by System Admin
Tagged with: , , , ,
by System Admin
Tagged with: , , , ,
by System Admin
Tagged with: , , , ,
by System Admin
Tagged with: , , , ,
by Mehedi Ahamed
This workflow automates image processing using VLM Run, extracting signed URLs, downloading results, and distributing them via multiple channels (Google Drive & Telegram). ✅ Key Features Upload image files through a Form Trigger. Process images through two VLM Run agents simultaneously: Segmentation Agent → extracts objects. Detection Agent → generates bounding boxes. Webhooks capture completed results asynchronously. Arifact Node** download the images. Downloaded images are automatically: Uploaded to Google Drive Sent to a Telegram chat ⚙️ Workflow Flow User Uploads File → Form Trigger node VLM Run Agents → Segmentation & Detection agents Webhook Nodes → Receive processed results Artifact Node → Download the artifacts Distribution Nodes → Upload to Google Drive & Telegram 📌 Notes Ensure Google Drive OAuth2 credentials have upload permissions. Telegram Bot token and chat ID must be configured correctly. Workflow allows multi-channel sharing of images automatically. ⚠️ Community Node Disclaimer > This workflow uses VLM Run node
by Garri
Description The Instagram Downloader workflow allows users to download Instagram videos or Reels directly through a Telegram Bot. Simply send an Instagram link to the bot, and it will process the link via a third-party API to fetch the highest quality video, then send it back to your Telegram chat. How It Works Telegram Trigger The workflow starts when the bot receives an Instagram link from a user. HTTP Request – URL Download The link is sent to the API https://www.mediadl.app/api/download to retrieve video metadata. Delay Waits a few seconds to ensure the API response is ready. Filtering URL Only Extracts the direct video file URL from the API result. Delay Adds a short pause to prevent connection errors during download. HTTP Request – Proxy Download Downloads the MP4 video file directly from the filtered URL. Send Video to Telegram Sends the downloaded video back to the user in Telegram. How to Set Up Create & Configure a Telegram Bot Open Telegram, search for BotFather. Send /newbot → choose a bot name & username. Copy the provided Bot Token. Prepare Your n8n Environment Log in to n8n (self-hosted or n8n Cloud). Create Telegram API Credentials using your Bot Token. Import the Workflow In n8n, click Import and select Instagram_Downloader.json. Configure Telegram Nodes Connect your Telegram API credentials in the Telegram Trigger and Send Video nodes. Configure HTTP Request Nodes Ensure the URL and headers in URL Download and Download nodes are correct (already pre-configured). Set responseFormat to file in the final download node. Activate & Test Toggle Activate. Send an Instagram link to your bot to test.
by Javier Quilez Cabello
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. How it works This workflow automates the registration of event participants in SinergiaCRM from a Google Sheets spreadsheet. A Google Sheets Trigger watches for new rows with pending registrations. The flow checks if the participant already exists in SinergiaCRM by NIF (national ID). If the contact exists, it creates a relationship and registers them for an event. If the contact doesn’t exist, it first creates the contact, then adds the relationship and event registration. Finally, it marks the row as "Processed" in the original spreadsheet to avoid duplicate entries. Set up steps Connect your Google Sheets and SinergiaCRM accounts using OAuth credentials. Replace the sample Google Sheet ID and worksheet name with your own. Ensure the spreadsheet contains the following columns: First name, Last name, NIF, Email, Event ID, Relation type, Registration date, and Relation date. Add the appropriate values in the "To CRM" and "Processed" columns to control processing logic. Review sticky notes inside the workflow for additional guidance and customization tips.
by InfraNodus
Augment AI chatbot prompts with a knowledge graph reasoning ontology and improve the quality of responses with Graph RAG. In this workflow, we augment the original prompt using the InfraNodus GraphRAG system that will extract a reasoning ontology from a graph that you create (or that you can copy from our repository of public graphs). This additional reasoning logic will improve the user's prompt and make it more descriptive and closely related to the logic you want to use. As the next step, you can send it back to the same graph to generate a high-quality response using Graph RAG or to another graph (or AI model) to apply one type of knowledge in a completely different field. How it works Receives a request from a user (via n8n or a publicly available URL chat bot, you can also connect it to Telegram Sends the request to the knowledge graph in your InfraNodus account that contains a reasoning ontology represented as a knowledge graph. Reformulates the original prompt to include the reasoning logic provided. Sends the request to the knowledge graph in your InfraNodus account (same as the previous one or a new one for cross-disciplinary research) to retrieve a high-quality response using GraphRAG Special sauce: InfraNodus will build a graph from your augmented prompt, then overlap it on the knowledge graph you want to inquire, traverse this graph based on the overlapped parts and extended relations, then retrieve the necessary part of the graph and include it in the context to improve the quality of your response. This helps InfraNodus grasp the relations and nuances that are not usually available through standard RAG. How to use • Just get an InfraNodus API key and add it into your Prompt Augmentation and Knowledge Base InfraNodus HTTP nodes for authentication • Then provide the name of the graphs you want to be using for prompt augmentation and retrieval. Note, these can be two different graphs if you want to apply a reasoning logic from one domain in another (e.g. machine learning in biology or philosophy in electrical engineering). Support If you wan to create your own reasoning ontology graphs, please, refer to this article on generating your own knowledge graph ontologies. You may also be interested to watch this video that explains the logic of this approach in detail: Help article on the same topic: Using knowledge graphs as reasoning experts.
by Sk developer
📞 Phone Number Validator with Google Sheets Validate and enrich phone numbers from Google Sheets using the phone number validator API. 📌 Use Case: Contact Validation & Enrichment Automatically check if phone numbers are valid and enrich them with metadata (country, location, timezone). Ideal for CRMs, lead management, and contact cleanup workflows. 🗂️ Google Sheets Columns | Column Name | Description | |-------------|-------------| | phone | The original phone number to validate (input column). | | is_valid | Result from API indicating if the phone number is valid (true / false). | | country | Country where the phone number is registered (e.g. "US"). | | location | More specific location info, such as city or region. | | timezone | The primary timezone associated with the phone number. | 🎯 Benefits ✅ Accurate Contact Data – Identify invalid or fake phone numbers automatically. 🌐 Geolocation Enrichment – Add country, location, and timezone for better segmentation. 🔁 Full Automation – No manual lookups or copying data between tools. 📊 Live Google Sheets Sync – Enriched data is updated directly into your spreadsheet. 🧠 Workflow Nodes Explained | Node | Purpose | |------|---------| | 🟢 Manual Trigger | Starts the workflow manually from n8n. | | 📄 Google Sheets (Read) | Fetches phone numbers from your spreadsheet using a Service Account. | | 🔁 Split In Batches | Loops over each row one at a time to handle individual API requests. | | 🌐 HTTP Request | Sends phone number to phone number validator via RapidAPI and receives validation + metadata. | | 📥 Google Sheets (Update) | Writes the response back into the matching row using the phone field. | 🛰️ API Used: phone number validator We use the phone number validator API from RapidAPI to: Validate phone numbers (real or fake?) Identify the country, location, and timezone > It’s fast, reliable, and great for cleaning large datasets or qualifying leads before outreach. 🧰 Prerequisites 📄 A Google Sheet with a column named phone 🔐 RapidAPI key with access to phone number validator 🔧 Google Service Account credentials set up in n8n 🚀 How to Use 🔗 Link your Google Sheet and configure authentication 🔑 Add your RapidAPI key in the HTTP node headers ▶️ Click "Execute Workflow" 🧠 Each phone number is validated and enriched 📊 Results are written back to your Google Sheet 📎 Tags phone validation, rapidapi, google sheets, data enrichment, phone number validator, crm automation, lead cleaning, timezone lookup
by Piotr Sobolewski
How it works This workflow automates the entire process of drafting and publishing blog posts to your WordPress site using advanced AI. It streamlines your content creation by: Generating engaging blog post titles based on your chosen topic. Crafting comprehensive blog post bodies (introduction, main points, conclusion) with professional formatting. Automatically publishing the generated content as a new post on your WordPress website. Save hours of manual writing and accelerate your content strategy with this intelligent automation. Set up steps Getting this workflow ready is straightforward and typically takes around 15-20 minutes. You'll need to: Obtain API keys for your preferred AI service (e.g., OpenAI, Google AI). Provide your WordPress website's URL and login credentials. Optionally, customize the AI prompts to match your specific content style or requirements. All detailed setup instructions and specific configuration guidance are provided within the workflow itself using sticky notes.
by Viktor Klepikovskyi
n8n Asynchronous Workflow with Wait Node POC This template contains a two-part workflow designed to demonstrate a proof-of-concept for asynchronous and parallel execution of tasks in n8n. Purpose The purpose of this template is to showcase how you can run multiple long-running tasks simultaneously without blocking your main workflow. It utilizes the "Wait For Sub-workflow Completion" option and the "Wait" node to effectively manage concurrent execution and collect results from sub-workflows via webhooks. This pattern is ideal for use cases involving batch processing or any scenario where a workflow needs to trigger multiple independent tasks and wait for all of them to report back. Setup Instructions Import: Import both the "Main Orchestrator" and "Asynchronous Worker" workflows into your n8n instance. Link Workflows: In the "Main Orchestrator" workflow, ensure the "Execute Workflow" node is correctly configured to call the "Asynchronous Worker" workflow. You can select it by its name from the dropdown menu. Configure: The template is pre-configured to run two parallel tasks with different wait durations to simulate a real-world scenario. You can adjust the parameters on the "Execute Workflow" node to test different wait times. Execution: Execute the "Main Orchestrator" workflow. You will see the workflow pause at the "Wait" nodes while the "Asynchronous Worker" workflows run in the background. Once they complete, they will call back via the webhook, allowing the main workflow to resume and summarize the results. For a detailed walkthrough of how this template works and an explanation of the underlying concepts, please read the full blog post here
by Mihail Morosan
Get the latest news, from Kagi, with a workflow that lets you filter by news category. Feed the results in your voice assistant automations to get on-demand news. Or leverage LLM models to create daily summaries from the headlines you retrieved. How it works This workflow takes a category name, from the ones available on Kagi News, then uses the Kagi News API to get all of the day's stories in that category. It then does a bit of filtering, to make it easier to manipulate. But you can skip or change that to your liking. How to use To test it, simply change the pinned data in the Start node, particularly the category field. You can use such examples as World, UK or Technology. Unsure as to what options for category there are? Just run the workflow and check the output of the Split Categories node! It will list all categories available. Take the value from categoryName. Things to consider I used categoryName as the input instead of categoryId for one reason: to make it easier for LLMs to populate that field. If this doesn't work for you, it should be quite easy to change. It is also a single category at a time. If you want to get stories from more categories at once, you can take an array as input in Start, then filter on the categories list containing your entries, rather than an exact match. Finally, you will have to merge all calls to Split out stories after each call to the API. Requirements None beyond an internet connection for your n8n instance. There is no API access token needed or any authorisation of any kind.