Workflow Templates

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.

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.

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.

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.

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

Who is this for? This template is designed for anyone who wants to integrate MCP with their AI Agents. Whether you're a developer, a data analyst, or an automation enthusiast, if you're looking to leverage the power of MCP and Google Calendar in your n8n workflows, this template is for you. What problem is this workflow solving? This template caters to MCP beginners seeking a hands - on example and developers looking to integrate Google Calendar MCP service. When integrating MCP with Google Calendar, manually updating AI Agents after changes to Google Calendar tools on the MCP Server is time - consuming and error - prone. This template automates the process, enabling the AI Agent to instantly recognize changes made to Google Calendar on the MCP Server. In project management, for example, it ensures that task schedule updates in Google Calendar are automatically detected by the AI Agent. With detailed steps, it simplifies the integration process for all users. What this workflow does This workflow focuses on integrating MCP with Google Calendar within n8n. Specifically, it allows you to build an MCP Server and Client using Google Calendar nodes in n8n. Any changes made to the Google Calendar tools on the MCP Server are automatically recognized by the MCP Client in the workflow. This means that you can make changes to your Google Calendar (such as adding, deleting, or modifying events) on the MCP Server, and the MCP Client in the n8n workflow will immediately detect these changes without any manual intervention. Setup Requirements An active n8n account. Access to Google Calendar API. You need to enable the Google Calendar API, and create the necessary credentials (OAuth 2.0 client ID). Basic knowledge of n8n workflows and MCP concepts. Step - by - step guide Create a new workflow in n8n: Log in to your n8n account and create a new workflow. Add Google Calendar nodes: Search for and add the Google Calendar nodes to your workflow. Configure the nodes with your Google Calendar API credentials. Set up the MCP Server and Client: Use the appropriate nodes in n8n to set up the MCP Server and Client. Connect the Google Calendar nodes to the MCP nodes as required. Test the workflow: Make some changes to your Google Calendar on the MCP Server and check if the MCP Client in the n8n workflow can detect these changes. How to customize this workflow to your needs If you want to customize this workflow, you can: Modify the triggers**: You can change the conditions under which the MCP Client detects changes. For example, you can set it to detect only specific types of events in Google Calendar. Integrate with other services**: You can add more nodes to the workflow to integrate with other services, such as sending notifications to Slack or saving data to a database when a change is detected.

This n8n template imports purchase order submissions from Outlook and converts attached purchase order forms in XLSX format into structured output. Data entry jobs with user-submitted XLSX forms are time consuming, incredibly mundane but necessary tasks which in likelihood are inherited and critical to business operation. While we could dream of system overhauls and modernisation, the fact is that change is hard. There is another way however - using n8n and AI! N8N offers an end-to-end solution to parse XLSX form attachments using LLM-powered OCR and send the extracted output to your ERP or otherwise. How it works An Outlook trigger is used to watch for incoming purchase order forms submitted via a shared inbox. The email attachment for the submission is a form in xlsx format - like this one Purchase Order Example - which is imported into the workflow. The 'Extract from File' node is used with the 'code' node to convert the xlsx file to markdown. This is so our LLM can understand it. The Information Extractor node is used to read and extract the relevant purchase order details and line items from the form. A simple validation step is used to check for common errors such as missing PO number or the amounts not matching up. A notification is automated to reply to the buyer if so. Once validation passes, a confirmation is sent to the buyer and the purchase order structured output can be sent along to internal systems. How to use This template only works if you're expecting and receiving forms in XLSX format. These can be invoices, request forms as well as purchase order forms. Update the Outlook nodes with your email or other emails as required. What's next? I've omitted the last steps to send to an ERP or accounting system as this is dependent on your org. Requirements Outlook for Emails Check out how to setup credentials here: https://docs.n8n.io/integrations/builtin/credentials/microsoft OpenAI for LLM document understanding and extraction. Customising the workflow This template should work for other Excel files. Some will be more complicated than others so experiment with different parsers and extraction tools and strategies. Customise the Information Extractor Schema to pull out the specific data you need. For example, capture any notes or comments given by the buyer.

📝 What this workflow does Every morning at 8 a.m., this workflow fetches the latest AI-related articles from both GNews and NewsAPI. It merges up to 40 new articles daily, selects the 15 most relevant ones on AI technology and applications, and uses GPT-4.1 to generate concise summaries in accurate Traditional Chinese (while preserving essential English technical terms). Each summary also includes the article link for easy referral. The compiled digest is then posted to your designated Telegram account or group. 👥 Who is this for? AI enthusiasts, professionals, and anyone interested in artificial intelligence news Individuals and teams wanting a concise daily digest of AI developments in Traditional Chinese Telegram users who prefer automated information delivery 🎯 What problem does this workflow solve? With the rapid evolution of AI technology, it can be overwhelming to keep up with new developments. This workflow addresses information overload by automatically collecting, summarizing, and translating the most important AI news each morning — all delivered conveniently to your chosen Telegram channel or group. ⚙️ Setup 🔑 Add NewsAPI and GNews API Keys Register for accounts on NewsAPI.org and GNews to obtain your API keys. Input your NewsAPI key directly into the Fetch NewsAPI articles node. Input your GNews API key into the Fetch GNews articles node. 🤖 Set up your Telegram Bot Create a Telegram Bot via BotFather and copy the generated Bot Token. In n8n, create Telegram Bot credentials using this token. In the Send summary to Telegram node, enter the chat ID of your target user, group, or channel to receive the messages. 🧠 Configure OpenAI Credentials In n8n, create a new credential using your OpenAI API key. Assign this credential to the GPT-4.1 Model node (or equivalent OpenAI/AI nodes). After completing these steps, your workflow is fully configured to fetch, summarize, and deliver daily AI news to your selected Telegram chat automatically. 🛠️ How to customize this workflow 🔍 Change the topic:** Update the keywords in the NewsAPI and GNews nodes for other subjects (e.g., "blockchain", "quantum computing"). ⏰ Adjust delivery time:** Modify the scheduled trigger to your preferred hour. ✍️ Tweak summary style or language:** Refine the prompt in the AI summarizer node for different tones or translate into other languages as needed. 📦 Dependencies NewsAPI account GNews account Telegram Bot OpenAI API access (for GPT-4.1) or compatible AI model for Langchain agent

Tags: Accessibility, SEO, Blogging, Marketing, Automation, AI, Web Auditing Context Hey! I’m Samir, a Supply Chain Engineer and Data Scientist from Paris, and the founder of LogiGreen Consulting. In my personal blog, I share insights on how to use AI, automation, and data analytics to improve logistics, operations, and digital sustainability practices. > Have you heard about accessibility? In this workflow, I use n8n to improve the quality of alternative texts for images on my personal website. 📬 For business inquiries, you can connect with me on LinkedIn Who is this template for? This workflow is for: Bloggers* and *website owners* who want to *improve accessibility** SEO professionals** looking to boost page performance Web developers* and *product teams** automating web audits What does it do? This n8n workflow: 🔍 Downloads the HTML of a blog or web page 🖼️ Extracts all ` tags and their alt` attributes 📉 Detects missing or too-short alt texts 🤖 Sends those images to GPT-4o (with vision) to generate new alt descriptions 📄 Saves the results into a Google Sheet, updating the alt text when needed How it works Set a page URL using the Set node Download HTML content Extract image src and alt using a Code node Store results in a Google Sheet Filter images with altLength < 50 Send image URL to GPT-4o Update the Google Sheet with the newly generated newAlt text The AI alt texts are concise, descriptive, and accessibility-compliant. What do I need to get started? You’ll need: A Google Sheet to store the audit results An OpenAI account with GPT-4o access Follow the Guide! Follow the sticky notes in the workflow or check my tutorial to configure each node and start using AI to improve the accessibility of your website. 🎥 Watch My Tutorial Notes GPT-generated alt texts are limited to ~125–150 characters for best results Use this to comply with WCAG and improve Google indexing Easily adapt it to audit multiple domains or e-commerce catalogues This workflow was built using n8n version 1.85.4 Submitted: April 21, 2025

Automatically convert documents from Google Drive into vector embeddings using OpenAI, LangChain, and PGVector — fully automated through n8n. ⚙️ What It Does This workflow monitors a Google Drive folder for new files, supports multiple file types (PDF, TXT, JSON), and processes them into vector embeddings using OpenAI’s text-embedding-3-small model. These embeddings are stored in a Postgres database using the PGVector extension, making them query-ready for semantic search or RAG-based AI agents. After successful processing, files are moved to a separate “vectorized” folder to avoid duplication. 💡 Use Cases Powering Retrieval-Augmented Generation (RAG) AI agents Semantic search across private documents AI assistant knowledge ingestion Automated document pipelines for indexing or classification 🧠 Workflow Highlights Trigger Options:** Manual or Scheduled (3 AM daily by default) Supported File Types:** PDF, TXT, JSON Embedding Stack:** LangChain Text Splitter, OpenAI Embeddings, PGVector Deduplication:** Files are moved after processing License:** CC BY-SA 4.0 Author:** AlexK1919 🛠 What You’ll Need Google Drive OAuth2** credentials (connected to Search Folder, Download File, and Move File nodes) OpenAI API Key** (used in the Embeddings OpenAI node) Postgres + PGVector** database (connected in the Postgres PGVector Store node) 🔧 Step-by-Step Setup Instructions Create Google OAuth2 credentials in n8n and connect them to all Google Drive nodes. Set your source folder ID in the Search Folder node — this is where incoming files are placed. Set your processed folder ID in the Move File node — files will be moved here after vectorization. Ensure you have a PGVector-enabled Postgres instance and input the table name and collection in the Postgres PGVector Store node. Add your OpenAI credentials to the Embeddings OpenAI node and select text-embedding-3-small. Optional: Activate the Schedule Trigger node to run daily or configure your own schedule. Run manually by triggering When clicking ‘Test workflow’ for on-demand ingestion. 🧩 Customization Tips Want to support more file types or enhance the pipeline? Add new extractors**: Use Extract from File with other formats like DOCX, Markdown, or HTML. Refine logic by file type**: The Switch node routes files to the correct extraction method based on MIME type (application/pdf, text/plain, application/json). Pre-process with OCR**: Add an OCR step before extraction to handle scanned PDFs or images. Add filters**: Enhance the Search Folder or Switch node logic to skip specific files or folders. 📄 License This workflow is available under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license. You are free to use, adapt, and share this workflow for non-commercial purposes under the terms of this license. Full license details: https://creativecommons.org/licenses/by-nc-sa/4.0/

Dynamically switch between LLMs for AI Agents using LangChain Code Purpose This example workflow demonstrates a way to connect multiple LLMs to a single AI Agent/LangChain Node and programmatically use one – or in this case loop through them. What it does This AI workflow takes in customer complaints and generates a response that is being validated before returned. If the answer was not satisfactory, the response will be generated again with a more capable model. How it works A LangChain Code Node allows multiple LLMs to be connected to a single Basic LLM Chain. On every call only one LLM is actually being connected to the Basic LLM Chain, which is determined by the index defined in a previous Node. The AI output is later validated by a Sentiment Analysis Node If the result was not satisfactory, it loops back to the beginning and executes the same query with the next available LLM The loop ends either when the result passed the requirements or when all LLMs have been used before. Setup Clone the workflow and select the belonging credentials. You'll need an OpenAI Account, alternatively you can swap the LLM nodes with ones from a different provider like Anthropic after the import. How to use Beware that the order of the used LLMs is determined by the order they have been added to the workflow, not by the position on the canvas. After cloning this workflow into your environment, open the chat and send this example message: > I really love waiting two weeks just to get a keyboard that doesn’t even work. Great job. Any chance I could actually use the thing I paid for sometime this month? Most likely you will see that the first validation fails, causing it to loop back to the generation node and try again with the next available LLM. Since AI responses are unpredictable, the results and number of tries will differ for each run. Disclaimer Please note, that this workflow can only run on self-hosted n8n instances, since it requires the LangChain Code Node.

Target Audience You will find this workflow or template perfect if you are in the internal talent acquisition teams, recruitment agencies, HR professionals, and hiring managers seeking to bulk automate the initial screening of CVs and resumes. Eg. Automatically get result of candidate who has been shortlisted/rejected with its rationale and score automatically. By eliminating manual evaluation and screening, you get smart AI-Agent helping you to have standardized efficient, and scalable solution for handling large volumes of applications. With bulk automation, you can focus strategic decision-making rather than tedious screening tasks, ensuring a faster, more accurate, and fair hiring process. Key focus This workflow focusses on having a more organized file-folder management, trackable candidate cv, maintainable job description, autonomous ai-agent. Organized Folder-File Structure – CVs are automatically categorized based on their status, ensuring a structured workflow and easy retrieval Candidate Tracker – A real-time tracking system records the state of each CV, allowing recruiters to monitor the shortlisted, rejected, or KIV (Keep in View) candidates. AI Agent for Decision Automation – The AI autonomously orchestrates screening decisions, replacing manual LLM configurations with dynamic AI-driven evaluations for scalability and accuracy. Maintainable Job Description Management – A structured job description file ensures continuous updates, keeping hiring criteria flexible and aligned with recruitment needs. Email Notifications – The system automatically sends receipt confirmations upon processing completion, providing timely updates to recruiters. Features - Workflow Automated Resume Screening Workflow This workflow leverages Groq Llama4 for intelligent resume analysis, speeding the screening process by generating a matching score, result (shortlisted/rejected/kiv), and key insights/rationale into their suitability for provided job description. Step-by-Step Process: Monitors Google Drive:** Listens and checks for new resume cv in google drive . Retrieve Resume:** Downloads the CV resumes from google drive . Extract Resume Data:* Extract *text content** from CV resume PDF files Extract Job Description Data:* Extract *text content** from job description Analyze with Groq:** Generate a matching score based on job requirements. [SCORE: 1-10] Provide decision into their job suitability. [SHORTLISTED/REJECTED/KIV] Provide actionable insights into their job suitability. [REASON] This ensures a fast, efficient, and accurate screening process, eliminating manual evaluation. Setup Guide Step-by-Step Instructions Ensure all credentials are ready and setup (groq, gdrive ,gmail, gsheet, gdoc) View official n8n documentation on node setup accordingly. See also the notes of setup . Folder & File Setup 1. Create a google-drive folder like this View directory example 2. Create a job description like this View file example 3. Configure a tracker like this ( Candidate Name, AI Score,AI Verdict, AI Reason) View file example email conversations report as you like. You are ready to go!