by Raymond Camden
This n8n template demonstrates how to add a document conversion process to incoming Word documents in a OneDrive folder. Documents are converted to PDF and emailed to a reviewer. Use cases would be environments where incoming documents are dropped into cloud storage and a human needs to review them. By converting to PDF, it becomes easier to read in a consistent format in the browser. How it works Listen for new files added in a OneDrive folder, identified by an ID Download the bits of the new document if the file was a Micrsoft Word document (the API I'm using can convert any Office document, but wanted to start simple) Upload to Foxit's API service, convert to PDF, and download when done Use GMail to mail the PDF to a human reviewer. How to use You'll need to determine a OneDrive folder ID to monitor, or select an entire account instead, just be careful when testing. When the workflow is done, it emails to myself, so please connect your own GMail and set a preferred email address for testing. Requirements A Microsoft OneDrive account Foxit developer account (https://developer-api.foxit.com) A Gmail account At least one Word document - we all have that, right? Next Steps This workflow could be modified to work with any Office style document, and could also upload the PDF version back to OneDrive.
by Pedro Santos
🎥 Summarize YouTube Videos using SearchApi & LLM Who is this for? This workflow is ideal for content creators, students, digital marketers, educators, and researchers who want to quickly summarize YouTube videos. What problem does this workflow solve? Manually extracting important information from lengthy YouTube videos can be tedious and prone to errors. This workflow streamlines the process by automatically fetching video transcripts using SearchApi.io and producing concise, informative summaries through a summarization chain powered by any LLM provider. This allows users to quickly access crucial information without the need for manual transcription or detailed viewing. What this workflow does Fetches the complete transcript of a YouTube video using SearchApi. Combines the retrieved transcript into a single, continuous text. Utilizes a Summarization Chain with an LLM (e.g., OpenRouter models) to create a concise summary of the video content. Setup Install the SearchApi community node: Open Settings → Community Nodes inside your self‑hosted n8n instance. Fill npm Package Name with @searchapi/n8n-nodes-searchapi. Accept the risk prompt, and hit Install. It should now appear as a node when you search for it. API Configuration: Set up your SearchApi.io credentials in n8n. Add your preferred LLM provider credentials (e.g., OpenRouter API). Input Requirements: Provide the YouTube video ID (e.g., wBuULAoJxok). Connect LLM Integration: Configure the summarization chain with your chosen model and parameters for text splitting. How to customize this workflow to meet your needs Adjust the summarization model or modify text-splitter parameters to accommodate different lengths and complexities of video transcripts. Integrate additional nodes to export summaries directly into your preferred tools, such as Google Drive, Slack, or email. Customize prompt templates in the summarization chain to obtain various summary styles (bullet points, paragraphs, etc.). Modify the trigger to suit your workflow. Example Usage Input: YouTube video ID (wBuULAoJxok). Output: A concise, actionable summary that highlights key ideas, recommendations, and insights from the video.
by InfraNodus
Using the knowledge graphs instead of RAG vector stores This workflow creates an AI chatbot agent that has access to several knowledge bases at the same time (used as "experts"). These knowledge bases are provided using the InfraNodus GraphRAG using the knowledge graphs and providing high-quality responses without the need to set up complex RAG vector store workflows. The advantages of using GraphRAG instead of the standard vector stores for knowledge are: Easy and quick to set up (no complex data import workflows needed) A knowledge graph has a holistic view of your knowledge base Better retrieval of relations between the document chunks = higher quality responses How it works This template uses the n8n AI agent node as an orchestrating agent that decides which tool (knowledge graph) to use based on the user's prompt. Here's a description step by step: The user submits a question using the AI chatbot (n8n interface, in this case, which can be accessed via a URL or embedded to any website) The AI agent node checks a list of tools it has access to. Each tool has a description of the knowledge it has auto-generated by InfraNodus. The AI agent decides which tool should be used to generate a response. It may reformulate user's query to be more suitable for the expert. The query is then sent to the InfraNodus HTTP node endpoint, which will query the graph that corresponds to that expert. Each InfraNodus GraphRAG expert provides a rich response that takes the whole context into account and provides a response from each expert (graph) along with a list of relevant statements retrieved using a combination or RAG and GraphRAG. The n8n AI Agent node integrates the responses received from the experts to produce the final answer. The final answer is sent back to the user's chat (or a webhook endpoint) How to use You need an InfraNodus GraphRAG API account and key to use this workflow. Create an InfraNodus account Get the API key at https://infranodus.com/api-access and create a Bearer authorization key for the InfraNodus HTTP nodes. Create a separate knowledge graph for each expert (using PDF / content import options) in InfraNodus For each graph, go to the workflow, paste the name of the graph into the body name field. Keep other settings intact or learn more about them at the InfraNodus access points page. Once you add one or more graphs as experts to your flow, add the LLM key to the OpenAI node and launch the workflow Requirements An InfraNodus account and API key An OpenAI (or any other LLM) API key Customizing this workflow You can use this same workflow with a Telegram bot, so you can interact with it using Telegram. There are many more customizations available. Check out the complete guide at https://support.noduslabs.com/hc/en-us/articles/20174217658396-Using-InfraNodus-Knowledge-Graphs-as-Experts-for-AI-Chatbot-Agents-in-n8n Also check out the video tutorial with a demo:
by Airtop
Scoring LinkedIn Profiles Against Your ICP Use Case This automation scores individual LinkedIn profiles against your Ideal Customer Profile (ICP) based on interest in AI, technical depth, and seniority level. It's ideal for prioritizing leads and understanding how well a person fits your ICP criteria. What This Automation Does Given a LinkedIn profile and an Airtop profile, it: Extracts relevant data from the person's profile Determines levels of AI interest, seniority, and technical depth Calculates an ICP score based on weighted criteria Returns the full enriched profile with the score Input parameters: LinkedIn Profile URL** (e.g., https://linkedin.com/in/janedoe) Airtop Profile** connected to LinkedIn ICP scoring method** in the Airtop node prompt Output fields in JSON format: Full name, job title, employer, company LinkedIn URL, location, number of connections and followers, about section content and more Calculated ICP Score (out of 95) How It Works Form Trigger or Workflow Trigger: Accepts input from either a form or another workflow. Parameter Assignment: Ensures proper variable names for downstream nodes. Airtop Enrichment Tool: Extracts and scores the person based on a detailed prompt. Scoring: Uses this point system: AI Interest: beginner (5), intermediate (10), advanced (25), expert (35) Technical Depth: basic (5), intermediate (15), advanced (25), expert (35) Seniority Level: junior (5), mid-level (15), senior (25), executive (30) Output Formatting: Cleans and returns the result as JSON. Setup Requirements IMPORTANT: Enter your ICP scoring method in the prompt field of the Airtop node Airtop Profile connected to LinkedIn. Airtop API credentials configured in n8n. Optional: a front-end form to collect profile URLs and trigger the automation. Next Steps Embed in CRM**: Trigger this automation on new leads to auto-score them. Batch Process Leads**: Run it over a list of profile URLs for segmentation. Customize Scoring**: Adjust point weights based on your sales priorities. Read more about ICP Scoring with Airtop and n8n
by Aditya Gaur
Who is this template for? This template is designed for developers, DevOps engineers, and automation enthusiasts who want to streamline their GitLab merge request process using n8n, a low-code workflow automation tool. It eliminates manual intervention by automating the merging of GitLab branches through API calls. How it works ? Trigger the workflow: The workflow can be triggered by a webhook, a scheduled event, or a GitLab event (e.g., a new merge request is created or approved). Fetch Merge Request Details: n8n makes an API call to GitLab to retrieve merge request details. Check Merge Conditions: The workflow validates whether the merge request meets predefined conditions (e.g., approvals met, CI/CD pipelines passed). Perform the Merge: If all conditions are met, n8n sends a request to the GitLab API to merge the branch automatically. Setup Steps 1. Prerequisites An n8n instance (Self-hosted or Cloud) A GitLab personal access token with API access A GitLab repository with merge requests enabled 2. Create the n8n Workflow Set up a trigger: Choose a trigger node (Webhook, Cron, or GitLab Trigger). Fetch merge request details: Add an HTTP Request node to call GET /merge_requests/:id from GitLab API. Validate conditions: Check if the merge request has necessary approvals. Ensure CI/CD pipelines have passed. Merge the request: Use an HTTP Request node to call PUT /merge_requests/:id/merge API. 3. Test the Workflow Create a test merge request. Check if the workflow triggers and merges automatically. Debug using n8n logs if needed. 4. Deploy and Monitor Deploy the workflow in production. Use n8n’s monitoring features to track execution. This template enables seamless GitLab merge automation, improving efficiency and reducing manual work! Note: Never hard code API token or secret in your https request.
by Mihai Farcas
This n8n workflow operates as a two-agent system where each agent has a specialized task. The process flows from initial user input to a final analysis, with a seamless handoff between the agents. How it works The Chat Trigger The entire process begins when you send a message using n8n's chat interface. This message serves as the initial prompt or query for the system. The Research Agent Takes Over The user's message is first sent to the Research Agent. This agent's job is to understand the query and gather relevant information. To do this, it has access to: LLM: Google Gemini, which acts as the agent's "brain" to process language and make decisions. Tools: web_search: It uses this tool (powered by your self-hosted SearXNG instance) to perform live searches on the internet. get_current_date: It can access the current date, which is useful for context-aware or time-sensitive research. The Research Agent uses these tools to find the most relevant information related to your query and then compiles it into a concise summary. Handoff to the Sentiment Analysis Agent Once the Research Agent has completed its task, it passes its findings directly to the Sentiment Analysis Agent. The Final Analysis The Sentiment Analysis Agent receives the text from the Research Agent. Its sole purpose, as defined by its system prompt, is to analyze the sentiment of the provided information. It determines if the content is positive, negative, or neutral and formulates a final response. This final analysis is then sent back to you in the chat, completing the workflow. Set up steps Select the Language Model (LLM): This workflow is pre-configured with Google Gemini. You can select a different model for the agents as needed. Configure LLM Credentials: Ensure that valid credentials for your chosen LLM are correctly set up within your n8n instance. Set Up the SearXNG Connection: Configure the node to connect to your self-hosted SearXNG instance. This enables the agent's web search capabilities. Define the Research Agent's Task: Customize the system prompt for the "Research Agent" to define its role, instructions, and how it should conduct its research. Define the Sentiment Analysis Agent's Task: Adjust the system prompt for the "Sentiment Analysis Agent" to specify how it should analyze the information provided by the Research Agent. Test the Workflow: Use the built-in chat interface in the n8n canvas to send a message and verify that the agents are functioning correctly.
by Lucas Peyrin
How it works This workflow is a robust and forgiving JSON parser designed to handle malformed or "dirty" JSON strings often returned by AI models or scraped from web pages. It takes a text string as input and attempts to extract and parse a valid JSON object from it. Cleans Input: It starts by trimming whitespace and removing common Markdown code fences (like ` Applies Multiple Fixes: It systematically attempts to correct common JSON errors in a specific order: Escapes unescaped control characters (like newlines) within strings. Fixes invalid backslash escape sequences. Removes trailing commas. Intelligently attempts to fix unescaped double quotes inside string values. Parses Strategically: If a direct parse fails, it tries to extract a potential JSON object from the text (e.g., finding a {...} block inside a larger sentence) and then re-applies the cleaning logic to that extracted portion. Outputs Clean Data: If successful, it outputs the parsed JSON fields. By default, it removes the detailed parsing_status object, but you can deactivate the final "Set" node to keep it for debugging. Set up steps Setup time: ~1 minute This workflow is designed to be used as a sub-workflow and requires no internal setup. In your main workflow, add an Execute Sub-Workflow node where you need to parse a messy JSON string. In the Workflow parameter, select this "Robust JSON Parser" workflow. Ensure the data you send to the node is a JSON object containing a text field, where the value of text is the string you want to parse. For example: { "text": "{\\\"key\\\": \\\"some broken json...\\\"}" }. The workflow will return the successfully parsed data. To see a detailed log of the cleaning process, simply deactivate the final Remove parsing_status node inside this workflow.
by Intuz
This n8n template from Intuz provides a complete and automated solution for real-time financial reporting. It instantly syncs new QuickBooks invoices to Google Sheets, using specific invoice data or keywords as triggers to ensure your financial records are always accurate and up-to-date. It uses a webhook to capture every new or updated invoice and logs the essential details into a designated Google Sheet. Perfect for creating custom reports, data backups, or a real-time dashboard of your accounts receivable. Use Cases Financial Reporting:** Create a simple, shareable Google Sheet for team members who don't have QuickBooks access. Data Backup:** Maintain a secure, independent log of all your invoices outside of the QuickBooks ecosystem. Custom Dashboards:** Use the Google Sheet as a data source for tools like Google Data Studio or Grafana to build custom financial dashboards. Auditing:** Easily track the history and status of all invoices in a simple, searchable spreadsheet format. How it Works 1. Instant Webhook Trigger: The workflow activates the moment an invoice is created or updated in QuickBooks. The QuickBooks webhook sends a notification to n8n, kicking off the process in real time. 2. Fetch Full Invoice Details: The initial webhook notification only contains the invoice ID. This node uses that ID to make a call back to the QuickBooks API and retrieve the complete invoice data, including customer name, due date, and more. 3. Format Key Data: A simple Code node cleans up the data fetched from QuickBooks. It extracts only the fields you need—ID, Domain, Customer Name, and Due Date—and structures them perfectly for the next step. 4. Append or Update in Google Sheets: The final node connects to your Google Sheet and uses the powerful "Append or Update" operation. If the ID of the invoice doesn't exist in the sheet, it adds a new row. If the ID already exists, it updates the existing row with the latest information. This ensures your Google Sheet is always a perfect mirror of your QuickBooks invoice data, preventing duplicates and keeping everything current. Setup Instructions For this workflow to run successfully, follow these setup steps: 1. Credentials: QuickBooks: Connect your QuickBooks account credentials to n8n. Google: Connect your Google account using OAuth2 credentials. Ensure the Google Sheets and Google Drive APIs are enabled. 2. QuickBooks Webhook Configuration: Activate the workflow. Copy the Production URL from the Webhook node. In your Intuit Developer Portal, go to the webhooks section for your app. Paste the URL and subscribe to Invoice events (e.g., Create, Update). 3. Google Sheet Setup: Create a Google Sheet for your invoice data. Crucially, create the following headers in the first row of your sheet: -ID -Domain -Customer Name -Due Date 4. Node Configuration: In the Append or update row in sheet node, select your Google Sheet document and the specific sheet name from the dropdown lists. The columns should map automatically if you've set up the headers correctly. Connect with us Website: https://www.intuz.com/cloud/stack/n8n Email: getstarted@intuz.com LinkedIn: https://www.linkedin.com/company/intuz Get Started: https://n8n.partnerlinks.io/intuz
by damo
Overview This workflow leverages the KIE. AI Veo3 model to generate AI videos from simple text descriptions. Users interact via a form interface, inputting a prompt (e.g., a scene description), and the system automatically submits the request to the KIE. AI API, monitors the generation status in real time, and retrieves the final video output. It's ideal for content creators, marketers, or developers exploring text-to-video AI creation, supporting intelligent video generation with minimal setup. Prerequisites A KIE. AI account and API key: Sign up at KIE.AI to obtain your free or paid API key. An active n8n instance (cloud or self-hosted) with HTTP Request and form submission capabilities. Basic knowledge of AI prompts for video generation to achieve optimal results. Setup Instructions Obtain API Key: Register at KIE. AI and generate your API key. Store it securely—do not share it publicly. Configure the Form: In the "On Form Submission" node, ensure fields like "prompt" (for video description) and "api_key" are set up. Example prompt: "A serene mountain landscape at sunset with birds flying." Test the Workflow: Click "Execute Workflow" in n8n. Access the generated form URL, submit your prompt and API key. The workflow will poll the API every 10 seconds until the video is ready, then display the results. Handle Outputs: The final node formats and displays the video file URL for download or embedding. Customization Tips Enhance Prompts**: Include specifics like duration, style (e.g., realistic, animated), actions, and visual elements to improve AI video quality. Keywords for SEO**: This template focuses on AI video generation, text-to-video models, Veo3 API integration, and automated workflows.
by Agent Studio
Overview This workflow provides Retell agent builders with a simple way to populate dynamic variables using n8n. The workflow fetches user information from a Google Sheet based on the phone number and sends it back to Retell. It is based on Retell's Inbound Webhook Call. Retell is a service that lets you create Voice Agents that handle voice calls simply, based on a prompt or using a conversational flow builder. Who is it for For builders of Retell's Voice Agents who want to make their agents more personalized. Prerequisites Have a Retell AI Account Create a Retell agent Purchase a phone number and associate it with your agent Create a Google Sheets - for example, make a copy of this one. Your Google Sheet must have at least one column with the phone number. The remaining columns will be used to populate your Retell agent’s dynamic variables. All fields are returned as strings to Retell (variables are replaced as text) How it works The webhook call is received from Retell. We filter the call using their whitelisted IP address. It extracts data from the webhook call and uses it to retrieve the user from Google Sheets. It formats the data in the response to match Retell's expected format. Retell uses this data to replace dynamic variables in the prompts. How to use it See the description for screenshots! Set the webhook name (keep it as POST). Copy the Webhook URL (e.g., https://your-instance.app.n8n.cloud/webhook/retell-dynamic-variables) and paste it into Retell's interface. Navigate to "Phone Numbers", click on the phone number, and enable "Add an inbound webhook". In your prompt (e.g., "welcome message"), use the variable with this syntax: {{variable_name}} (see Retell's documentation). These variables will be dynamically replaced by the data in your Google Sheet. Notes In Google Sheets, the phone number must start with '+. Phone numbers must be formatted like the example: with the +, extension, and no spaces. You can use any database—just replace Google Sheets with your own, making sure to keep the phone number formatting consistent. 👉 Reach out to us if you're interested in analysing your Retell Agent conversations.
by Anurag
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Description This workflow automates document processing and structured table extraction using the Nanonets API. You can submit a PDF file via an n8n form trigger or webhook—the workflow then forwards the document to Nanonets, waits for asynchronous parsing to finish, retrieves the results (including header fields and line items/tables), and returns the output as an Excel file. Ideal for automating invoice, receipt, or order data extraction with downstream business use. How It Works A document is uploaded (via n8n form or webhook). The PDF is sent to the Nanonets Workflow API for parsing. The workflow waits until processing is complete. Parsed results are fetched. Both top-level fields and any table rows/line items are extracted and restructured. Data is exported to Excel format and delivered to the requester. Setup Steps Nanonets Account: Register for a Nanonets account and set up a workflow for your specific document type (e.g., invoice, receipt). Credentials in n8n: Add HTTP Basic Auth credentials in n8n for the Nanonets API (never store credentials directly in node parameters). Webhook/Form Configuration: Option 1: Configure and enable the included n8n Form Trigger node for document uploads. Option 2: Use the included Webhook node to accept external POSTs with a PDF file. Adjust Workflow: Update any HTTP nodes to use your credential profile. Insert your Nanonets Workflow ID in all relevant nodes. Test the Workflow: Enable the workflow and try with a sample document. Features Accepts documents via n8n Form Trigger or direct webhook POST. Securely sends files to Nanonets for document parsing (credentials stored in n8n credentials manager). Automatically waits for async processing, checking Nanonets until results are ready. Extracts both header data and all table/line items into a tabular format. Exports results as an Excel file download. Modular nodes allow easy customization or extension. Prerequisites Nanonets account** with workflow configured for your document type. n8n** instance with HTTP Request, Webhook/Form, Code, and Excel/Spreadsheet nodes enabled. Valid HTTP Basic Auth credentials** saved in n8n for API access. Example Use Cases | Scenario | Benefit | |-----------------------|--------------------------------------------------| | Invoice Processing | Automated extraction of line items and totals | | Receipt Digitization | Parse amounts and charges for expense reports | | Purchase Orders | Convert scanned POs into structured Excel sheets | Notes You must set up credentials in the n8n credentials manager—do not store API keys directly in nodes. All configuration and endpoints are clearly explained with inline sticky notes in the workflow editor. Easily adaptable for other document types or similar APIs—just modify endpoints and result mapping.
by Alex Kim
Automate Video Creation with Luma AI Dream Machine and Airtable (Part 2) Description This is the second part of the Luma AI Dream Machine automation. It captures the webhook response from Luma AI after video generation is complete, processes the data, and automatically updates Airtable with the video and thumbnail URLs. This completes the end-to-end automation for video creation and tracking. 👉 Airtable Base Template 👉 Tutorial Video Setup 1. Luma AI Setup Ensure you’ve created an account with Luma AI and generated an API key. Confirm that the API key has permission to manage video requests. 2. Airtable Setup Make sure your Airtable base includes the following fields (set up in Part 1): Use the Airtable Base Template linked above to simplify setup. Generation ID** – To match incoming webhook data. Status** – Workflow status (e.g., "Done"). Video URL** – Stores the generated video URL. Thumbnail URL** – Stores the thumbnail URL. 3. n8n Setup Ensure that the n8n workflow from Part 1 is set up and configured. Import this workflow and connect it to the webhook callback from Luma AI. How It Works 1. Webhook Trigger The Webhook node listens for a POST response from Luma AI once video generation is finished. The response includes: Video URL – Direct link to the video. Thumbnail URL – Link to the video thumbnail. Generation ID – Used to match the record in Airtable. 2. Process Webhook Data The Set node extracts the video data from the webhook response. The If node checks if the video URL is valid before proceeding. 3. Store in Airtable The Airtable node updates the record with: Video URL – Direct link to the video. Thumbnail URL – Link to the video thumbnail. Status – Marked as "Done." Uses the Generation ID to match and update the correct record. Why This Workflow is Useful ✅ Automates the completion step for video creation ✅ Ensures accurate record-keeping by matching generation IDs ✅ Simplifies the process of managing and organizing video content ✅ Reduces manual effort by automating the update process Next Steps Future Enhancements** – Adding more complex post-processing, video trimming, and multi-platform publishing.