Integrate Split Out with 500+ apps and services

Who this template is for This template is for every engineer who wants to automate their code reviews or just get a 2nd opinion on their PR. How it works This workflow will automatically review your changes in a Gitlab PR using the power of AI. It will trigger whenever you comment with +0 to a Gitlab PR, get the code changes, analyze them with GPT, and reply to the PR discussion. Set up Steps Set up webhook of note_events in Gitlab repository (see here on how to do it) Configure ChatGPT credentials Note "+0" in MergeRequest to trigger automatic review by ChatGPT

This n8n workflow simplifies the process of removing backgrounds from images stored in Google Drive. By leveraging the PhotoRoom API, this template enables automatic background removal, padding adjustments, and output formatting, all while storing the updated images back in a designated Google Drive folder. This workflow is very useful for companies or individuals that are spending a lot of time into removing the background from product images. How it Works The workflow begins with a Google Drive Trigger node that monitors a specific folder for new image uploads. Upon detecting a new image, the workflow downloads the file and extracts essential metadata, such as the file size. Configurations are set for background color, padding, output size, and more, which are all customizable to match specific requirements. The PhotoRoom API is called to process the image by removing its background and adding padding based on the settings. The processed image is saved back to Google Drive in the specified output folder with an updated name indicating the background has been removed. Requirements PhotoRoom API Key Google Drive API Access Customizing the Workflow Easily adjust the background color, padding, and output size using the configuration node. Modify the output folder path in Google Drive or replace Google Drive with another storage service if needed. For advanced use cases, integrate further image processing steps, such as adding captions or analyzing content using AI.

Use case This workflow automatically turns any RSS feed into a newsletter. It send an email every time a new post is published to an RSS feed in the last hour. I have been using this personally to follow Derek Sivers and Anil Dash, who don't have newsletters. Check them out 😉 How to setup Add your email and email creds Add the RSS feed URLs you want to follow How to adjust this template Add the feeds you want to follow. It does not have to be just email. Why not get a telegram message? Or Slack message? Ah the power of n8n 🚀

Using the Systeme API can be challenging due to its pagination settings and low rate limit. This requires a bit more knowledge about API requests than a beginner might have. This template provides preconfigured HTTP Request nodes to help you work more efficiently. Pagination settings, item limits, and rate limits are all configured for you, making it easier to get started. How to configure Systeme.io credentials The Systeme API uses the Header Auth method. So create a Header Auth credential in your n8n with the name "X-API-Key". . Check out my other templates 👉 https://n8n.io/creators/solomon/

Use Case When trying to maximize your outreach, website visitors are often an overlooked source of qualified new leads. This workflow allows your to track and enrich new website visitors and saves them to a Google Sheet once they meet a pre-defined criteria. What this workflow does This workflow fires once a day and gets all your leads saved in Leadfeeder. It then takes the leads that meet a pre-defined engagement criteria, e.g. that they visited your site 3 times, and enriches them additionally with Clearbit. From there it filters the leads again by a criteria on the company, e.g. a minimum employee count, and saves matching leads into a Google Sheet document. Setup Add your Leedfeeder credentials. The name should be Authorization and the value Token token=yourapitoken. You can find your token via Settings -> Personal -> API-Token Add your Google Sheet credentials Save the Leedfeeder account names you want to use in the Setup node Copy the Google Sheets Template and add its URL to the Setup node How to adjust this to your needs Adjust and/or remove the engagement and company criteria Add more ways to enrich a company Potential ideas to enhance the use of this workflow Automatically reach out to users that meet the criteria / that get added to the sheet Create a workflow that finds the right employee in companies that are identified by this workflow

How it works This template takes a YouTube video ID and identifies potentially engaging moments based on the intensity of specific timestamps 👇 Ideal for vloggers and YouTube content creators, it serves as a foundation for various automations to streamline content calendars or highlight popular moments in your videos. You can leverage it for: Automatic processes to analyze YouTube videos and create sizzle reels or clips for social media, particularly effective for microcontent strategies like those endorsed by Gary Vee. Instant alerts via Slack, Telegram, Email, or WhatsApp when significant moments occur in your videos. Utilizing transcripts of these moments with AI to refine content ideas or brainstorm chatbots in your editorial workflow. Example response from the Workflow-as-an-API A GET request to {your instance URL}/webhook/youtube-engaging-moments-extractor?ytID=IZsQqarWXtYy returns 👇 The workflow generates multiple moments; the screenshot above shows a truncated version. Not all videos contain timestamp intensity data, the workflow handles this case as well 👇 How to use Import the template into your n8n workspace or self-hosted instance, then activate the workflow. Open the Webhook trigger node and copy the Production URL. In a web browser or any tool capable of consuming HTTP Requests (e.g., native code, Bubble app, n8n workflow, another automation tool, Postman, etc.), pass along the URL parameter ?ytID={youtube video ID} when invoking the API endpoint. Your URL should resemble something like https://acme.app.n8n.cloud/webhook/youtube-engaging-moments-extractor?ytID=IZsQqarWXtYy. Keep in mind This workflow relies on an unofficial YouTube API graciously hosted for free by the folks at lemnoslife.com. It's not recommended for high-volume production usecases.

This automation syncs your Invoice PDFs from Stripe to a (AWS) S3 Bucket each month, in a folder of your choice, with the following subPath: yourFolder/invoiceYear/invoiceMonth/fileName Fill in your Credentials and Settings in the Nodes marked with "*". You can adjust this Workflow to your needs. You can also override the yearand month in the ENV* Node for manual syncs. It will sync every Invoice PDF which created-date is greater then the provided year and month. It will automatically set the day to the first day of the desired month. Enjoy the Workflow! ❤️ https://let-the-work-flow.com Workflow Automation & Development

Purpose This workflow enables you to listen to your recent favorites in very hight quality offline without sacrificing all of your storage. How it works This workflow automatically creates a playlist in Spotify named "Downloads" which periodically gets updated so it always contains only a defined amount of the latest liked songs. This enables only the Downloads playlist to set for automatic downloading and thus free up space on the device. Setup The workflow is ready to go. Just select your Spotify credentials and activate the workflow. In Spotify just enable automatic downloads on the automatically created Downloads folder after the first workflow run. Current limitations This setup currently supports a maximum of 50 songs in the Downloads Playlist. This is due to the paylod limits defined by Spotify encountered in the Get liked songs node. Implementing batching would solve the issue.

What it does The workflow is a simple yet efficient way to automate the process of indexing your website on Google using the Google Indexing API. How it works It works by extracting information from your sitemap, converting it into a JSON file, and looping through each URL to submit it for indexing. Here's a brief rundown of the workflow: The workflow can be triggered manually via the "Execute Workflow" button or scheduled to run at a specific time using the "Schedule Trigger" node. The sitemap of your website is fetched using the "sitemap_set" node with a HTTP Request to the sitemap URL. This XML sitemap is then converted into a JSON file using the "sitemap_convert" node. The "sitemap_parse" node splits the JSON file into individual URLs. The "url_set" node then prepares each URL to be sent to the Google Indexing API. A loop is created using the "loop" node to process each URL individually and make a POST request to Google Indexing API indicating that the URL has been updated. If the POST request is successful and the URL has been updated, the workflow waits for 2 seconds before moving to the next URL. In case the daily limit for the Google Indexing API is reached (200/day by default), an error message is triggered using the "Stop and Error" node. Before you use the workflow Activate the indexing API Create an account with Google Cloud Platform > Console and then create a new project Search for the Indexing API in the Library Activate the API Create a Service Account and get credentials Open the Service accounts page. If prompted, select a project. Click add Create Service Account, enter a name and description for the service account. You can use the default service account ID, or choose a different, unique one. When done click Create. On the Grant users access to this service account screen, scroll down to the Create key section. Click add Create key. In the side panel that appears, select the JSON format Click Create. Your new public/private key pair is generated and downloaded to your machine. Open the file and copy the private key. Add the credentials in the url_index node Add the user as owner of the site Beware, for each site you need to add the user as a owner like this: Set your sitemap Open the sitemap_set node and add the url to your sitemap. Now you should be able to ensure that Google is always up-to-date with the latest content on your website, improving your website's visibility and SEO rankings, have fun!

This workflow with AI agent is designed to navigate through the page to retrieve specific type of information (in this example: social media profile links). The agent is equipped with 2 tools: text tool:** to retrieve all the text from the page, URLs tool:** to extract all possible links from the page. 💡 You can edit prompt and JSON schema connected to the agent in order to return other data then social media profile links. 👉 This workflow uses Supabase as storage (input/output). Feel free to change it to any other database of your choice. 🎬 See this workflow in action in my YouTube video. How it works? The workflow uses the input URL (website) as a starting point to retrieve the data (e.g. example.com). Using the "URLs tool", the agent is able to retrieve all links from the page and navigate to them. For example, if you want to retrieve contact information, agent will try to find a subpage that might contain this information (e.g. example.com/contact) and extract the information using the text tool. Set up steps Connect database with input data (website addresses) or pin sample data to trigger node. Configure the crawling agent to retrieve the desired data (e.g. modify prompt and/or parsing schema). Set credentials for OpenAI. Optionally: split agent tools to separate workflows. If you like this workflow, please subscribe to my YouTube channel and/or my newsletter.

Sync your Google Sheets Data with your Postgres database table, requiring minimal adjustments. Follow these steps: Retrieve Data: Pull data from Google Sheets and PostgreSQL. Compare Datasets: Identify differences, focusing on new or updated entries. Update PostgreSQL: Apply changes to ensure both platforms mirror each other. Automate this process to regularly synchronize data. Before starting, grant necessary access to both Google Sheets and PostgreSQL, and specify the data details for synchronization. This streamlined workflow enhances data consistency across platforms. This example is a one-way synchronization from Google Sheets into your Postgres. With small adjustments, you can make it the other way around, or 2-way.

How it works: The workflow starts by sending a request to a website to retrieve its HTML content. It then parses the HTML extracting the relevant information The extracted data is storted and converted into a CSV file. The CSV file is attached to an email and sent to your specified address. The data is simultaneously saved to both Google Sheets and Microsoft Excel for further analysis or use. Set-up steps: Change the website to scrape in the "Fetch website content" node Configure Microsoft Azure credentials with Microsoft Graph permissions (required for the Save to Microsoft Excel 365 node) Configure Google Cloud credentials with access to Google Drive, Google Sheets and Gmail APIs (the latter is required for the Send CSV via e-mail node).

🚀 Supercharge Your Website Indexing with This Powerful n8n Workflow! 🌐 Google page indexing too slow? Tired of manually clicking through each page in the Google Search Console? 😴 Say goodbye to that tedious process and hello to automation with this n8n workflow! 🎉 **NB: this workflow was tested with sitemap.xml generated by Ghost CMS and WordPress. Reach out to Eduard if you need help adapting this workflow to your specific use-case!** ⚙️ How this automation works 📅 The workflow runs on a schedule or when you click "Test workflow". 🌐 It fetches the website's primary sitemap.xml and extracts all the content-specific sitemaps (this is a typical structure of the sitemap). 📑 Each content-specific sitemap is then parsed to retrieve the individual page data. 🔄 The extracted page data is converted to JSON format for easy manipulation. 🗃️ The lastmod (last modified date) and loc (page URL) fields are assigned to each page entry to ensure compliance with the Sitemap protocol. 🔀 The page entries are sorted by the lastmod field in descending order (newest to oldest). 🔁 The workflow then loops over each page entry and performs the following steps: 🔍 Checks the URL metadata in the Google Indexing API. ✅ If the page is new or has been updated since the last indexing request, it sends a request to the Google Indexing API to update the URL. ⏳ Wait a sec and move on with the next page. 🌟 Benefits ⏰ Save time by automating the indexing process. 🎯 Ensure all your website pages are consistently indexed by Google. 🚀 Improve your website's visibility and search engine rankings. 🛠️ Customize the workflow to fit your specific CMS and requirements. 🔧 Getting started To start using this powerful n8n workflow, follow these steps: ☑️ Make sure to verify the website ownership in the Google Search Console. 👨‍💻 Import the workflow JSON into your n8n instance. Edit the Get sitemap.xml node and update the URL with your website's valid sitemap.xml 🔑 Set up the necessary credentials for the Google Indexing API. 🎚️ Adjust the schedule trigger to run the workflow at your desired frequency. 🎉 Sit back and let the workflow handle the indexing process for you! Ready to take your website indexing to the next level? 🚀 Try this workflow now and see the difference it makes! 😊 ⚠️ IMPORTANT NOTE 1 Need help with connecting Google Cloud Platform to n8n? Check out our article on connecting Google Sheets to n8n. The process is mainly the same. When activating Google APIs, make sure to add Web Search Indexing API. Also, in the credential page of n8n, add the https://www.googleapis.com/auth/indexing scope: Check out Yulia's page for more n8n workflows! ⚠️ IMPORTANT NOTE 2 Free Google Cloud Platform account allows (re)indexing only 200 pages per day. If your website has more, then the workflow will automatically fail on quota limit ⛔. Next day it will skip the previously added items and continue with remaining pages. Example:* Assuming you have a free Google account, 500 pages on your website and they don't change for 3 days: On the first day 200 pages will be added for indexing and the workflow will fail due to quota limits. On the second day, the workflow will check 200 pages again and skip them (because the date of re-indexing is later then the page last modified date). The next 200 pages will be added to indexing. Workflow will fail again due to quota limits. On the third day 400 pages will be checked and skipped, the last 100 pages will be added for indexing and the workflow finishes successfully.

Workflow Information 📌 Purpose 🎯 The intention of this workflow is to integrate New Shopify Orders into MS Dynamics Business Central: Point-of-Sale (POS):** POS orders will be created in Business Central as Sales Invoices given no fulfillment is expected. Web Orders:** This type of orders will be created as Business Central Sales Orders. How to use it 🚀 Edit the "D365 BC Environment Settings" node with your own account values (Company Id, Tenanant Id, Tax & Discount Items). Go to the "Shopify" node and edit the connection with your environment. More help here. Go to the "Lookup Customers" node to edit the Business Central connection details with your environment settings. Set the required filters on the "Shopify Order Filter" node. Edit the "Schedule Trigger" node with the required frequency. Useful Workflow Links 📚 Step-by-step Guide/ Integro Cloud Solutions Business Central REST API Documentation Video Demo Need Help? Contact me at: ✉️greg.lopez@integrocloudsolutions.com 📥 https://www.linkedin.com/in/greg-lopez-08b5071b/

This n8n workflow demonstrates a simple multi-agent setup to perform the task of competitor research. It showcases how using the HTTP request tool could reduce the number of nodes needed to achieve a workflow like this. How it works For this template, a source company is defined by the user which is sent to Exa.ai to find competitors. Each competitor is then funnelled through 3 AI agents that will go out onto the internet and retrieve specific datapoints about the competitor; company overview, product offering and customer reviews. Once the agents are finished, the results are compiled into a report which is then inserted in a notion database. Check out an example output here: https://jimleuk.notion.site/2d1c3c726e8e42f3aecec6338fd24333?v=de020fa196f34cdeb676daaeae44e110&pvs=4 Requirements An OpenAI account for the LLM. Exa.ai account for access to their AI search engine. SerpAPI account for Google search. Firecrawl.dev account for webscraping. Notion.com account for database to save final reports. Customising the workflow Add additional agents to gather more datapoints such as SEO keywords and metrics. Not using notion? Feel free to swap this out for your own database.

This workflow is a building block designed to be called from other workflows via an Execute workflow node. When called from another workflow, and given the JSON input of a "pulse" field with the ID to pull from monday, this workflow will return: The items name and ID All column data, indexable by the column name All column data, indexable by the column's ID string All board relation columns, with their data and column values All subitems, with their data and column values For example: ++Prerequisites++ A monday.com account and credential A workflow that needs to get detailed data from a monday.com row The pulse id of the monday.com row to retreive data from. ++Setup++ Import the workflow Configure all monday nodes with your credentials and save the workflow Copy the workflow ID from it's URL In a different workflow, add an Edit Fields node, to output the field "pulse", with the monday item you want to retrieve. Feed the Edit Fields node with your pulse into an Execute workflow node, and paste the workflow ID from above into it This "pulse" field will tell the workflow what pulse to retreive. This can be populated by an expression in your workflow There is an example of the Edit Fields and Execute Workflow nodes in the template

Purpose of workflow: The purpose of this workflow is to automatically transform complex, lengthy PDFs into concise, insightful blog posts. This process aims to make dense information more accessible and understandable to a broader audience. How it works: Multi-agent team: Working together to transform PDF to insightful blog Content Analyst: Extracts key information and structure from the PDF. Project Planner: Organizes the workflow and ensures efficient processing. Writers: Multiple agents that craft engaging content based on the analyzed information. Editor: Polishes the final output for accuracy, reliability, and readability. Step by step User inputs parameters via a n8n form (tone, word count, sections, PDF file). System extracts text from the PDF. Content Analyst AI agent analyzes the extracted text, identifying main topics and key points. Project Planner AI agent organizes the workflow, creating a structure for the blog post. Multiple Writer AI agents (based on the number of sections specified) each write a portion of the blog post. Editor AI agent combines all sections and polishes the final draft. Generates a title for the blog post. Final content is uploaded to a publishing Ghost platform

Use Case Research search engine rankings for SEO analysis: You need to track keyword rankings for your website You want to analyze competitor positions in search results You need data for SEO competition analysis You want to monitor SERP changes over time What this Workflow Does The workflow uses ScrapingRobot API to fetch Google search results: Retrieves SERP data for your target keywords Captures URL rankings and page titles Processes up to 5000 searches with free account Organizes results for SEO analysis Setup Create a ScrapingRobot account and get your API key Add your ScrapingRobot API key to the HTTP Request node's GET SERP token parameter Either connect your keyword database (column name "Keyword") or use the "Set Keywords" node Configure your preferred output database connection How to Adjust it to Your Needs Modify keyword source to pull from different databases Adjust the number of SERP results to capture Customize output format for your reporting needs Made by Simon @ automake.io

Use Case Generate accurate search volume data for SEO keyword research: You have a list of potential keywords to target for your website SEO but don't know their actual search volume You need historical data to identify seasonal trends in keyword popularity You want to assess keyword difficulty to prioritize your content strategy You need data-driven insights for planning your SEO campaigns What this Workflow Does The workflow connects to Google's Keyword Planner API to retrieve keyword metrics for your SEO research: Fetches monthly search volume for each keyword Provides historical trends data for the past 12 months Calculates keyword difficulty scores Delivers competition metrics from Google Ads Setup Fill the Set 20 Keywords with up to 20 Keywords of your choosing in an array e.g. ["keyword 1", "keyword 2",...] Create a Google Ads API account and add credentials to Get Search Data node Replace the Connect to your own database with your own database for the output How to Adjust it to Your Needs Change the Set 20 Keywords node input to a source of your choosing e.g. Airtable database with 20 keywords Connect to output source of your choosing Made by Simon @ automake.io

This n8n workflow demonstrates how to automate indexing of images to build a object-based image search. By utilising a Detr-Resnet-50 Object Classification model, we can identify objects within an image and store these associations in Elasticsearch along with a reference to the image. How it works An image is imported into the workflow via HTTP request node. The image is then sent to Cloudflare's Worker AI API where the service runs the image through the Detr-Resnet-50 object classification model. The API returns the object associations with their positions in the image, labels and confidence score of the classification. Confidence scores of less the 0.9 are discarded for brevity. The image's URL and its associations are then index in an ElasticSearch server ready for searching. Requirements A Cloudflare account with Workers AI enabled to access the object classification model. An ElasticSearch instance to store the image url and related associations. Extending this workflow Further enrich your indexed data with additional attributes or metrics relevant to your users. Use a vectorstore to provide similarity search over the images.

What is this workflow doing? This simple workflow is pulling the latest Euro foreign exchange reference rates from the European Central Bank and responding expected values to an incoming HTTP request (GET) via a Webhook trigger node. Setup no authentication** needed the workflow is ready to use test** the workflow template by hitting the test workflow button and calling the URL in the webhook node optional: choose your own Webhook listening path in the Webhook trigger node Usage There are two possible usage scenarios: get all Euro exchange rates as an array of objects get only a specific currency exchange rate as a single object All available rates Using the HTTP query ?foreign=USD (where USD is one of the available currency symbols) will provide only that specificly asked rate. Response example: {"currency":"USD","rate":"1.0852"} Single exchange rate If no query is provided, all available rates are returned. Response example: [{"currency":"USD","rate":"1.0852"},{"currency":"JPY","rate":"163.38"},{"currency":"BGN","rate":"1.9558"},{"currency":"CZK","rate":"25.367"},{"currency":"DKK","rate":"7.4542"},{"currency":"GBP","rate":"0.85495"},{"currency":"HUF","rate":"389.53"},{"currency":"PLN","rate":"4.3053"},{"currency":"RON","rate":"4.9722"},{"currency":"SEK","rate":"11.1675"},{"currency":"CHF","rate":"0.9546"},{"currency":"ISK","rate":"149.30"},{"currency":"NOK","rate":"11.4285"},{"currency":"TRY","rate":"33.7742"},{"currency":"AUD","rate":"1.6560"},{"currency":"BRL","rate":"5.4111"},{"currency":"CAD","rate":"1.4674"},{"currency":"CNY","rate":"7.8100"},{"currency":"HKD","rate":"8.4898"},{"currency":"IDR","rate":"16962.54"},{"currency":"ILS","rate":"3.9603"},{"currency":"INR","rate":"89.9375"},{"currency":"KRW","rate":"1444.46"},{"currency":"MXN","rate":"18.5473"},{"currency":"MYR","rate":"5.1840"},{"currency":"NZD","rate":"1.7560"},{"currency":"PHP","rate":"60.874"},{"currency":"SGD","rate":"1.4582"},{"currency":"THB","rate":"38.915"},{"currency":"ZAR","rate":"20.9499"}] Further info Read more about Euro foreign exchange reference rates here.

Pull data using the Facebook Graph API and get your Meta Ads insights into your Google Sheets for analysis. Get metrics like impressions, spend, reach, conversions, CTR, and CPC. Automate your data collection. Who is this template for? Marketing professionals looking to analyze Meta Ads data. You can also replace the Google Sheets node for a database node like MySQL or Postgres, and then use your BI tool (Power BI, Looker Studio, Tableau) to analyze the data. How it works Every day at 3am, the flow gets Meta Ads insights from the previous day and saves them to Google Sheets. How to set up All information you need to set up this workflow is already inside the template. Check out my other templates 👉 https://n8n.io/creators/solomon/

Overview This template integrates an IOT multi-button switch (meant for controlling a dimmable light) with Spotify playback functions, via MQTT messages. This isn't likely to work without some tinkering, but should be a good head start on receiving/routing IOT/MQTT messages and hooking up to a Spotify-like API. Requirements An IOT device capable of generating events that can be delivered as MQTT messages through an MQTT Broker e.g. Ikea Strybar remote An MQTT Broker to which n8n can connect and consume messages e.g. Zigbee2MQTT in HomeAssistant A Spotify developer-account (which provides access to API functions via OAuth2 authorization) A Spotify user-account (which provides access to Spotify streamed content, user settings, etc.) Setup Create an MQTT Credential item in n8n and assign it to the MQTT Trigger node Modify the MQTT trigger node to match the topic for your IOT device messages Modify the switch/router nodes to map to the message text from your IOT button (e.g. arrow_left_click, brightness_up_click, etc.) Create a Spotify developer-account (or use the login for a user-account) Create an "App" in the developer-account to represent the n8n workflow Chicken/Egg ALERT: The n8n Spotify Credentials dialog box will display the "OAuth Redirect URL" required to create the App in Spotify, but the n8n Credential item itself cannot be created until AFTER the App has been created. Create a Spotify Credentials item in n8n Open the Settings on the Spotify App to find the required Client ID and Client Secret information. ALERT: Save this before proceeding to the Connect step. Connect the n8n Spotify Credential item to the Spotify user-account ALERT: Expect n8n to open a separate OAuth2 window on authorization.spotify.com here, which may require a login to the Spotify user-account Open each of the HTTP and Spotify nodes, one by one, and re-assign to your Spotify Credential (try not to miss any). (Then, probably, upvote this feature request: https://community.n8n.io/t/select-credentials-via-expression/5150 Modify the variable values in the Globals node to match your own environment. target_spotify_playback_device_name - The name of a playback device available to the Spotify user-account favorite_playlist_name - The name of a playlist to start when one of the button actions is indicated in the MQTT message. Used in example "Custom Function 2" sequence. Notes You're on your own for getting the multi-button remote switch talking to MQTT, figuring out what the exact MQTT topic name is, and mapping the message parts to the workflow (actions, etc.). The next / previous actions are wired up to not transfer control to the target device. This alternative routing just illustrates a different behavior than the remaining actions/functions, which include activation of the target device when required. Some of the Spotify API interactions use the Spotify node in n8n, but many of the available Spotify API functions are limited or not implemented at all in the Spotify node. So, in other cases, a regular HTTP node is used with the Spotify OAuth2 API credential instead. By modifying one of the examples included in the template, it should be possible to call nearly anything the Spotify API has to offer. Spotify+n8n OAuth Mini-Tutorial Definitions The developer-account is the Spotify login for creating a spotify-app which will be associated with a client id and client secret. The user-account is the Spotify login that has permission to stream songs, set up playback devices, etc. ++A spotify-login allows access to a Spotify user-account, or a Spotify developer-account, OR BOTH++ The spotify-app, which has a client id and client secret, is an object created in the developer-account. The app-implementation (in this case, an ++n8n workflow++) uses the spotify-app's credentials (client id / client secret) to call Spotify API endpoints on behalf of a user-account. Using One Spotify Login as Both User and Developer When an n8n Spotify-node or HTTP-node (i.e. an app-implementation) calls a Spotify API endpoint, the Credentials item may be using the client id and client secret from a spotify-app, which was created in a developer-account that is ++one and the same spotify-login as the user-account++. However, it helps to remind yourself that from the Spotify API server's perspective, the developer-account + spotify-app, and the user-account, are ++two independent entities++. n8n Spotify-OAuth2-API Credential Authorization Process The 2 layers/steps, in the process of authorizing an n8n Spotify-OAuth2-API credential to make API calls, are: n8n must identify itself to Spotify as the app-implementation associated with the developer-account/spotify-app by sending the app's credentials (client id and client secret) to Spotify. The Client ID and Client Secret are supplied in the n8n Spotify OAuth2 Credentials UI/dialog-box Separately, n8n must obtain an authorization token from Spotify to represent the permissions granted by the user to execute actions (call API endpoints) on behalf of the user (i.e. access things that belong to the user-account). This authorization for the user-account access is obtained when the "Connect" or "Reconnect" button is clicked in the n8n Spotify Credentials UI/dialog-box (which pops up a separate authorization UI/browser-window managed by Spotify). The Authorization for a given spotify-app stays "registered" in the user-account until revoked. See: https://support.spotify.com/us/article/spotify-on-other-apps/ Direct Link: https://www.spotify.com/account/apps/ More than one user-account can be authorized for a given spotify-app. A particular n8n Spotify-OAuth2-API credential item appears to cache an authorization token for the user-account that was most recently authorized. Up to 25 users can be allowed access to a spotify-app in Developer-Mode, but any user-account other than the one associated with the developer-account must be added by email address at https://developer.spotify.com/dashboard/{{app-credential-id}}/users ALERT: IF the browser running the n8n UI is ALSO logged into a Spotify account, and the spotify-app is already authorized for that Spotify account, the "reconnect" button in the Spotify-OAuth2-API credential dialog may automatically grab a token for that logged in user-account, offering no opportunity to select a different user-account. This can be managed somewhat by using "incognito" browser windows for n8n, Spotify, or both. References n8n Spotify Credentials Docs Spotify Authorization Docs

This n8n workflow template allows you to write WordPress posts by just providing a few keywords. It uses AI technology to write the text and to create the post's featured image. The text includes an introduction, chapters, and conclusions. Each chapter is written independently and this allows you to create also very long articles. The workflow uses technologies provided by Open AI: Chat GPT for the text and Dall-E for the image. I suggest reviewing the created posts before publishing them on your WordPress website. The article generation might take some minutes as each chapter is created independently. Features Easy to use:** Easy web interface to start the generation of the WordPress post AI-powered:** Text and image generation is done by artificial intelligence Long-text ready:** Possibility to create very long articles Configurable:** Possibility to provide as many keywords as you want, to choose the number of chapters and the length of the article Plugs into your WordPress:** Easily integrates with your WordPress website Tweak it as you want:** Fine-tune the Open AI prompts and the workflow as you want Workflow Steps User form:** An n8n form is used to trigger the post creation Settings:** This node is used to set your WordPress URL (which is used later in the workflow) Article structure:** First AI action that writes the introduction, the conclusions, and the chapter structure. Data check:** Check that the data provided by the AI is valid Chapters split/Chapters text:** Splits the data for each chapter in a separate item and generates each chapter's text with AI Content preparation:** Prepares the text for posting merging the introduction, the chapters, and the conclusions. Adds some basic HTML formatting Draft on WordPress:** Creates the draft post on WordPress Featured image:** Creates a featured image and adds it to the post on WordPress User feedback:** Sends a feedback to the user on the n8n form Getting Started To deploy and use this template: Import the workflow into your n8n workspace Set your WordPress URL in the wordpress_url field in the "Settings" node. Include the slash (/) at the end of the URL Set up your Open AI n8n credentials by following this guide. The Open AI credentials are used by the Open AI nodes ("Create post title and structure", "Create chapters text", and "Generate featured image") Set up your WordPress n8n credentials by following this guide. The WordPress credentials are used by the WordPress and HTTP Request nodes ("Post on Wordpress", "Upload media", and "Set image ID for the post"). Pay attention that the "Password" in the WordPress credentials is not the user's password by the Application Password How use the workflow to create a WordPress post Activate the workflow Open the "Form" node and copy the "Production URL". This is the public URL of the form to AI-write the post Open the URL in a browser and fill in the form Wait a few minutes till you get the feedback in the form that the post was created Go to WordPress and check the newly created draft post. Review and publish your post!

This n8n workflow takes Slack conversations and turns them into Calendar events complete with accurate date and times and location information. Adding and removing attendees are also managed automatically. How it works Workflow monitors a Slack channel for invite messages with a "📅" reaction and sends this to the AI agent. AI agent parses the message determining the time, date and location. Using its Location tool, the AI agent searches for the precise location address from Google Maps. Using its Calendar tool, the AI agent creates a Google Calendar invite with the title, description and location address for the user. Back in the Slack channel, others can RSVP to the invite by reacting with the "✅" emjoi. The workflow polls the message after a while and adds the users who have reacted to the Calendar Invite as attendees. Conversely, removing any attendees who have since removed their reaction. Examples Jill: "Hey team, I'm organising a round of Laser Tag (Bunker 51) next Thursday around 6pm. Please RSVP with a ✅" AI: "I've helped you create an event in your calendar https://cal.google.com/..." Jack: "✅" AI: "I've added Jack to the event as an attendee". Requirements Slack channel to attach the workflow OpenAI account to use a GPT model Google Calendar to create and update events Customising the Workflow This workflow can work with other messaging platforms that support reactions or tagging like features such as discord. Don't use Google Calendar? Swap it out for Outlook or your own. Use any combinations of emjoi reactions and add new rules like "RSVP maybe" which could send reminder updates nearer the event date.

How it works This workflow reads a list of URLs every 15 minutes, and sends an HTTP request to every URL on the list. Set up steps Schedule the workflow to run at your desired frequency (default is every 15 minutes). Add your desired URLs to the list. The list should be in the same format as the image below (Don't forget to have single quotes around every URL in the list, and separate each one with a comma!): Turn the workflow ON. Ideas to customize the workflow for your own use cases: Change the HTTP method Add headers Add a request body

This n8n template is one of a 3-part series exploring use-cases for clustering vector embeddings: Survey Insights Customer Insights Community Insights This template demonstrates the Customer Insights scenario where Trustpilot reviews can be quickly grouped by similarity and an AI agent can generate insights on those groupings. With this workflow, marketers can save days and even weeks of work breaking down their own or competitor reviews and identify frequently mentioned positives and negatives. Sample Output: https://docs.google.com/spreadsheets/d/e/2PACX-1vQ6ipJnXWXgr5wlUJnhioNpeYrxaIpsRYZCwN3C-fFXumkbh9TAsA_JzE0kbv7DcGAVIP7az0L46_2P/pubhtml How it works Trustpilot reviews are scraped for a particular company using the HTTP request node. Reviews are then inserted into a Qdrant collection carefully tagged with the question and Trustpilot metadata. Reviews are fetched and put through a clustering algorithm using the Python Code node. The Qdrant points are returned in clustered groups. Each group is looped to fetch the payloads of the points and feed them to the AI agent to summarise and generate insights for. The resulting insights and raw responses are then saved to the Google Spreadsheet for further analysis by the marketer. Requirements Qdrant Vectorstore for storing embeddings. OpenAI account for embeddings and LLM. Customising the Template Adjust clustering parameters which make sense for your data. Consider expanding date range of reviews for insights over common intervals: 3mth, 6mth and YTD.

This is a very simple workflow that lets you subscribe to any github repository for the latest release (using n8n as example). How it works: daily poll to Github repository for release for latest (stable) version of n8n parses the content to HTML sends a gmail Setup steps: add your gmail credentials (or use other email node of choice) change the url to the right Github repository you want to check regularly change the To email address to the email that you want to receive the updates for Feedback & Questions If you have any questions or feedback about this workflow - Feel free to get in touch at ria@n8n.io

How it works Fetch transaction notification emails (including attachments) Clean up data Let AI (Basic LLM Chain node) generate bookkeeping item Send to Google sheet Details The example fetch email from Gmail lables, suggested using filters to automatically orgianize email into the labels Data will send to "raw data" sheet Example google sheet: https://docs.google.com/spreadsheets/d/1_IhdHj8bxtsfH2MRqKuU2LzJuzm4DaeKSw46eFcyYts/edit?gid=1617968863#gid=1617968863

How it works It’s very important to come prepared to Sales calls. This often means a lot of manual research about the person you’re calling with. This workflow delivers a summary of the latest social media activity (LinkedIn + X) for businesses you are about to interact with each day. Scans Your Calendar**: Each morning, it reviews your Google Calendar for any scheduled meetings or calls with companies based on each attendee email address. Fetches Latest Posts**: For each identified company, it fetches recent LinkedIn and X posts and summerizes them using AI to deliver a qucik overview for a busy sales rep. Delivers Insights**: You receive personalized emails via Gmail, each dedicated to a company you’re meeting with that day, containing a reminder of the meeting and a summary of company's recent social media activity. Setup steps The workflow requires you to have the following accounts set up in their respective nodes: Google Calendar GMail Clearbit OpenAI Besides those, you will need an account on the RapidAPI platform and subscribe to the following APIs: Fresh LinkedIn Profile Data Twitter Email example

The template allows to make Dropcontact batch requests up to 250 requests every 10 minutes (1500/hour). Valuable if high volume email enrichment is expected. Dropcontact will look for email & basic email qualification if first_name, last_name, company_name is provided. +++++++++++++++++++++++++++++++++++++++++ Step 1: Node "Profiles Query" Connect your own source (Airtable, Google Sheets, Supabase,...) the template is using Postgres by default. Note I: Be careful your source is only returning a maximum of 250 items. Note II: The next node uses the next variables, make sure you can map these from your source file: first_name last_name website (company_name would work too) full_name (see note) Note III: This template is using the Dropcontact Batch API, which works in a POST & GET setup. Not a GET request only to retrieve data, as Dropcontact needs to process the batch data load properly. +++++++++++++++++++++++++++++++++++++++++ Step 2: Node "Data Transformation" Will transform the input variables in the proper json format. This json format is expected from the Dropcontact API to make a batch request. "full_name" is being used as a custom identifier to update the returned email to the proper contact in your source database. To make things easy, use a unique identiefer in the full_name variable. +++++++++++++++++++++++++++++++++++++++++ Step3: Node: "Bulk Dropcontact Requests". Enter your Dropcontact credentials in the node: Bulk Dropcontact Requests. +++++++++++++++++++++++++++++++++++++++++ Step4: Connect your output source by mapping the data you like to use. +++++++++++++++++++++++++++++++++++++++++ Step5: Node: "Slack" (OPTIONAL) Connect your slack account, if an error occur, you will be notified. TIP: Try to run the workflow with a batch of 10 (not 250) as it might need to run initially before you will be able to map the data to your final destination. Once the data fields are properly mapped, adjust back to 250.

Campaign tracking is pivotal; it enables marketers to evaluate the efficacy of various strategies and channels. UTM parameters are particularly essential as they provide granular details about the source, medium, and campaign effectiveness. However, when this data is not automatically integrated into a centralized system, it can become a tedious and error-prone process to manually collate and analyze it. Retrieving UTM data from Shopify and storing it in Baserow enables oy to do more with this data. For example you could build a campaign database in Baserow and automatically add campaign revenue to it using this workflow template. This template will help you: Automatically retrieve UTM parameters from Shopify orders using the Shopify Admin API Process marketing data through n8n Store this data into Baserow, providing you with a dynamic, responsive base for campaign tracking and decision-making This template will demonstrate the follwing concepts in n8n: use the Schedule trigger node use the GraphQL node to call the Shopify Admin API split larger incoming datasets into n8n items with the Split node transform the data structure with the Set node control flow with the If node store data in Baserow with the Baserow node How to get started? Create a custom app in Shopify get the credentials needed to connect n8n to Shopify This is needed for the Shopify Trigger Create Shopify Acces Token API credentials n n8n for the Shopify trigger node Create Header Auth credentials: Use X-Shopify-Access-Token as the name and the Acces-Token from the Shopify App you created as the value. The Header Auth is neccessary for the GraphQL nodes. You will need a running Baserow instance for this. You can also sign up for a free account at https://baserow.io/ Please make sure to read the notes in the template. For a detailed explanation please check the corresponding video: https://youtu.be/VBeN-3129RM

If you have a shared or personal drive location with a high frequency of files created by humans, it can become difficult to organise. This may not matter... until you need to search for something! This n8n workflow works with the local filesystem to target the messy folder and categorise as well as organise its files into sub directories automatically. Disclaimer Unfortunately due to the intended use-case, this workflow will not work on n8n Cloud and a self-hosted version of n8n is required. How it works Uses the local file trigger to activate once a new file is introduced to the directory The new file's filename and filetype are analysed using AI to determine the best location to move this file. The AI assess the current subdirectories as to not create duplicates. If a relevant subdirectory is not found, a new subdirectory is suggested. Finally, an Execute Command node uses the AI's suggestions to move the new file into the correct location. Requirements Self-hosted version of n8n. The nodes used in this workflow only work in the self-hosted version. If you are using docker, you must create a bind mount to a host directory. Mistral.ai account for LLM model Customise this workflow If the frequency of files created is high enough, you may not want the trigger to active on every new file created event. Switch to a timer to avoid concurrency issues. Want to go fully local? A version of this workflow is available which uses Ollama instead. You can download this template here: https://drive.google.com/file/d/1iqJ_zCGussXpfaUBYGrN5opziEFAEQMu/view?usp=sharing

This workflow automates the collection of comments from posts on a Facebook Page. Providing clean, structured data for analysis or further automation. What this workflow does Fetches recent posts from a Facebook Page. Retrieves comments for each post. Outputs structured data of Comments and Posts for further use. Setup Facebook Graph API: Connect your Access Token with the required permissions (pages_read_engagement, pages_read_user_content). Workflow: Set the Page ID and the number of posts to fetch in the "Set Number of Latest Posts to Fetch" node.

Workflow Description: This n8n workflow automates the drafting of email replies for Fastmail using OpenAI's GPT-4 model. Here’s the overall process: Email Monitoring: The workflow continuously monitors a specified IMAP inbox for new, unread emails. Email Data Extraction: When a new email is detected, it extracts relevant details such as the sender, subject, email body, and metadata. AI Response Generation: The extracted email content is sent to OpenAI's GPT-4, which generates a personalized draft response. Get Fastmail Session and Mailbox IDs: Connects to the Fastmail API to retrieve necessary session details and mailbox IDs. Draft Identification: Identifies the "Drafts" folder in the mailbox. Draft Preparation: Compiles all the necessary information to create the draft, including the generated response, original email details, and specified recipient. Draft Uploading: Uploads the prepared draft email to the "Drafts" folder in the Fastmail mailbox. Prerequisites: IMAP Email Account: You need to configure an IMAP email account in n8n to monitor incoming emails. Fastmail API Credentials: A Fastmail account with JMAP API enabled. You should set up HTTP Header authentication in n8n with your Fastmail API credentials. OpenAI API Key: An API key from OpenAI to access GPT-4. Make sure to configure the OpenAI credentials in n8n. Configuration Steps: Email Trigger (IMAP) Node: Provide your email server settings and credentials to monitor emails. HTTP Request Nodes for Fastmail: Set up HTTP Header authentication in n8n using your Fastmail API credentials. Replace the httpHeaderAuth credential IDs with your configured credential IDs. OpenAI Node: Configure the OpenAI API key in n8n. Replace the openAiApi credential ID with your configured credential ID. By following these steps and setting up the necessary credentials, you can seamlessly automate the creation of email drafts in response to new emails using AI-generated content. This workflow helps improve productivity and ensures timely, personalized communication.

What this workflow does Downloads the daily top podcasts of a selected genre Summarizes the content of each podcast in a few paragraphs Sends the summaries and the direct link to each podcast in a formatted email Setup Create a free API key on Taddy here: https://taddy.org/signup/developers Input your user number and API key into the TaddyTopDaily node in the header parameters X-USER-ID and X-API-KEY respectively. Create access credentials for your Gmail as described here: https://developers.google.com/workspace/guides/create-credentials. Use the credentials from your client_secret.json in the Gmail node. In the Genre node, set the genre of podcasts you want a summary for. Valid values are: TECHNOLOGY, NEWS, ARTS, COMEDY, SPORTS, FICTION, etc. Look at api.taddy.org for the full list (they will be displayed in the help docs as PODCASTSERIES_TECHNOLOGY, PODCASTSERIES_NEWS, etc.) Enter your email address in the Gmail node. Change the schedule time for sending email from Schedule to whichever time you want to receive the email. Test: Hit Test Workflow. Check your email for the results. That's it! It should take less than 5 minutes total.

Introduction: Streamline your fundamental stock analysis process with AI-powered automation. By harnessing the power of SEC 10K reports - comprehensive documents required by the SEC containing vital company information - this template automates the analysis workflow. From planning by a Senior Research Analyst to execution by five Research Analysts and final review by a Senior Editor, this template takes an AI persona approach to compose the report that includes an overview of the business, strategy, SWOT (Strengths, Weaknesses, Opportunities, and Threads) analysis, near term catalysts, and top risks. Additionally, this template allows you to control the length and detail of the report generated. How it works There are three personas in the workflow: Senior Research Analyst** is the first part of the workflow. They are responsible for planning the work for the rest of the team. Squad of Research Analysts** is the second part of the workflow. They execute the plan created. Senior Editor** is the third part of the workflow. They polish the draft report and send it to publish This template uses a custom tool that is able to answer the SEC 10K questions from the Research team. Setup steps Setup the Stock Q&A Workflow for the company you want to analyze using this template Customize the setup node by specifying the company to analyze Customize the publish step by specifying the file name in the Google docs node Credit Inspired by Guilio's template

Use Case Transform web pages into AI-friendly markdown format: You need to process webpage content for LLM analysis You want to extract both content and links from web pages You need clean, formatted text without HTML markup You want to respect API rate limits while crawling pages What this Workflow Does The workflow uses Firecrawl.dev API to process webpages: Converts HTML content to markdown format Extracts all links from each webpage Handles API rate limiting automatically Processes URLs in batches from your database Setup Create a Firecrawl.dev account and get your API key Add your Firecrawl API key to the HTTP Request node's Authorization header Connect your URL database to the input node (column name must be "Page") or edit the array in Example fields from data source Configure your preferred output database connection How to Adjust it to Your Needs Modify input source to pull URLs from different databases Adjust rate limiting parameters if needed Customize output format for your specific use case Made by Simon @ automake.io

This n8n template demonstrates the beginnings of building your own n8n-powered WhatsApp chatbot! Under the hood, utilise n8n's powerful AI features to handle different message types and use an AI agent to respond to the user. A powerful tool for any use-case! How it works Incoming WhatsApp Trigger provides a way to get messages into the workflow. The message received is extracted and sent through 1 of 4 branches for processing. Each processing branch uses AI to analyse, summarize or transcribe the message so that the AI agent can understand it. The supported types are text, image, audio (voice notes) and video (no sound). The AI Agent is used to generate a response generally and uses a wikipedia tool for more complex queries. Finally, the response message is sent back to the WhatsApp user using the WhatsApp node. How to use Once you have setup and configured your WhatsApp account, you'll need to activate your workflow to start processing messages. Good to know: Large media files may negatively impact workflow performance. Requirements WhatsApp Buisness account OpenAI for LLM Customising this workflow For performance reasons, consider processing audio and video using dedicated services. To handle videos with sound, you have 2 choices: use an LLM like Gemini which fully supports video processing (though video input is not currently supported in LLM node) or split the video into a image track and audio track and process separately. Good luck! Go beyond and create rich and engagement customer experiences by responding using images, audio and video instead of just text!

How to scrap emails from websites This workflow shows how to quickly build an Email scraping API using n8n. Email marketing is at the core of most marketing strategies, be it content marketing, sales, etc. As such, being able to find contacts in bulk for your business on a large scale is key. There are available tools available in the market that can do this, but most are premium; why not build a custom one with n8n? Usage The workflow gets the data from a website and performs an extraction based on the date around on the website Copy the webhook URL to your browser Add a query parameter eg ?Website=https://mailsafi.com . This should give you a URL like this {{$n8nhostingurl/webhook/ea568868-5770-4b2a-8893-700b344c995e?Website=https://mailsafi.com Click on the URL and wait for the extracted email to be displayed. This will return the email address on the website, or if there is no email, the response will be "workflow successfully executed." Make sure to use HTTP:// for your domains Otherwise, you may get an error.

This n8n template is one of a 3-part series exploring use-cases for clustering vector embeddings: Survey Insights Customer Insights Community Insights This template demonstrates the Survey Insights scenario where survey participant responses can be quickly grouped by similarity and an AI agent can generate insights on those groupings. With this workflow, researchers can save days and even weeks of work breaking down cohorts of participants and identify frequently mentioned positives and negatives. Sample Output: https://docs.google.com/spreadsheets/d/e/2PACX-1vT6m8XH8JWJTUAfwojc68NAUGC7q0lO7iV738J7aO5fuVjiVzdTRRPkMmT1C4N8TwejaiT0XrmF1Q48/pubhtml# How it works All survey questions and responses are imported from a Google Sheet. Responses are then inserted into a Qdrant collection carefully tagged with the question and survey metadata. For each question, all relevant response are put through a clustering algorithm using the Python Code node. The Qdrant points are returned in clustered groups. Each group is looped to fetch the payloads of the points and feed them to the AI agent to summarise and generate insights for. The resulting insights and raw responses are then saved to the Google Spreadsheet for further analysis by the researcher. Requirements Survey data and format as shown in the attached google sheet. Qdrant Vectorstore for storing embeddings. OpenAI account for embeddings and LLM. Customising the Template Adjust clustering parameters which make sense for your data. Add more clusters for open-ended questions and less clusters when responses are multiple choice.

Who this is for This template is for everyone that wants to download their n8n Cloud invoices automatically as a PDF instead of downloading them manually. How it works This workflow checks your Gmail inbox for new n8n invoice emails from n8n's payment provider Paddle. Once it finds something, it converts the URL into a PDF using pdflayer and saves it in Google Drive. Setup Setup your Gmail and Google Drive credentials Create a free account at https://pdflayer.com/ Insert your pdflayer API key into the Setup node Insert the URL to the wanted drive folder into the setup node (make sure to remove everything after the ?) How to adjust it to your need Instead of saving the PDF in Google drive, you could also save it in your local system, any other storage provider or send the PDF automatically to the right person in your company.

This n8n workflow takes in a document such as a research paper, marketing or sales deck or company filings, and breaks them down into 3 templates: study guide, briefing doc and timeline. These templates are designed to help a student, associate or clerk quickly summarise, learn and understand the contents to be more productive. Study guide - a short quiz of questions and answered generated by the AI Agent using the contents of the document. Briefing Doc - key information and insights are extracted by the AI into a digestable form. Timeline - key events, durations and people are identified and listed into a simple to understand timeline by the AI How it works A local file trigger watches a local network directory for new documents. New documents are imported into the workflow, its contents extracted and vectorised into a Qdrant vector store to build a mini-knowledgebase. The document then passes through a series of template generating prompts where the AI will perform "research" on the knowledgebase to generate the template contents. Generated study guide, briefing and timeline documents are exported to a designated folder for the user. Requirements Self-hosted version of n8n. Qdrant instance for knowledgebase. Mistral.ai account for embeddings and AI model. Customising your workflow Try adding your own templates or adjusting the existing templates to suit your unique use-case. Anything is quite possible and limited only by your imagination! Want to go fully local? A version of this workflow is available which uses Ollama instead. You can download this template here: https://drive.google.com/file/d/1VV5R2nW-IhVcFP_k8uEks4LsLRZrHSNG/view?usp=sharing

This workflow integrates both web scraping and NLP functionalities. It uses HTML parsing to extract links, HTTP requests to fetch essay content, and AI-based summarization using GPT-4o. It's an excellent example of an end-to-end automated task that is not only efficient but also provides real value by summarizing valuable content. Note that to use this template, you need to be on n8n version 1.50.0 or later.

Create a recommendation tool without hallucinations based on RAG with the Qdrant Vector database. This example is based on movie recommendations on the IMDB-top1000 dataset. You can provide your wishes and your "big no's" to the chatbot, for example: "A movie about wizards but not Harry Potter", and get top-3 recommendations. How it works a video with the full design process Upload IMDB-1000 dataset to Qdrant Vector Store, embedding movie descriptions with OpenAI; Set up an AI agent with a chat. This agent will call a workflow tool to get movie recommendations based on a request written in the chat; Create a workflow which calls Qdrant's Recommendation API to retrieve top-3 recommendations of movies based on your positive and negative examples. Set Up Steps You'll need to create a free tier Qdrant Cluster (Qdrant can also be used locally; it's open-sourced) and set up API credentials You'll OpenAI credentials You'll need GitHub credentials & to upload the IMDB Kaggle dataset to your GitHub.

Use Case This workflow is beneficial when you're automatically adding new leads to your Pipedrive CRM. Usually, you'd have to manually review each lead to determine if they're a good fit. This process is time-consuming and increases the chances of missing important leads. This workflow ensures every new lead is promptly evaluated upon addition. What this workflow does The workflow runs every 5 minutes. On every run, it checks your new Pipedrive leads and enriches them with Clearbit. It then marks items as enriched and checks if the company of the new lead matches certain criteria (in this case if they are B2B and have more than 100 employees) and sends a Slack alert to a channel for every match. Pre Conditions You must have Pipedrive, Clearbit, and Slack accounts. You also need to set up the custom fields Domain and Enriched at in Pipedrive. Setup Go to Company Settings -> Data fields -> Organization and add Domain as a custom field Go to Company Settings -> Data fields -> Leads and add Enriched at as a custom date field Add your Pipedrive, Clearbit and Slack credentials. Fill the setup node below. To get the ID of your custom domain fields, simply run the Show only custom organization fields and Show only custom lead fields nodes below and copy the keys of your domain, and enriched at fields. How to adjust this workflow to your needs Modify the criteria to suit your definition of an interesting lead. If you only want to focus on interesting leads in Pipedrive, add a node that archives all others. This workflow was built using n8n version 1.29.1

This workflow automates the process of gathering LinkedIn advice articles, extracting their content, and generating unique contributions for each article using an AI model. The contributions are then posted to a Slack channel and a NocoDB database for record-keeping. The workflow is triggered weekly to ensure new articles are continuously collected and responded to. Who is this for? This workflow is designed for professionals, marketers, and content creators looking to boost their LinkedIn presence by regularly engaging with LinkedIn advice articles. It’s especially useful for those who want to be seen as a "thought leader" or "top voice" in their niche by contributing relevant and unique advice to trending topics. What problem is this workflow solving? Manually searching for relevant LinkedIn articles, reading through them, and crafting thoughtful contributions can be time-consuming. This workflow solves that by automating the process of finding new articles, extracting key content, and generating AI-powered contributions. It helps users stay consistently active on LinkedIn, contributing value to trending discussions. What this workflow does Triggers Weekly: The workflow is set to run every Monday at 8:00 AM. Search Google for LinkedIn Advice Articles: Uses a predefined Google search URL to find the latest LinkedIn advice articles based on the user's area of expertise. Extract LinkedIn Article Links: A code node extracts all LinkedIn advice article links from the search results. Retrieve Article Content: For each article link, the workflow retrieves the HTML content and extracts the article title, topics, and existing contributions. Generate AI-Powered Contributions: The workflow sends the extracted article content to an AI model, which generates unique, helpful advice for each topic within the article. Post to Slack & NocoDB: The AI-generated contributions, along with the article links, are posted to a designated Slack channel and stored in a NocoDB database for future reference. Setup Google Search URL: Update the Google search URL with the relevant LinkedIn advice query for your field (e.g., "site:linkedin.com/advice 'marketing automation'"). Slack Integration: Connect your Slack account and specify the Slack channel where you want the contributions to be posted. NocoDB Integration: Set up your NocoDB project to store the generated contributions along with the article titles and links. How to customize this workflow Change Search Terms**: Modify the Google search URL to focus on a different LinkedIn topic or expertise area. Adjust Trigger Frequency**: The workflow is set to run weekly, but you can adjust the frequency by changing the schedule trigger. Enhance Contribution Quality**: Customize the AI model's prompt to generate contributions that align with your brand voice or content strategy. Workflow Summary This workflow helps users maintain a consistent presence on LinkedIn by automating the discovery of new advice articles and generating unique contributions using AI. It is ideal for professionals who want to engage with LinkedIn content regularly without spending too much time manually searching and drafting responses.

This n8n workflow demonstrates how you can summarise and automate post-meeting actions from video transcripts fed into an AI Agent. Save time between meetings by allowing AI handle the chores of organising follow-up meetings and invites. How it works This workflow scans for the calendar for client or team meetings which were held online. * Attempts will be made to fetch any recorded transcripts which are then sent to the AI agent. The AI agent summarises and identifies if any follow-on meetings are required. If found, the Agent will use its Calendar Tool to to create the event for the time, date and place for the next meeting as well as add known attendees. Requirements Google Calendar and the ability to fetch Meeting Transcripts (There is a special OAuth permission for this action!) OpenAI account for access to the LLM. Customising the workflow This example only books follow-on meetings but could be extended to generate reports or send emails.

Who is this template for? This workflow template is designed for everyone with a Gmail address, who wants to forward all Netflix emails, including temporary login codes, to friends and family effortlessly. How it works Scans your Gmail inbox every minute for new e-mails from Netflix Forwards all Netflix e-mails to all desired e-mail addresses via the e-mail provider Mailjet Setup Steps Connect your Google Mail Account to n8n following the official n8n instructions Add all recipients you want to the recipients array at the "Set all recipients" node. Create and connect your Mailjet Account to n8n following the official n8n instructions. Note: You cannot use an Gmail e-mail address as the sender address, as mailjet does not support this. I recommend using your own email address from a custom domain. This works perfectly.

Monthly Spotify Track Archiving and Playlist Classification This n8n workflow allows you to automatically archive your monthly Spotify liked tracks in a Google Sheet, along with playlist details and descriptions. Based on this data, Claude 3.5 is used to classify each track into multiple playlists and add them in bulk. Who is this template for? This workflow template is perfect for Spotify users who want to systematically archive their listening history and organize their tracks into custom playlists. What problem does this workflow solve? It automates the monthly process of tracking, storing, and categorizing Spotify tracks into relevant playlists, helping users maintain well-organized music collections and keep a historical record of their listening habits. Workflow Overview Trigger Options**: Can be initiated manually or on a set schedule. Spotify Playlists Retrieval**: Fetches the current playlists and filters them by owner. Track Details Collection**: Retrieves information such as track ID and popularity from the user’s library. Audio Features Fetching**: Uses Spotify's API to get audio features for each track. Data Merging**: Combines track information with their audio features. Duplicate Checking**: Filters out tracks that have already been logged in Google Sheets. Data Logging**: Archives new tracks into a Google Sheet. AI Classification**: Uses an AI model to classify tracks into suitable playlists. Playlist Updates**: Adds classified tracks to the corresponding playlists. Setup Instructions Credentials Setup: Make sure you have valid Spotify OAuth2 and Google Sheets access credentials. Trigger Configuration: Choose between manual or scheduled triggers to start the workflow. Google Sheets Preparation: Set up a Google Sheet with the necessary structure for logging track details. Spotify Playlists Setup: Have a diverse range of playlists and exhaustive description (see example) ready to accommodate different music genres and moods. Customization Options Adjust Playlist Conditions**: Modify the AI model’s classification criteria to align with your personal music preferences. Enhance Track Analysis**: Incorporate additional audio features or external data sources for more refined track categorization. Personalize Data Logging**: Customize which track attributes to log in Google Sheets based on your archival preferences. Configure Scheduling**: Set a preferred schedule for periodic track archiving, e.g., monthly or weekly. Cost Estimate For 300 tracks, the token usage amounts to approximately 60,000 tokens (58,000 for input and 2,000 for completion), costing around 20 cents with Claude 3.5 Sonnet (as of October 2024). Playlists' Description Examples | Playlist Name | Playlist Description | |-------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------| | Classique | Indulge in the timeless beauty of classical music with this refined playlist. From baroque to romantic periods, this collection showcases renowned compositions. | | Poi | Find your flow with this dynamic playlist tailored for poi, staff, and ball juggling. Featuring rhythmic tracks that complement your movements. | | Pro Sound | Boost your productivity and focus with this carefully selected mix of concentration-enhancing music. Ideal for work or study sessions. | | ChillySleep | Drift off to dreamland with this soothing playlist of sleep-inducing tracks. Gentle melodies and ambient sounds create a peaceful atmosphere for restful sleep. | | To Sing | Warm up your vocal cords and sing your heart out with karaoke-friendly tracks. Featuring popular songs, perfect for solo performances or group sing-alongs. | | 1990s | Relive the diverse musical landscape of the 90s with this eclectic mix. From grunge to pop, hip-hop to electronic, this playlist showcases defining genres. | | 1980s | Take a nostalgic trip back to the era of big hair and neon with this 80s playlist. Packed with iconic hits and forgotten gems, capturing the energy of the decade.| | Groove Up | Elevate your mood and energy with this upbeat playlist. Featuring a mix of feel-good tracks across various genres to lift your spirits and get you moving. | | Reggae & Dub | Relax and unwind with the laid-back vibes of reggae and dub. This playlist combines classic reggae tunes with deep, spacious dub tracks for a chilled-out vibe. | | Psytrance | Embark on a mind-bending journey with this collection of psychedelic trance tracks. Ideal for late-night dance sessions or intense focus. | | Cumbia | Sway to the infectious rhythms of Cumbia with this lively playlist. Blending traditional Latin American sounds with modern interpretations for a danceable mix. | | Funky Groove | Get your body moving with this collection of funk and disco tracks. Featuring irresistible basslines and catchy rhythms, perfect for dance parties. | | French Chanson | Experience the romance and charm of France with this mix of classic and modern French songs, capturing the essence of French musical culture. | | Workout Motivation | Push your limits and power through your exercise routine with this high-energy playlist. From warm-up to cool-down, these tracks will keep you motivated. | | Cinematic Instrumentals | Immerse yourself in a world of atmospheric sounds with this collection of cinematic instrumental tracks, perfect for focus, relaxation, or contemplation. |

This workflow is aimed at generating keywords for SEO and articles To get started, you need to use the workflow as it is. You just call the webhook URL with a query parameter as q={{ $keywords}} For example, you can call it using ?q=keyword research This will give you a list of keywords back as an array. This system can be used by SEO pros, content marketers and also social media marketers to generate relevant keywords for their user needs

Automate Report Generation with n8n & Qualys Introducing the Save Qualys Reports to TheHive Workflow—a robust solution designed to automate the retrieval and storage of Qualys reports in TheHive. This workflow fetches reports from Qualys, filters out already processed reports, and creates cases in TheHive for the new reports. It runs every hour to ensure continuous monitoring and up-to-date vulnerability management, making it ideal for Security Operations Centers (SOCs). How It Works: Set Global Variables:** Initializes necessary global variables like base_url and newtimestamp. This step ensures that the workflow operates with the correct configuration and up-to-date timestamps. Ensure to change the Global Variables to match your environment. Fetch Reports from Qualys:** Sends a GET request to the Qualys API to retrieve finished reports. Automating this step ensures timely updates and consistent data retrieval. Convert XML to JSON:** Converts the XML response to JSON format for easier data manipulation. This transformation simplifies further processing and integration into TheHive. Filter Reports:** Checks if the reports have already been processed using their creation timestamps. This filtering ensures that only new reports are handled, avoiding duplicates. Process Each Report:** Loops through the list of new reports, ensuring each is processed individually. This step-by-step handling prevents issues related to bulk processing and improves reliability. Create Case in TheHive:** Generates a new case in TheHive for each report, serving as a container for the report data. Automating case creation improves efficiency and ensures that all relevant data is captured. Download and Attach Report:** Downloads the report from Qualys and attaches it to the respective case in TheHive. This automation ensures that all data is properly archived and easily accessible for review. Get Started: Ensure your Qualys and TheHive integrations are properly set up. Customize the workflow to fit your specific vulnerability management needs. Need Help? Join the discussion on our Forum or check out resources on Discord! Deploy this workflow to streamline your vulnerability management process, improve response times, and enhance the efficiency of your security operations.

This workflow syncs multiple Notion databases to your Google Calendar. And it works both ways. What events are supported? Everything except recurring events. All day events, multiple day events, start and end date… these are all supported. You set them in Notion and they stay in sync with Google. And vice versa. Why doesn’t it support recurring events? Notion doesn’t support recurring events yet. So when you create a recurring event in Google, it will only consider the first date, ignoring future occurrences of the event. Can I connect more than one Notion database? Yes. You can have many Notion databases synced to one Google Calendar account. You can see how to do it in the workflow instructions. It is recommended that you create more calendars in your account, so that you can link each calendar to a different database in Notion. But that’s a choice. What happens if I delete an event or page? Notion page deleted → Deletes event in Google Notion date property cleared → Deletes event in Google Google event deleted → Clears the date property in Notion, but keeps the page, so you don’t lose your work. Does it update the events? Yes. When you update the event in Google or in Notion it syncs both ways. How can I know what Notion item was linked to an event? Either by the name or by clicking the hyperlink in the event description that says: 👉 View in Notion. When I create a new event in Google, does it add an item to Notion? Yes. When you create an event inside one of your calendars, the item is synced to the corresponding Notion database. Does it sync event descriptions? No. The event description will always be “View in Notion”. Even if you change it in Google Calendar it will be overwritten when you make a change to the Notion page. 🎉 When you buy this template you receive step-by-step instructions on how to set it up. Check out my other templates 👉 https://n8n.io/creators/solomon/

How it works it will return workflows that have buil-in nodes not of latest version with information of node name, type, current version and latest version for that type Set up steps: You need to have n8n credentials set, you can get n8n API key under settings set your instance base URL in "instance base url" node Disclaimar: Only check build-in nodes, community nodes are not supported

The Stripe API does not provide custom fields in invoice or charge data. So you have to get it from the Checkout Sessions endpoint. But that endpoint is not easy for begginners. It has dictionary parameters and pagination settings. This workflows solves that problem by having a preconfigured GET request that gets all the checkout sessions from the last 7 days. It then transforms the data to make it easier to work with and allows you to filter by the custom_fields you want to get. . Check out my other templates 👉 https://n8n.io/creators/solomon/

How it works It’s very important to come prepared to Sales calls. This often means a lot of manual research about the person you’re calling with. This workflow delivers the latest social media activity (LinkedIn + X) for businesses you are about to interact with each day. Scans Your Calendar**: Each morning, it reviews your Google Calendar for any scheduled meetings or calls with companies based on each attendee email address. Fetches Latest Posts**: For each identified company, it fetches recent LinkedIn and X posts Delivers Insight**s: You receive personalized emails via Gmail, each dedicated to a company you’re meeting with that day, containing a reminder of the meeting, list of posts categorized by the social media platform, and direct links to posts. Setup steps The workflow requires you to have the following accounts set up in their respective nodes: Google Calendar GMail Clearbit Besides those, you will need an account on the RapidAPI platform and subscribe to the following APIs: Fresh LinkedIn Profile Data Twitter Email example

Workflow: Snapshot Contabo How it Works This workflow automates daily backups (snapshots) of VPS instances hosted on Contabo. Each day at midnight, it checks for existing snapshots and ensures that only the latest backups are retained by removing older ones. It provides a seamless, hands-off backup process to keep your data secure. Setup Steps Setting up this workflow is quick, typically taking about 10-15 minutes. The essential part of the setup is providing the necessary credentials, which you can easily retrieve from your Contabo control panel. Import the Workflow: Download and upload the workflow JSON into n8n. Configure Credentials: Add CLIENT_ID, CLIENT_SECRET, API_USER, and API_PASSWORD in the credential node. Activate the Workflow: Enable it to run automatically at midnight every day. Flow Overview Schedule Trigger (00:00 daily):** Automatically initiates the workflow. Formatted Date:** Prepares a timestamp for naming the snapshot. List Snapshots:** Verifies if an existing snapshot is available for each VPS. Conditional Logic:** No Snapshot? Proceeds to create a new one. Snapshot Found? Deletes the old snapshot before creating a new one. Key Points Snapshot Retention:** Old snapshots are deleted to ensure only the latest backups are stored. Unique Identifiers:** UUIDs are used to track and guarantee unique operations.

What this workflow does: This flow uses an AI node to generate Seed Keywords to focus SEO efforts on based on your ideal customer profile. You can use these keywords to form part of your SEO strategy. Outputs: List of 20 Seed Keywords Setup Fill the Set Ideal Customer Profile (ICP) Connect with your credentials Replace the Connect to your own database with your own database Pre-requisites / Dependencies You know your ideal customer profile (ICP) An AI API account (either OpenAI or Anthropic recommended) Made by Simon @ automake.io

This n8n template is one of a 3-part series exploring use-cases for clustering vector embeddings: Survey Insights Customer Insights Community Insights This template demonstrates the Community Insights scenario where HN commments can be quickly grouped by similarity and an AI agent can generate insights on those groupings. With this workflow, Researchers or HN users can quickly breakdown community consensus on a particular topic and identify frequently mentioned positives and negatives. Sample Output: https://docs.google.com/spreadsheets/d/e/2PACX-1vQXaQU9XxsxnUIIeqmmf1PuYRuYtwviVXTv6Mz9Vo6_a4ty-XaJHSeZsptjWXS3wGGDG8Z4u16rvE7l/pubhtml How it works HN comments are imported via the Hacknews API node. Comments are then inserted into a Qdrant collection carefully tagged with the Hackernews API metadata. Comments are then fetched and are put through a clustering algorithm using the Python Code node. The Qdrant points are returned in clustered groups. Each group is looped to fetch the payloads of the points and feed them to the AI agent to summarise and generate insights for. The resulting insights and raw responses are then saved to the Google Spreadsheet for further analysis by the researcher or the HN user. Requirements Works best with lots of comments! Qdrant Vectorstore for storing embeddings. OpenAI account for embeddings and LLM. Customising the Template Adjust clustering parameters which make sense for your data. Adjust sentimentality setting if comments are overwhelmingly negative at times.

Use case To guarantee an effective sales process deals must be distributed between sales reps in the best way. Normally, this involves manually assigning new deals that have come in. This workflow automates it for you! What this workflow does This workflow runs once a day and checks for unassigned deals in your Hubspot CRM. Once it finds one, it enriches the deal with information about the assigned contact and their company. It then checks the region of the assigned company before looking at the company's employee size. Based on this, it assigns the deal to the right sales rep within your company. Requirements New deals in Hubspot need to be unassigned in the beginning New deals have to have an attached contact that has an attached company in Hubspot The company needs to have values for region and employee count in Hubspot Setup The setup is quite straight forward and will probably take a few minutes only. Add your Hubspot credentials Customize your criterias for assigning deals in the Assign by Region and the following Assign nodes Make sure deals are assigned to the right salesrep in the Hubspot nodes at the end Activate the workflow Customizing this to your needs Adjust the trigger interval to your needs. Currently, it defaults to once a day Adjust your region settings by adding/updating/removing options in the respective node Adjust your employee size settings by adding/updating/removing options in the respective node Ideas to enhance this flow Wrap each region's assigned criteria into different sub-workflows for easier maintainability. This will not consume additional execution counts. Add more logic on what happens once a deal does not match any criteria you've set

Use Case Track all Linear tickets in Google sheets. Useful if you want to do some custom analysis but don't want to pay for Linear's Plus features (Linear Insights) or that it does not cover. Setup Add Linear API header key Add Google sheets creds Update which teams to get tickets from in Graphql Nodes Update which Google Sheets page to write all the tickets to You only need to add one column, id, in the sheet. Google Sheets node in automatic mapping mode will handle adding the rest of the columns. Set any custom data on each ticket Activate workflow 🚀 How to adjust this template Set any custom fields you want to get out of this, that you can quickly do in n8n.

This n8n workflow shows how using multimodal LLMs with AI vision can tackle tricky image validation tasks which are near impossible to achieve with code and often impractical to be done by humans at scale. You may need image validation when users submitted photos or images are required to meet certain criteria before being accepted. A wine review website may require users only submit photos of wine with labels, a bank may require account holders to submit scanned documents for verification etc. In this demonstration, our scenario will be to analyse a set of portraits to verify if they meet the criteria for valid passport photos according to the UK government website (https://www.gov.uk/photos-for-passports). How it works Our set of portaits are jpg files downloaded from our Google Drive using the Google Drive node. Each image is resized using the Edit Image node to ensure a balance between resolution and processing speed. Using the Basic LLM node, we'll define a "user message" option with the type of binary (data). This will allow us to pass our portrait to the LLM as an input. With our prompt containing the criteria pulled off the passport photo requirements webpage, the LLM is able to validate the photo does or doesn't meet its criteria. A structured output parser is used to structure the LLM's response to a JSON object which has the "is_valid" boolean property. This can be useful to further extend the workflow. Requirements Google Gemini API key Google Drive account Customising this workflow Not using Gemini? n8n's LLM node works with any compatible multimodal LLM so feel free to swap Gemini out for OpenAI's GPT4o or Antrophic's Claude Sonnet. Don't need to validate portraits? Try other use cases such as document classification, security footage analysis, people tagging in photos and more.

Purpose This workflow allows you to import any workflow from a file or another n8n instance and map the credentials easily. How it works A multi-form setup guides you through the entire process At the beginning you have two options: Upload a workflow file (JSON) Copy workflow from a remote n8n instance If you choose the second option, you get to choose one of your predefined (in the Settings node) remote instances first, then it retrieves a list of all the workflows using the n8n API which you then can choose a workflow from. Now both initial options come together - the workflow file is being processed In parallel all credentials of the current instance are being retrieved using the Execute Command node The next form page enables a mapping of all the credentials used in the workflow. The matching happens between the names (because one workflow can contain different credentials of the same type) of the original credentials and the ones available on the current instance. Every option then shows all available credentials of the same type. In addition the user has always the choice to create a new credential on the fly. For every option which was set to create a new credential, an empty credential is being created on the current instance using the n8n API. An emoji is being appended to the name, which indicates that it needs to be populated. Finally the workflow gets updated with the new credential ID’s and created on the current instance using the n8n API. Then the user gets a message, if the process has succeeded or not. Setup Select your credentials in the nodes which require those Configure your remote instance(s) in the Settings node. (You can skip this step, if you only want to use the File Upload feature) Every instance is defined as object with the keys name, apiKey and baseUrl. Those instances are then wrapped inside an array. You can find an example described within a note on the workflow canvas. How to use Grab the (production) URL of the Form from the first node Open the URL and follow the instructions given in the multi-form Disclaimer Security: Beware, that all credentials are being decrypted and processed within the workflow. Also the API keys to other n8n instances are stored within the workflow. This solution is primarily meant for transferring data between testing environments. For production use consider the n8n enterprise edition which provides a reliable way to deploy workflows between different environments without the need of manual credential mapping.

This n8n workflow template lets you easily generate comprehensive FAQ (Frequently Asked Questions) content for multiple services (or any items or pages you need to add the FAQs to). Simply provide the Google Sheets document containing the items to scrape, and the workflow automatically creates detailed, AI-enhanced FAQ documents. How it works The workflow reads data from a Google Sheets document containing information about different services and categories (again, in your case - whatever objects you need). For each service and category, it generates a set of standard questions and answers covering setup, permissions, integrations, use cases, and pricing benefits. An AI model (OpenAI's GPT) is used to enhance or complete some of the answers, making the content more comprehensive and natural-sounding. The workflow formats the Q&A pairs, combining AI-generated content with predefined answers where applicable. It creates a text file (JSON) for each service or category, containing the formatted Q&A pairs. The generated files are saved to specific folders in Google Drive, organized by the type of integration (native, credential-only, non-native) or category. After processing each service or category, it updates the status in the original Google Sheets document to mark it as completed. Ideal for: Marketing teams: Rapidly create comprehensive FAQ documents for multiple products or services. Customer support: Generate consistent and detailed answers for common customer queries. Product managers: Easily maintain up-to-date documentation as products evolve. Content creators: Streamline the process of creating informative content about various offerings. Accounts required Google account (for Google Sheets and Google Drive) OpenAI API account (for AI-enhanced content generation) n8n.io account (for workflow execution) Set up instructions Set up the required credentials for Google Sheets, Google Drive, and OpenAI when you first open the workflow. Prepare your Google Sheets document with the service/category information. Here's an example of Google Sheet. Fill the "Define Sheets" node with your sheets Adjust the folder IDs in the "Prepare Job" node to match your Google Drive structure. Configure the OpenAI model settings in the "OpenAI Chat Model" node if needed. Test the workflow with a small subset of data before running it on your entire dataset. Adjust the questions asked in the "Create your Q&A templates" section After testing, activate your workflow for automated FAQ generation. 🙏 Big, big kudos to Jim Le for his ideas, input and support when building this workflow. Your approach to AI workflows is always super helpful!

This n8n workflows builds another example of creating a knowledgebase assistant but demonstrates how a more deliberate and targeted approach to ingesting the data can produce much better results for your chatbot. In this example, a government tax code policy document is used. Whilst we could split the document into chunks by content length, we often lose the context of chapters and sections which may be required by the user. Our approach then is to first split the document into chapters and sections before importing into our vector store. Additionally, using metadata correctly is key to allow filtering and scoped queries. Example Human: "Tell me about what the tax code says about cargo for intentional commerce?" AI: "Section 11.25 of the Texas Property Tax Code pertains to "MARINE CARGO CONTAINERS USED EXCLUSIVELY IN INTERNATIONAL COMMERCE." In this section, a person who is a citizen of a foreign country or an en..." How it works The tax code policy document is downloaded as a zip file from the government website and its pages are extracted as separate chapters. Each chapter is then parsed and split into its sections using data manipulation expressions. Each section is then inserted into our Qdrant vector store tagged with its source, chapter and section numbers as metadata. When our AI Agent needs to retrieve data from our vector store, we use a custom workflow tool to perform the query to Qdrant. Because we're relying on Qdrant's advanced filtering capabilities, we perform the search using the Qdrant API rather than the Qdrant node. When the AI Agent, needs to pull full wording or extracts, we can use Qdrant's scroll API and metadata filtering to do so. This makes Qdrant behave like a key-value store for our document. Requirements A Qdrant instance is required for the vector store and specifically for it's filtering functionality. Mistral.ai account for Embeddings and AI models. Customising this workflow Depending on your use-case, consider returning actual PDF pages (or links) to the user for the extra confirmation and to build trust. Not using Mistral? You are able to replace but note to match the distance and dimension size of Qdrant collection to your chosen embedding model.

This n8n workflow automates the process of parsing and extracting data from PDF invoices. With this workflow, accounts and finance people can realise huge time and cost savings in their busy schedules. Read the Blog: https://blog.n8n.io/how-to-extract-data-from-pdf-to-excel-spreadsheet-advance-parsing-with-n8n-io-and-llamaparse/ How it works This workflow will watch an email inbox for incoming invoices from suppliers It will download the attached PDFs and processing them through a third party service called LlamaParse. LlamaParse is specifically designed to handle and convert complex PDF data structures such as tables to markdown. Markdown is easily to process for LLM models and so the data extraction by our AI agent is more accurate and reliable. The workflow exports the extracted data from the AI agent to Google Sheets once the job complete. Requirements The criteria of the email trigger must be configured to capture emails with attachments. The gmail label "invoice synced" must be created before using this workflow. A LlamaIndex.ai account to use the LlamaParse service. An OpenAI account to use GPT for AI work. Google Sheets to save the output of the data extraction process although this can be replaced for whatever your needs. Customizing this workflow This workflow uses Gmail and Google Sheets but these can easily be swapped out for equivalent services such as Outlook and Excel. Not using Excel? Simple redirect the output of the AI agent to your accounting software of choice.

This workflow uses AI to analyze the content of every new message in Gmail and then assigns specific labels, according to the context of the email. Default configuration of the workflow includes 3 labels: „Partnership” - email about sponsored content or cooperation, „Inquiry” - email about products, services, „Notification” - email that doesn't require response. You can add or edit labels and descriptions according to your use case. 🎬 See this workflow in action in my YouTube video about automating Gmail. How it works? Gmail trigger performs polling every minute for new messages (you can change the trigger interval according to your needs). The email content is then downloaded and forwarded to an AI chain. 💡 The prompt in the AI chain node includes instructions for applying labels according to the email content - change label names and instructions to fit your use case. Next, the workflow retrieves all labels from the Gmail account and compares them with the label names returned from the AI chain. Label IDs are aggregated and applied to processed email messages. ⚠️ Label names in the Gmail account and workflow (prompt, JSON schema) must be the same. Set up steps Set credentials for Gmail and OpenAI. Add labels to your Gmail account (e.g. „Partnership”, „Inquiry” and „Notification”). Change prompt in AI chain node (update list of label names and instructions). Change list of available labels in JSON schema in parser node. Optionally: change polling interval in Gmail trigger (by default interval is 1 minute). If you like this workflow, please subscribe to my YouTube channel and/or my newsletter.