Workflow Templates

🧩 Workflow: Process Tour PDF from Google Drive to Pinecone Vector DB with OpenAI Embeddings Overview This workflow automates the process of extracting tour information from PDF files stored in a Google Drive folder, processes and vectorizes the extracted data, and stores it in a Pinecone vector database for efficient querying. This is especially useful for building AI-powered search or recommendation systems for travel packages. Setup: Prerequisites A folder in Google Drive with PDF tour package brochures. Pinecone account + API key OpenAI API key n8n cloud or self-hosted instance Workflow Setup Steps Trigger Manual Trigger (When clicking 'Test workflow'): Used for manual testing and execution of the workflow. Google Drive Integration Step 1: Store Tour Packages in PDF Format Upload your curated tour packages containing the tours, activities and sight-seeings in PDF format into a designated Google Drive folder. Step 2: Search Folder Node: PDF Tour Package Folder (Google Drive) This node searches the designated folder for files (filter by MIME type = application/pdf if needed). Step 3: Download PDFs Node: Download Package Files (Google Drive) Downloads each matching PDF file found in the previous step. Process Each PDF File Step 4: Loop Through Files Node: Loop Over each PDF file Iterates through each downloaded PDF file to extract, clean, split, and embed. Data Preparation & Embedding Step 5: Data Loader Node: Data Loader Reads each PDF’s content using a compatible loader. It passes clean raw text to the next node. Often integrated with document loaders like pdf-loader, Unstructured, or pdfplumber. Step 6: Recursive Text Splitter Node: Recursive Character Text Splitter Splits large chunks of text into manageable segments using overlapping window logic (e.g., 500 tokens with 50 token overlap). This ensures contextual preservation for long documents during embedding. Step 7: Generate Embeddings Node: Embeddings OpenAI Uses text-embedding-3-small model to vectorize the split chunks. Outputs vector representations for each content chunk. Store in Pinecone Step 8: Pinecone Vector Store Node: Pinecone Vector Store - Store... Stores each embedding along with its metadata (source PDF name, chunk ID, etc.). This becomes the basis for fast, semantic search via RAG workflows or agents. 🛠️ Tools & Nodes Used Google Drive (Search & Download) Searches for all PDF files in a specified Google Drive folder. Downloads each file for processing. SplitInBatches (Loop Over Items) Loops through each file found in the folder, ensuring each is processed individually. Default Data Loader (LangChain) Reads and extracts text from the PDF files. Recursive Character Text Splitter (LangChain) Splits the extracted text into manageable chunks for embedding. OpenAI Embeddings (LangChain) Converts each text chunk into a vector using OpenAI’s embedding model. Pinecone Vector Store (LangChain) Stores the resulting vectors in a Pinecone index for fast similarity search and querying. 🔗 Workflow Steps Explained Trigger: The workflow starts manually for testing or can be scheduled. Google Drive Search: Finds all PDF files in the specified folder. Loop Over Files: Each file is processed one at a time using the SplitInBatches node. Download File: Downloads the current PDF file from Google Drive. Extract Text: The Default Data Loader node reads the PDF and extracts its text content. *Text Splitting: * The Recursive Character Text Splitter breaks the text into chunks (e.g., 1000 characters with 50 overlap) to optimize embedding quality. **Vectorization: **Each chunk is sent to the OpenAI Embeddings node to generate vector representations. Store in Pinecone: The vectors are inserted into a Pinecone index, making them available for semantic search and recommendations. 🚀 What Can Be Improved in the Next Version? *Error Handling: * Add error handling nodes to manage failed downloads or extraction issues gracefully. File Type Filtering: Ensure only PDF files are processed by adding a filter node. Metadata Storage: Store additional metadata (e.g., file name, tour ID) alongside vectors in Pinecone for richer search results. *Parallel Processing: * Optimize for large folders by processing multiple files in parallel (with care for API rate limits). Automated Triggers: Replace manual trigger with a time-based or webhook trigger for full automation. Data Validation: Add checks to ensure extracted text contains valid tour data before vectorization. User Feedback: Integrate notifications (e.g., email or Slack) to inform when processing is complete or if issues arise. 💡 Summary This workflow demonstrates how n8n can orchestrate a powerful AI data pipeline using Google Drive, LangChain, OpenAI, and Pinecone. It’s a great foundation for building intelligent search or recommendation features for travel and tour data. Feel free to ask for more details or share your improvements! Let me know if you want to see a specific part of the workflow or need help with a particular node!

Use Case This workflow is a slight variation of a workflow we're using at n8n. In most companies, employees have a lot of great ideas. That was the same for us at n8n. We wanted to make it as easy as possible to allow everyone to add their ideas to some formatted database - it should be somewhere where everyone is all the time and could add a new idea without much extra effort. Since we're using Slack, this seemed to be the perfect place to easily add ideas. In this example, we're adding the ideas to Google Sheets instead of Notion, like we do. What this workflow does This workflow waits for a webhook call within Slack, that gets fired when users use the /idea command on a bot that you will create as part of this template. It then checks the command, adds the idea to Google Sheets and notifies the user about the newly added idea as you can see below: Creating your Slack bot Visit https://api.slack.com/apps, click on New App and choose a name and workspace. Click on OAuth & Permissions and scroll down to Scopes -> Bot token Scopes Add the chat:write scope Head over to Slash Commands and click on Create New Command Use /idea as the command Copy the test URL from the Webhook node into Request URL Add whatever feels best to the description and usage hint Go to Install app and click install Setup Create a Google Sheets document with the columns Name and Creator Add your Google credentials Fill the Set me up node. Create your Slack app (see other sticky) Click Test workflow and use the /idea comment in Slack Activate the workflow and exchange the Request URL with the production URL from the webhook How to adjust it to your needs You can adjust the table in Google Sheets and for example, add different types of ideas or areas that they impact Rename the Slack command as it works best for you How to enhance this workflow At n8n we use this workflow in combination with some others. E.g. we have the following things on top: We additionally have a /bug Slack command that adds a new bug to Linear. Here we're using AI to classify the bugs and move it to the right team. (Bug command workflow and Ai Classifier workflow) We also added other types, like /pain to be less solution-driven To make it easier for everyone to give input, we added a Votes column that allows everyone to vote on ideas/pain points in the list We're also running a workflow once a week that highlights the most popular new ideas and the most active voters

This workflow demonstrates how to use the workflowStaticData() function to set any type of variable that will persist within workflow executions. https://docs.n8n.io/code/cookbook/builtin/get-workflow-static-data/ This can be useful for example when working with access tokens that expire after a certain time period. Using staticData we can keep a record of that access token and the expiry time and build our workflow logic around it. Important Static Data only persists across production executions, i.e. triggered by Webhooks or Schedule Triggers (not manual executions!) For this the workflow will have to be activated. Setup configure HTTP Request node to fetch access token from your API (optional) activate workflow test the workflow with the webhook production link you can check the population of the static data in the single executions Feedback If you found this useful or want to report some missing information - I'd be happy to hear from you at ria@n8n.io

Extract Title tag and meta description from url for SEO analysis. How it works The workflows takes records from Airtable, get the url in the records and extract from the related webpage the title tag (<title>) and meta description (<meta name="description" content="Some content">). If title tag and/or meta description tag isn't available on the webpage, the result will be empty. Setup Set a Base in Airtable with a table with the following structure: url (field type url), title tag (field type text string), meta desc (field type text field) Minimum suggested table structure is: url (https://example.com), title (Title example), meta desc* (This is the meta description of the example page) Connect Airtable to both Airtable nodes in the template and, with the following formula, get all the records that miss title tag and meta desc. Formula: AND(url != "", {title tag} = "", {meta desc} = "") Insert the url to be analyzed in the table in the field url and let the workflow do the rest. Extra You can also calculate the length for title tag and meta desc using formula field inside Airtable. This is the formula: LEN({title tag}) or LEN({meta desc}) You can automate the process calling a Webhook from Airtable. For this, you need an Airtable paid plan.

Encode JSON to Base64 String in n8n This example workflow demonstrates how to convert a JSON object into a base64-encoded string using n8n’s built-in file processing capabilities. This is a common requirement when working with APIs, webhooks, or SaaS integrations that expect payloads to be base64-encoded. > Tip: The three green-highlighted nodes (Stringify → Convert to File → Extract from File) can be wrapped in a Subworkflow to create a reusable Base64 encoder in your own projects. 🔧 Requirements Any running n8n instance (local or cloud) No credentials or external services required What This Workflow Does Generates example JSON data Converts the JSON to a string Saves the string as a binary file Extracts the file’s contents as a base64 string Outputs the base64 string on the final node Step-by-Step Setup Manual Trigger Start the workflow using the Manual Execution node. This is useful for testing and development. Create JSON Data The Create Json Data node uses raw mode to construct a sample object with all major JSON types: strings, numbers, booleans, nulls, arrays, nested objects, etc. Convert to String The Convert to String node uses the expression ={{ JSON.stringify($json) }} to flatten the object into a single string field named json_text. Convert to File The Convert to File node takes the json_text value and saves it to a UTF-8 encoded binary file in the property encoded_text. Extract from File This node takes the binary file and extracts its contents as a base64-encoded string. The result is saved in the base64_text field. Customization Tips Replace the sample JSON in the Create Json Data node with your own payload structure. To make this reusable, extract the three core nodes into a Subworkflow or wrap them in a custom Function. Use the base64_text output field to post to APIs, store in databases, or include in webhook responses.

Who is this for? Content creators, social media managers, digital marketers, and researchers who need to download original TikTok videos without watermarks for analysis, repurposing, or archiving purposes. What problem does this workflow solve? Downloading TikTok videos without watermarks typically requires using questionable third-party websites that may have limitations, ads, or privacy concerns. This workflow provides a clean, automated solution that can be integrated into your own systems and processes. What this workflow does This workflow automates the process of downloading TikTok videos without watermarks in three simple steps: Fetch the TikTok video page by providing the video URL Extract the raw video URL from the page's HTML data Download the original video file without watermark (Optional) Upload to Google Drive with public sharing link generation The workflow uses web scraping techniques to extract the original video source directly from TikTok's own servers, maintaining the highest possible quality without any added watermarks or branding. Setup (Est. time: 5-10 minutes) Before getting started, you'll need: n8n installation The URL of a TikTok you want to download (Optional) Google Drive API enabled in Google Cloud Console with OAuth Client ID and Client Secret credentials if you want to use the upload feature How to customize this workflow to your needs Replace the example TikTok URL with your desired video links Modify the file naming convention for downloaded videos Integrate with other nodes to process videos after downloading Create a webhook to trigger the workflow from external applications Set up a schedule to regularly download videos from specific accounts This workflow can be extended to support various use cases like trending content analysis, competitor research, creating compilation videos, or building a content library for inspiration. It provides a foundation that can be customized to fit into larger automated workflows for content creation and social media management.

Daily YouTrack In-Progress Tasks Summary to Discord by Assignee Keep your team in sync with a daily summary of tasks currently In Progress in YouTrack — automatically posted to your Discord channel. This workflow queries issues, filters them by status, groups them by assignee and priority, and sends a formatted message to Discord. It's perfect for teams that need a lightweight, automated stand-up report. > 📝 This workflow uses Discord as an example. You can easily replace the messaging integration with Slack, Mattermost, MS Teams, or any other platform that supports incoming webhooks. Use Case Remote development teams using YouTrack + Discord Replacing daily stand-up meetings with async updates Project managers needing quick visibility into active tasks Features Scheduled** daily execution (default: weekdays at 09:00) Status filter**: only issues marked as In Progress Grouping** by assignee and priority Custom mapping** for user mentions (YouTrack → Discord) Clean Markdown output** for Discord, with direct task links Setup Instructions YouTrack Configuration Get a permanent token: Go to your YouTrack profile → Account Security → Authentication Create a new permanent token with "Read Issue" permissions Copy the token value Set the base API URL: Format: https://yourdomain.youtrack.cloud/api/issues Replace yourdomain with your actual YouTrack instance Identify custom field IDs: Method 1: Go to YouTrack → Administration → Custom Fields → find your "Status" field and note its ID Method 2: Use API call GET /api/admin/customFieldSettings/customFields to list all field IDs Method 3: Inspect a task's API response and look for field IDs in the customFields array Example Status field ID: 105-0 or 142-1 Discord Configuration Create a webhook URL in your Discord server: Server Settings → Integrations → Webhooks → New Webhook Choose target channel and copy the webhook URL Extract webhook ID from URL (numbers after /webhooks/) Environment Variables & Placeholders | Placeholder | Description | |-------------|-------------| | {{API_URL}} | Your YouTrack API base URL | | {{TOKEN}} | YouTrack permanent token | | {{FIELD_ID}} | ID of the "Status" custom field | | {{QUERY_FIELDS}} | Fields to fetch (e.g., summary, id) | | {{PROJECT_LINK}} | Link to your YouTrack project | | {{USER_X}} | YouTrack usernames | | {{DISCORD_ID_X}} | Discord mentions or usernames | | {{NAME_X}} | Display names | | {{WEBHOOK_ID}} | Discord webhook ID | | {{DISCORD_CHANNEL}} | Discord channel name | | {{CREDENTIAL_ID}} | Your credential ID in n8n | Testing the Workflow Test YouTrack connection: Execute the "HTTP Request YT" node individually Verify that issues are returned from your YouTrack instance Check if the Status field ID is correctly filtering tasks Verify filtering: Run the "Filter fields" node Confirm only "In Progress" tasks pass through Check message formatting: Execute the "Discord message" node Review the generated message content and formatting Test Discord delivery: Run the complete workflow manually Verify the message appears in your Discord channel Schedule verification: Enable the workflow Test weekend skip functionality by temporarily changing dates Customization Tips Language**: All labels/messages are in English — customize if needed User mapping**: Adjust assignee → Discord mention logic in the message builder Priorities**: Update the priorityMap to reflect your own naming structure Schedule**: Modify the trigger time in the Schedule Trigger node Alternative platforms**: Swap out the Discord webhook for another messaging service if preferred

I am submitting this workflow for the Obsidian community to showcase the potential of integrating Obsidian with n8n. While straightforward, it serves as a compelling demonstration of the potential unlocked by integrating Obsidian with n8n. How it works This workflow lets you retrieve specific Airtable data you need in seconds, directly within your Obsidian note, using n8n. By highlighting a question in Obsidian and sending it to a webhook via the Post Webhook Plugin, you can fetch specific data from your Airtable base and instantly insert the response back into your note. The workflow leverages OpenAI’s GPT model to interpret your query, extract relevant data from Airtable, and format the result for seamless integration into your note. Set up steps Install the Post Webhook Plugin: Add this plugin to your Obsidian vault from the plugin store or GitHub. Set up the n8n Webhook: Copy the webhook URL generated in this workflow and insert it into the Post Webhook Plugin's settings in Obsidian. Configure Airtable Access: Link your Airtable account and specify the desired base and table to pull data from. Test the Workflow: Highlight a question in your Obsidian note, use the “Send Selection to Webhook” command, and verify that data is returned as expected.

Use Case In most companies, employees have a lot of great ideas. That was the same for us at n8n. We wanted to make it as easy as possible to allow everyone to add their ideas to some formatted database - it should be somewhere where everyone is all the time and could add a new idea without much extra effort. Since we're using Slack, this seemed to be the perfect place to easily add ideas and collect them in Notion. What this workflow does This workflow waits for a webhook call within Slack, that gets fired when users use the /idea command on a bot that you will create as part of this template. It then checks the command, adds the idea to Notion, and notifies the user about the newly added idea as you can see below: Creating your Slack bot Visit https://api.slack.com/apps, click on New App and choose a name and workspace. Click on OAuth & Permissions and scroll down to Scopes -> Bot token Scopes Add the chat:write scope Head over to Slash Commands and click on Create New Command Use /idea as the command Copy the test URL from the Webhook node into Request URL Add whatever feels best to the description and usage hint Go to Install app and click install Setup Add a Database in Notion with the columns Name and Creator Add your Notion credentials and add the integration to your Notion page. Fill the setup node below Create your Slack app (see other sticky) Click Test workflow and use the /idea comment in Slack Activate the workflow and exchange the Request URL with the production URL from the webhook How to adjust it to your needs You can adjust the table in Notion and for example, add different types of ideas or areas that they impact You might wanna add different templates in Notion to make it easier for users to fill their ideas with details Rename the Slack command as it works best for you How to enhance this workflow At n8n we use this workflow in combination with some others. E.g. we have the following things on top: We additionally have a /bug Slack command that adds a new bug to Linear. Here we're using AI to classify the bugs and move it to the right team. (see this template and this template) We also added other types, like /pain to be less solution-driven To make it easier for everyone to give input, we added a Votes column that allows everyone to vote on ideas/pain points in the list We're also running a workflow once a week that highlights the most popular new ideas and the most active voters (see here)

AI-Powered Proposal Generator - Sales Automation Workflow Overview This n8n workflow automates the entire proposal generation process using AI, transforming client requirements into professional, customized proposals delivered via email in seconds. Use Case Perfect for agencies, consultants, and sales teams who need to generate high-quality proposals quickly. Instead of spending hours writing proposals manually, this workflow captures client information through a web form and uses GPT-4 to generate contextually relevant, professional proposals. How It Works Form Trigger - Captures client information through a customizable web form OpenAI Integration - Processes form data and generates structured proposal content Google Drive - Creates a copy of your proposal template Google Slides - Populates the template with AI-generated content Gmail - Automatically sends the completed proposal to the client Key Features AI Content Generation**: Uses GPT-4 to create personalized proposal content Professional Templates**: Integrates with Google Slides for polished presentations Automated Delivery**: Sends proposals directly to clients via email Form Integration**: Captures all necessary client data through web forms Customizable Output**: Generates structured proposals with multiple sections Template Sections Generated Proposal title and description Problem summary analysis Three-part solution breakdown Project scope details Milestone timeline with dates Cost integration Requirements n8n instance** (cloud or self-hosted) OpenAI API key** for content generation Google Workspace account** for Slides and Gmail Basic n8n knowledge** for setup and customization Setup Complexity Intermediate - Requires API credentials setup and basic workflow customization Benefits Time Savings**: Reduces proposal creation from hours to minutes Consistency**: Ensures all proposals follow the same professional structure Personalization**: AI analyzes client needs for relevant content Automation**: Eliminates manual copy-paste and formatting work Scalability**: Handle multiple proposal requests simultaneously Customization Options Modify AI prompts for different industries or services Customize Google Slides template design Adjust form fields for specific information needs Personalize email templates and signatures Configure milestone templates for different project types Error Handling Includes basic error handling for API failures and form validation to ensure reliable operation. Security Notes All credentials have been removed from this template. Users must configure their own: OpenAI API credentials Google OAuth2 connections for Slides, Drive, and Gmail Form webhook configuration This workflow demonstrates practical AI integration in business processes and showcases n8n's capabilities for complex automation scenarios.

This n8n template demonstrates how to create a comprehensive voice-powered restaurant assistant that handles table reservations, food orders, and restaurant information requests through natural language processing. The system uses VAPI for voice interaction and PostgreSQL for data management, making it perfect for restaurants looking to automate customer service with voice AI technology. Good to know Voice processing requires active VAPI subscription with per-minute billing Database operations are handled in real-time with immediate confirmations The system can handle multiple simultaneous voice requests All customer data is stored securely in PostgreSQL with proper indexing How it works Table Booking & Order Handling Workflow Voice requests are captured through VAPI triggers when customers make booking or ordering requests The system processes natural language commands and extracts relevant details (party size, time, food items) Customer data is immediately saved to the bookings and orders tables in PostgreSQL Voice confirmations are sent back through VAPI with booking details and estimated wait times All transactions are logged with timestamps for restaurant management tracking Restaurant Info Provider Workflow Info requests trigger when customers ask about hours, menu, location, or services Restaurant details are retrieved from the restaurant_info table containing current information Wait nodes ensure proper data loading before voice response generation Structured restaurant information is delivered via VAPI in natural, conversational format Database Schema Bookings Table booking_id (PRIMARY KEY) - Unique identifier for each reservation customer_name - Customer's full name phone_number - Contact number for confirmation party_size - Number of guests booking_date - Requested reservation date booking_time - Requested time slot special_requests - Dietary restrictions or special occasions status - Booking status (confirmed, pending, cancelled) created_at - Timestamp of booking creation Orders Table order_id (PRIMARY KEY) - Unique order identifier customer_name - Customer's name phone_number - Contact for order updates order_items - JSON array of food items and quantities total_amount - Calculated order total order_type - Delivery, pickup, or dine-in special_instructions - Cooking preferences or allergies status - Order status (received, preparing, ready, delivered) created_at - Order timestamp Restaurant_Info Table info_id (PRIMARY KEY) - Information entry identifier category - Type of info (hours, menu, location, contact) title - Information title description - Detailed information content is_active - Whether info is currently valid updated_at - Last modification timestamp How to use The manual trigger can be replaced with webhook triggers for integration with existing restaurant systems Import the workflow into your n8n instance and configure VAPI credentials Set up PostgreSQL database with the required tables using the schema provided above Configure restaurant information in the restaurant_info table Test voice commands such as "Book a table for 4 people at 7 PM" or "What are your opening hours?" Customize voice responses in VAPI nodes to match your restaurant's tone and branding The system can handle multiple concurrent voice requests and scales with your restaurant's needs Requirements VAPI account for voice processing and natural language understanding PostgreSQL database for storing booking, order, and restaurant information n8n instance with database and VAPI integrations enabled Customising this workflow Voice AI automation can be adapted for various restaurant types - from quick service to fine dining establishments Try popular use-cases such as multi-location booking management, dietary restriction handling, or integration with existing POS systems The workflow can be extended to include payment processing, SMS notifications, and third-party delivery platform integration

Who is this for? This workflow is designed for SEO specialists, content creators, marketers, and website developers who want to ensure their web content is easily accessible, understandable, and indexable by Large Language Models (LLMs) like ChatGPT, Perplexity, and Google AI Overviews. If you're looking to optimize your site for the evolving AI-driven search landscape, this template is for you. What problem is this workflow solving? / Use case Modern AI tools often crawl websites without executing JavaScript. This can lead to them "seeing" a very different version of your page than a human user or traditional search engine bot might. This workflow helps you: Identify how much of your content is visible without JavaScript. Check for crucial on-page SEO elements that AI relies on (headings, meta descriptions, structured data). Detect if your site presents JavaScript-blocking warnings. Get an AI-generated readability score and actionable recommendations to improve AI-friendliness. What this workflow does Receives a URL via a chat interface. Sanitizes the input URL to ensure it's correctly formatted. Fetches the website's HTML content, simulating a non-JavaScript crawler (like Googlebot). Extracts key HTML features: visible text length, presence of H1/H2/H3 tags, meta description, Open Graph data, structured data (JSON-LD), and <noscript> tags. It also checks for common JavaScript-blocking messages. Performs an AI SEO Analysis using an LLM (via OpenAI) based on the extracted features. Provides a report including an AI Readability Score (0-10), a summary, actionable recommendations, and a reminder to check the robots.txt file for AI bot access. Setup Estimated setup time:** 2-5 minutes. Import this workflow into your n8n instance. Ensure you have an OpenAI account and API key. Configure the "OpenAI Chat Model" node with your OpenAI API credentials. If you don't have credentials set up yet, create new ones in n8n. Activate the workflow. Interact with the chat interface provided by the "When chat message received" trigger node (you can access this via its webhook URL). How to customize this workflow to your needs Change LLM Model:** In the "OpenAI Chat Model" node, you can select a different model that suits your needs or budget. Adjust AI Prompt:** Modify the prompt in the "AI SEO Analysis" node (Chain Llm) to change the focus of the analysis or the format of the report. For example, you could ask for more technical details or a different scoring system. User-Agent:** The "Get HTML from Website" node uses a Googlebot User-Agent. You can change this to simulate other bots if needed. JS Block Indicators:** The "Extract HTML Features" node contains a list of common JavaScript-blocking phrases. You can expand this list with other languages or specific messages relevant to your checks.