Runs every Monday at 8 AM MySQL Node – Connects and runs SQL to fetch project data missing budgeted_project_cost Switch Node – Routes logic based on cost_center (e.g., Retail, Service, Projects) Outlook Nodes – Sends formatted HTML emails; each node handles a specific group Dynamic Content – Inject values using mustache tags like {{ $json.project_name }} 🔧 Setup Instructions MySQL Setup: Ensure the MySQL node is connected using a valid credential set: Hostname/IP Port (default: 3306) Database name Username with SELECT permissions Password Query Example: SELECT project_name, cost_center FROM tabProject WHERE status = 'Open' AND project_type = 'External' AND budgeted_project_cost IS NULL; Outlook Configuration: Connect your Microsoft Outlook node using OAuth2 credentials. Rename each Outlook node clearly (e.g., Send Email - Retail, Send Email - Service). Switch Node: Modify cost center values as needed to match your organization (e.g., 'Retail', 'Service', 'Projects'). HTML Email Formatting: Customize the HTML message body using inline styles and mustache syntax. Sample: Missing Budgeted Cost Report Project: {{ $json.project_name }} Cost Center: {{ $json.cost_center }} Recipients: Replace amjid@amjidali.com with the actual email addresses of the concerned teams. 📘 Read More 👉 Why Simple Workflows Work 📺 Demo & Tutorial 🎥 Watch the video walkthrough: https://youtube.com/@syncbricks 👤 About the Creator Amjid Ali 🌐 amjidali.com 📘 n8n Book 🎓 Learn n8n > “Start simple, scale smart. Even basic workflows like this can save your team hours!” — Amjid Ali
by Sagar
This template streamlines your Instagram content posting workflow by connecting Google Drive for image storage, using OpenAI for AI-generated captions, and leveraging Facebook Graph API for automated publishing. Pre-requisites Before setting up this workflow, ensure you have: A Google account with access to Google Drive An OpenAI API key for AI caption generation A Facebook Developer account with Instagram Graph API access An Instagram Business or Creator account connected to a Facebook Page n8n.io account with workflow access Setup Instructions Configure Data Source Create a Google Sheet with the following columns: Name: Filename of your image in Google Drive Caption: Optional custom caption (leave empty for AI-generated captions) URL: your Video Reel or Image in Google Drive Connect Google Drive Add your Google Drive credentials in the "Google Drive" node Specify the folder path where your Instagram image/Video are stored Configure the node to retrieve image files based on filenames from your Google Sheet Set Up OpenAI Integration Add your OpenAI API key to the credentials Configure the OpenAI node to generate engaging captions based on image content Adjust temperature and model parameters for desired creativity level Configure Facebook Graph API Connect your Facebook account with Instagram access Set up the Facebook Graph API node to post to your Instagram Business/Creator account Ensure proper image formatting (1:1, 4:5, or 16:9 aspect ratios supported by Instagram) Workflow Automation Setup Configure the scheduler node to run at your preferred frequency Set up error handling to notify you of any posting failures Add conditional nodes to use either custom or AI-generated captions Execution Instructions After completing all connections, test the workflow with a single image Monitor the execution in the n8n dashboard to ensure proper functioning View the "Executions" tab to track successful posts and troubleshoot any errors Adjust posting frequency and scheduling as needed This template saves hours of manual Instagram posting work while maintaining an authentic presence. Perfect for social media managers, content creators, and businesses looking to maintain consistent Instagram activity without the daily manual effort. The workflow handles image retrieval, caption generation or customization, proper Instagram API formatting, scheduled posting, and execution tracking - all in one automated solution.
by Łukasz
Who is it for? If you are getting a lot of emails into your Gmail inbox, then probably some of those can be solved easly by replying or by doing specific short tasks. But analyzing whole email thread content just to catch up with multiple threads can be very wasteful. So by using AI you can actually get simple propositions of what should be done before closing this specific email and actual proposed answer to that email. This is especially useful if you need to do some actions before replying to email. In that case you can simply assign task to specific person, await until it's done, copy-paste AI answer when it's done, and close. Another good use would be if on one inbox there are working multiple people. It can make the process much more streamlined. How It Works? Script runs on your selected trigger. If you are using section "Read and Star", then you may use "Email Trigger". Automation is looking for exiting open Todoist tasks, that have the same title as email If task does not exist, then we are asking AI to analyze thread and give output that is Todoist-API-ready: having summary of email content having proposed actions to be taken having proposed answer to this email If email was unstarred for some reason but task was not closed, then task is being closed automatically. Script FOR PURPOSE is not trying to unstar messagess which have closed tasks, because this could lead to some inconsistencies. How to set up? Select and setup your triggers, depending on your needs Setup connections using N8N instructions. You will need: Gmail Todoist AI (in this workflow OpenAI is used) (Optional) Remove "Read and Star" section if you don't want tasks automatically read and starred. (Optional) Adjust AI node - especially useful if you want to use different model or have response in different language NOTE Chat does not heave memory attached on purpose. The purpose is that it should analyze each inbox message separately, not in thread. When using memory, it can get lost easily. NOTE2 You might want to adjust limits on nodes "Get Unread From Inbox", "Get Starred From Inbox" and "Get Open Tasks", especially if having issues with model complying to output structure. And that's it. I hope that this automation will make your Gmail <-> Todoist process much more streamlined! What's More? There is actually more that you could do with this automation, but it really depends on your needs. For example, you could add Form trigger to handle incoming support requests. Another thing is that you could replace Todoist with Asana or any database (like NocoDB) if you are using it for your task management.
by Yang
Workflow Description This workflow helps content creators automatically repurpose YouTube videos into SEO-friendly blog posts. It extracts the video transcript, uses AI to generate a full blog post with a relevant image, and sends the complete package via email, ready for publication. Prerequisites/Requirements This workflow relies on external AI services. You will need: OpenAI Account: Used for generating the blog post text (specifically mentioned using GPT-4o in the workflow notes). Credentials: Requires an API key from OpenAI. Cost: OpenAI API usage is typically paid based on the amount of text processed (tokens). Check OpenAI's current pricing. Setup: Sign up at OpenAI and obtain your API key. Dumpling AI Account: Used for retrieving YouTube video transcript and generating the blog post image. Credentials: Requires an API key from Dumpling AI. Cost: Dumpling AI offers 250 free credits to start with and different plans for different levels of usage. Check the pricing page for more details. Setup: Sign up at Dumpling AI and obtain your API key/credentials. Email Account: Credentials for the email service (e.g., Gmail) used to send the final result. How it works Input Video Details: You provide the YouTube video URL and your email address. Get Transcript: The workflow fetches the transcript of the specified YouTube video. Generate Content: An AI model crafts a blog post (title, description, body) based on the transcript. Create Image: Another AI model generates a suitable image for the blog post. Format & Package: The blog post is converted to HTML, and the image is prepared for sending. Email Result: The final HTML blog post and image are emailed to you. Set up steps Configure Variables: Enter the specific YouTube video URL and the recipient email address in the "Set Variables" node. Connect Credentials: Add your credentials for the services used (e.g., OpenAI for text generation, Dumpling AI for YouTube Transcript and AI image generation service). Connect Email Credentials: Authenticate your Gmail account (or chosen email provider) to allow the workflow to send the email. Take it to the next level Direct Publishing:** Instead of emailing the result, connect directly to your CMS (like WordPress, Ghost, Webflow) to automatically create a draft or publish the blog post. AI Agent Integration:** Replace the single "Generate Blog Post" step with an AI Agent for more sophisticated content generation, potentially researching topics or structuring the post section by section based on the transcript. Social Media Snippets:** Add steps to generate companion social media posts (e.g., for Twitter, LinkedIn) summarizing the blog post. Batch Processing:** Modify the trigger to read multiple YouTube URLs from a spreadsheet or database to convert videos in bulk. Enhanced SEO:** Refine the AI prompts to specifically target keywords or incorporate SEO best practices more deeply into the generated content. Multiple Image Options:** Generate several image variations and include them in the email or draft post for selection.
by Ranjan Dailata
Who this is for? This workflow is designed for professionals and teams who need real-time, structured insights from Google Search results without manual effort. What problem is this workflow solving? This n8n workflow solves the problem of automating Google Search result extraction, cleanup, summarization, and AI-enhanced formatting for downstream use like sending the results to a webhook or another system. What this workflow does Automates Google Search via Bright Data Uses Bright Data’s proxy-based SERP API to run a Google Search query programmatically. Makes the process repeatable and scriptable with different search terms and regions/zones. Cleans and Extracts Useful Content The Google Search Data Extractor uses LLM based cleaning to remove HTML/CSS/JS from the response and extract pure text data. Converts messy, unstructured web content into structured, machine-readable format. Summarizes Search Results Through the Gemini Flash + Summarization Chain, it generates a concise summary of the search results. Ideal for users who don’t have time to read full pages of search results. Formats Data Using AI Agent The AI Agent acts like a virtual assistant that: Understands search results Formats them in a readable, JSON-compatible form Prepares them for webhook delivery Delivers Results to Webhook Sends the final summary + structured search result to a webhook (could be your app, a Slack bot, Google Sheets, or CRM). 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. A Google Gemini API key (or access through Vertex AI or proxy). Update the Google Search query as you wish by navigating to the Set Google Search Query node. Update the Webhook HTTP Request node with the Webhook endpoint of your choice. How to customize This Workflow to your needs 1. Change the Search Input Default: It searches a fixed query or dataset. Customize: Accept input from a Google Sheet, Airtable, or a form. Auto-trigger searches based on keywords or schedules. 2. Customize Summarization Style (LLM Output) Default: General summary using Google Gemini or OpenAI. Customize: Add tone: formal, casual, technical, executive-summary, etc. Focus on specific sections: pricing, competitors, FAQs, etc. Translate the summaries into multiple languages. Add bullet points, pros/cons, or insight tags. 3.Choose Where the Results Go Options: Email, Slack, Notion, Airtable, Google Docs, or a dashboard. Auto-create content drafts for WordPress or newsletters. Feed into CRM notes or attach to Salesforce leads.
by Ranjan Dailata
Who this is for? This workflow automates the process of Wikipedia data extraction using the Bright Data Web Unlocker, parsing and cleaning the data, and then sending the results to a specified webhook URL for downstream processing, reporting, or integration. What problem is this workflow solving? Researchers who need structured information from Wikipedia pages regularly. Data Engineers building knowledge bases or enriching datasets with factual data. Digital Marketers or Content Writers automating fact-checking or content sourcing. Automation Enthusiasts who want to trigger external systems with rich context from Wikipedia. What this workflow does This workflow addresses the challenges of manually retrieving, structuring, and using data from Wikipedia at scale. Workflow Breakdown Trigger Type: Scheduled or Manual Purpose: Starts the workflow either on a fixed schedule (e.g., daily) or on-demand via a manual trigger or incoming webhook. Bright Data Wikipedia Scraping Tool Used: Bright Data Web Unlocker Action: Scrape the HTML content of one or multiple Wikipedia article URLs. Parse & Extract Structured Data The Basic LLM Chain node is responsible for producing a human readable content. Summarization Summarize the Wikipedia content by utilizing the Summarization Chain node. Send to Webhook Initiates a Webhook notification to the specified URL as part of the "Summary Webhook Notifier" node. 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 Set Wikipedia URL with Bright Data Zone node with the Wikipedia URL and Bright Data Zone. Update the Summary Webhook Notifier node with the Webhook endpoint of your choice. How to customize this workflow to your needs Update Wikipedia URL Replace with your own Wikipedia URL of your interest. Make sure to set the Wikipedia URL as part of the "Set Wikipedia URL with Bright Data Zone" node. Modify Data Extraction Logic Extract entire article content or just specific sections by extending the "LLM Data Extractor" node prompt. Extend AI Summarization Extract key bullet points or entities. Create short-form summaries by extending the "Concise Summary Generator" node. Extend Summary Webhook Notifier Send to Slack, Discord, Telegram, MS Teams via the Webhook notification mechanism. Connect to your internal database/API via the Webhook notification mechanism.
by Jimleuk
This n8n template reviews and audits recently active Google Drive files and reports on files with excessively open permissions. This shows how you can automate simple compliance tasks for access control management. File Sharing Permissions are routinely abused when access needs and scopes expand to many colleagues, clients and users. Often, granting excessively open permissions means you can get back to work rather than deal with numerous access request notifications. Whilst sometimes justified, the problem is that the permissions are rarely reverted to a safer setting at a later date when it is no longer needed. This template serves to improve your security posture by giving frequent reminders of these open files so that they can be actioned and not forgotten about. See example Audit Report here: https://docs.google.com/spreadsheets/d/1V2aiLhp3_nH7EBniMn7D0kFHg7-A5NjpDZXMhb4F5UI/edit?gid=503992967 How it works A scheduled trigger runs everyday to generate a new audit report. A new sheet is created in a designated Google Sheets document to store the day's results. The Google Drive node is used with Advanced Search params to fetch recently modified files for the user with each file result containing the current permission settings. The results are filtered for those with publicly accessible "anyone with link" and sharing with external users via domain. The results are then manipulated into rows so that we can append them to the Sheet we created earlier. The audit Google Sheet is updated with the results and an audit report is sent to the user to action. How to use Set the scheduled trigger to a more appropriate interval which works for you or your organisation. Consider using allowlists for organisations you frequently share with to reduce the number of false positives. The results can be forwarded to other security or analytical products as required. Requirements Google Drive for Document Management Google Sheet for Reports and Data Collection Gmail to Email Reports Customising the workflow Not using Google? Apply the same approach using Microsoft Sharepoint or Dropbox. If your security policies require it, you could automate fixing the file permissions as a proactive action instead and notify the user later.
by merfy
Use Case Manually extracting images from PDF files for analysis is often slow and inefficient. Many users resort to taking screenshots of each page, uploading them to an AI tool like OpenAI for image analysis, and then manually copying the insights into a document. This manual process is time-consuming and prone to errors. This workflow streamlines the entire process by automatically extracting images from a PDF, analyzing them using the GPT-4o model, and saving the results in seconds—eliminating the need for manual effort. What This Workflow Does Extracts all images from the uploaded PDF file automatically The workflow scans each page of the PDF and identifies embedded images without manual intervention. Uses the GPT-4o model to analyze each extracted image Each image is processed through GPT-4o to generate descriptive insights, summaries, or context-specific analysis depending on the use case. Saves the analysis results to a .txt file, including image URLs The final output is a plain text file containing both the image URLs (e.g., hosted on cloud storage) and the corresponding GPT-4o analysis, ready for further use or sharing. Setup 1.Set up your credentials when you first open the workflow. You’ll need accounts for OpenAI, Convert API, and Google Drive. 2.Convert API does not rate-limit your API, sometimes you may receive 503 service unavailable error. Nevertheless, it doesn’t mean that you cannot convert your file. It simply means that you should retry the conversion in a few seconds. 3.Upload a PDF with images to Google Drive. 4.Remove unnecessary parts and retrieve image-related information. 5.Integrate image and image analysis information together. 6.Analyze each image using the OPENAI GPT-4o model. 7.Retrieve all image analysis content and image URL 8.Integrate multiple image URLs and analysis content 9.Output content to a .txt file. Template was created in n8n v1.83.2 How to Customize Replace the manual trigger with a Google Drive trigger or other automation triggers Change the image analysis model (e.g., switch or fine-tune GPT-4o) Send the results to other platforms (e.g., Slack, Telegram, LINE, etc.) instead of saving to a .txt file