Workflow Templates

Automating LinkedIn Company URL Verification Use Case This automation verifies that a given LinkedIn URL actually belongs to a company by comparing the website listed on their LinkedIn page against the expected company domain. It is essential for ensuring data accuracy in lead qualification, enrichment, and CRM updates. What This Automation Does Input Parameters Company LinkedIn**: The LinkedIn URL to be verified. Company Domain**: The expected domain (e.g., example.com) for validation. Airtop Profile (connected to LinkedIn)**: Airtop Profile with LinkedIn authentication. Output Confirmation whether the LinkedIn page corresponds to the provided domain. Returns the verified LinkedIn URL if the match is confirmed. How It Works Extracts the website URL from the specified LinkedIn company profile. Compares the extracted URL with the provided company domain. If the domain is contained in the extracted website, the LinkedIn profile is confirmed as valid. Returns the original LinkedIn URL if the match is successful. Setup Requirements Airtop API Key LinkedIn-authenticated Airtop Profile Next Steps Use for LinkedIn Discovery Validation**: Ensure correctness after automated LinkedIn page discovery. Combine with CRM Updates**: Prevent incorrect LinkedIn links from being stored in CRM. Automate in Data Pipelines**: Use this as a validation gate before enrichment or scoring steps.

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.

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

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

🧩 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!

Send structured logs to BetterStack from any workflow using HTTP Request Who is this for? This workflow is perfect for automation builders, developers, and DevOps teams using n8n who want to send structured log messages to BetterStack Logs. Whether you're monitoring mission-critical workflows or simply want centralized visibility into process execution, this reusable log template makes integration easy. What problem is this workflow solving? Logging failures or events across multiple workflows typically requires duplicated logic. This workflow solves that by acting as a shared log sender, letting you forward consistent log entries from any other workflow using the Execute Workflow node. What this workflow does Accepts level (e.g., "info", "warn", "error") and message fields via Execute Workflow Trigger Sends the structured log to your BetterStack ingestion endpoint via HTTP Request Uses HTTP Header Auth for secure delivery Includes a manual trigger for testing and a sample call to demonstrate usage Comes with clear sticky notes to help you get started Setup Copy your BetterStack Logs ingestion URL. Create a Header Auth credential in n8n with your Authorization: Bearer YOUR_API_KEY. Replace the URL in the HTTP Request node with your BetterStack endpoint. Optionally modify the test data or log levels for custom scenarios. Use Execute Workflow in any of your workflows to send logs here.

Google Sheets UI for Workflow Control This n8n template provides a practical and efficient way to manage your n8n workflows using Google Sheets as a user-friendly interface. It demonstrates how to leverage a simple spreadsheet to control inputs, capture outputs, and track the processing status of individual data rows, offering a clear and visual overview of your automation tasks. Purpose of This Template: The primary purpose of this template is to illustrate how Google Sheets can serve as a dynamic UI for your n8n automations. It's designed for n8n users who need: A structured method to feed specific data into their workflows. The ability to selectively trigger workflow execution based on data status. A centralized place to view and store workflow outputs alongside original inputs. A simple, no-code solution for managing workflow data without building custom applications. Setup Instructions: To use this template, follow these steps: Create a Google Sheet: Set up a new Google Sheet (see the template here) with three columns: Color, Status, and Number. Populate the Color column with some sample data (e.g., color names) and set the Status for the rows you want to process to READY. Import the n8n Workflow: Import this n8n template into your n8n instance. Configure Google Sheets Nodes: For the first Google Sheets node (Read operation), ensure it's connected to your newly created Google Sheet and configured to read rows where the Status column is READY. You will need to authenticate your Google Sheets account. For the second Google Sheets node (Update operation), ensure it's also connected to the same Google Sheet. The node should automatically map the row_number, Number, and Status fields from the preceding nodes. Execute the Workflow: Run the workflow. Observe how it reads READY rows, processes them (calculates string length), and updates the Number and Status columns in your Google Sheet to DONE. Control Execution: To process new data, simply add new rows to your Google Sheet and set their Status to READY. Rerunning the workflow will then only process these new entries. For more details and context on this approach, you can refer to the related blog post here.

This n8n workflow automates the process of saving web articles or links shared in a chat conversation directly into a Notion database, using Google's Gemini AI and Browserless for web scraping. Who is this AI automation template for? It's useful for anyone wanting to reduce manual copy-pasting and organize web findings seamlessly within Notion. A smarter web clipping tool! What this AI automation workflow does Starts when a message is received Uses a Google Gemini AI Agent node to understand the context and manage the subsequent steps. It identifies if a message contains a request to save an article/link. If a URL is detected, it utilizes a tool configured with the Browserless API (via the HTTP Request node) to scrape the content of the web page. Creates a new page in a specified Notion database, populating it with thea summary scraped content, in a specific format, never leaving out any important details. It also saves the original URL, smart tags, publication date, and other metadata extracted by the AI. Posts a confirmation message (e.g., to a Discord channel) indicating whether the article was saved successfully or if an error occurred. Setup Import Workflow: Import this template into your n8n instance. Configure Credentials & Notion Database: Notion Database: Create or designate a Notion database (like the example "Knowledge Database") where articles will be saved. Ensure this database has the following properties (fields): Name (Type: Text) - This will store the article title. URL (Type: URL) - This will store the original article link. Description (Type: Text) - This can store the AI-generated summary. Tags (Type: Multi-select) - Optional, for categorization. Publication Date (Type: Date) - *Optional, store the date the article was published. Ensure the n8n integration has access to this specific database. If you require a different format to the Notion Database, not that you will have to update the Notion tool configuration in this n8n workflow accordingly. Notion Credential: Obtain your Notion API key and add it as a Notion credential in n8n. Select this credential in the save_to_notion tool node. Configure save_to_notion Tool: In the save_to_notion tool node within the workflow, set the 'Database ID' field to the ID of the Notion database you prepared above. Map the workflow data (URL, AI summary, etc.) to the corresponding database properties (URL, Description, etc.). In the blocks section of the notion tool, you can define a custom format for the research page, allowing the AI to fill in the exact details you want extracted from any web page! Google Gemini AI: Obtain your API key from Google AI Studio or Google Cloud Console (if using Vertex AI) and add it as a credential. Select this credential in the "Tools Agent" node. Discord (or other notification service): If using Discord notifications, create a Webhook URL (instructions) or set up a Bot Token. Add the credential in n8n and select it in the discord_notification tool node. Configure the target Channel ID. Browserless/HTTP Request: Cloud: Obtain your API key from Browserless and configure the website_scraper HTTP Request tool node with the correct API endpoint and authentication header. Self-Hosted: Ensure your Browserless Docker container is running and accessible by n8n. Configure the website_scraper HTTP Request tool node with your self-hosted Browserless instance URL. Activate Workflow: Save test and activate the workflow. How to customize this workflow to your needs Change AI Model:** Experiment with different AI models supported by n8n (like OpenAI GPT models or Anthropic Claude) in the Agent node if Gemini 2.5 Pro doesn't fit your needs or budget, keeping in mind potential differences in context window size and processing capabilities for large content. Modify Notion Saving:** Adjust the save_to_notion tool node to map different data fields (e.g., change the summary style by modifying the AI prompt, add specific tags, or alter the page content structure) to your Notion database properties. Adjust Scraping:** Modify the prompt/instructions for the website_scraper tool or change the parameters sent to the Browserless API if you need different data extracted from the web pages. You could also swap Browserless for another scraping service/API accessible via the HTTP Request node.

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. This workflow automates the process of scraping product data from e-commerce websites and using it to fine-tune a custom OpenAI GPT model for generating high-quality marketing copy and product descriptions. Main Use Cases Fine-tune OpenAI models with real product data from hundreds of supported e-commerce websites for marketing content generation. Create custom AI models specialized in writing compelling product descriptions across different industries and platforms. Automate the entire pipeline from data collection to model training using Bright Data's extensive scraper library. Generate marketing copy using your custom-trained model via an interactive chat interface. How it works The workflow operates in two main phases: model training and model usage, organized into these stages: Data Collection & Processing Manually triggered to start the fine-tuning process. Uses Bright Data's web scraper to extract product information from any supported e-commerce platform (Amazon, eBay, Shopify stores, Walmart, Target, and hundreds of other websites). Collects product titles, brands, features, descriptions, ratings, and availability status from your chosen platform. Easily customizable to scrape from different websites by simply changing the dataset configuration and product URLs. Training Data Preparation A Code node processes the scraped product data to create training examples in OpenAI's required JSONL format. For each product, generates a complete training example with: System message defining the AI's role as a marketing assistant. User prompt containing specific product details (title, brand, features, original description snippet). Assistant response providing an ideal marketing description template. Compiles all training examples into a single JSONL file ready for OpenAI fine-tuning. Model Fine-Tuning Uploads the training file to OpenAI using the OpenAI File Upload node. Initiates a fine-tuning job via HTTP Request to OpenAI's fine-tuning API using the GPT-4o-mini model as the base. The fine-tuning process runs on OpenAI's servers to create your custom model. Interactive Chat Interface Provides a chat trigger that allows real-time interaction with your fine-tuned model. An AI Agent node connects to your custom-trained OpenAI model. Users can chat with the model to generate product descriptions, marketing copy, or other content based on the training. Custom Model Integration The OpenAI Chat Model node is configured to use your specific fine-tuned model ID. Delivers responses trained on your product data for consistent, high-quality marketing content. Summary Flow: Manual Trigger → Scrape E-commerce Products (Bright Data) → Process & Format Training Data (Code) → Upload Training File (OpenAI) → Start Fine-Tuning Job (HTTP Request) | Parallel: Chat Trigger → AI Agent → Custom Fine-Tuned Model Response Benefits: Fully automated pipeline from raw product data to trained AI model. Works with hundreds of different e-commerce websites through Bright Data's extensive scraper library. Creates specialized models trained on real e-commerce data for authentic marketing copy across various industries. Scalable solution that can be adapted to different product categories, niches, or websites. Interactive chat interface for immediate access to your custom-trained model. Cost-effective fine-tuning using OpenAI's most efficient model (GPT-4o-mini). Easily customizable with different websites, product URLs, training prompts, and model configurations. Setup Requirements: Bright Data API credentials for web scraping (supports hundreds of e-commerce websites). OpenAI API key with fine-tuning access. Replace placeholder credential IDs and model IDs with your actual values. Customize the product URLs list and Bright Data dataset for your specific website and use case. The workflow can be adapted for any e-commerce platform supported by Bright Data's scraping infrastructure.

This workflow restores all n8n instance workflows from GitHub backups using the n8n API node. It complements the Backup Your Workflows to GitHub template by allowing users to seamlessly restore previously saved workflows. How It Works The workflow fetches workflows stored in a GitHub repository and imports them into your n8n instance. Setup Instructions To configure the workflow, update the Globals node with the following values: repo.owner** – Your GitHub username repo.name** – The name of your GitHub repository storing the workflows repo.path** – The folder path within the repository where workflows are stored For example, if your GitHub username is john-doe, your repository is named n8n-backups, and workflows are stored in a workflows/ folder, you would set: repo.owner → john-doe repo.name → n8n-backups repo.path → workflows/ Required Credentials GitHub API** – Access to your repository n8n API** – To import workflows into your n8n instance Who Is This For? This template is ideal for users who want to restore their workflows from GitHub backups, ensuring easy migration and recovery in case of data loss. Check out my other templates: 👉 My n8n Templates

This workflow takes two inputs, YouTube video URL (required) and a description of what information to extract from the video. If the description/"what you want" field is left empty, the default prompt will generate a detailed summary and description of the video's contents. However, you can ask for something more specific using this field/input. ++ Don't forget to make the workflow Active and use the production URL from the form node. Benefits Instant Summary Generation - Convert hours of watching YouTube videos to familiar, structured paragraphs and sentences in less than a minute Live Integration - Generate a summary or extract information on the contents of a YouTube video whenever, wherever Virtually Complete Automation - All that needs to be done is to add the video URL and describe what you want to know from the video Presentation - You can ask for a specific structure or tone to better help you understand or study the contents of the video How It Works Smart Form Interface: Simple N8N form captures video URL and description of what's to be extracted Designed for rapid and repeated completion anywhere and anytime Description Check: Uses JavaScript to determine if the description was filled in or left empty If the description field was left empty, the default prompt is, "Please be as descriptive as possible about the contents being spoken of in this video after giving a detailed summary." If the description field is filled, then the filled input will be used to describe what information to extract from the video HTTP Request: We're using Gemini API, specifically the video understanding endpoint We make a post HTTP request passing the video URL and the description of what information to extract Setup Instructions: HTTP Request Setup: Sign up for a Google Cloud account, join the Developer Program and get your Gemini API key Get curl for Gemini Video Understanding API The video understanding relies on the inputs from the form, code and HTTP request node, so correct mapping is essential for the workflow to function correctly. Feel free to reach out for additional help or clarification at my Gmail: terflix45@gmail.com, and I'll get back to you as soon as I can. Setup Steps: Code Node Setup: The code node is used as a filter to ensure a description prompt is always passed on. Use the JavaScript code below for that effect: // Loop over input items and add a new field called 'myNewField' to the JSON of each one for (const item of $input.all()) { item.json.myNewField = 1; if ($input.first().json['What u want?'].trim() == "") { $input.first().json['What do you want?'] = "Please be as descriptive as possible about the contents being spoken of this video after giving a detailed summary"; } } return $input.all(); // End of Code HTTP Request: To use Gemini Video Understanding, you'll need your Gemini API key Go to https://ai.google.dev/gemini-api/docs/video-understanding#youtube. This link will take you directly to the snippet. Just select REST programming language, copy that curl command, then paste it into the HTTP Request node Replace "Please summarize the video in 3 sentences." with the code node's output, which should either be the default description or the one entered by the user (second output field variable) Replace "https://www.youtube.com/watch?v=9hE5-98ZeCg" with the n8n form node's first output field, which should be the YouTube video URL variable Replace $GEMINI_API_KEY with your API key Redirect: Use n8n form node, page type "Final Ending" to redirect user to the initial n8n form for another analysis or preferred destination

Description: This n8n workflow automates a Discord bot to fetch messages from a specified channel and send AI-generated responses in threads. It ensures smooth message processing and interaction, making it ideal for managing community discussions, customer support, or AI-based engagement. This workflow leverages Redis for memory persistence, ensuring that conversation history is maintained even if the workflow restarts, providing a seamless user experience. How It Works The bot listens for new messages in a specified Discord channel. It sends the messages to an AI model for response generation. The AI-generated reply is posted as a thread under the original message. The bot runs on an Ubuntu server and is managed using PM2 for uptime stability. The Discord bot (Python script) acts as the bridge, capturing messages from Discord and sending them to the n8n webhook. The n8n workflow then processes these messages, interacts with the AI model, and sends the AI's response back to Discord via the bot. Prerequisites to host Bot Sign up on Pella, which is a managed hosting service for Discord Bots. (Easy Setup) A Redis instance for memory persistence. Redis is an in-memory data structure store, used here to store and retrieve conversation history, ensuring that the AI can maintain context across multiple interactions. This is crucial for coherent and continuous conversations. Set Up Steps 1️⃣ Create a Discord Bot Go to the Discord Developer Portal. Click “New Application”, enter a name, and create it. Navigate to Bot > Reset Token, then copy the Bot Token. Enable Privileged Gateway Intents (Presence, Server Members, Message Content). Under OAuth2 > URL Generator, select bot scope and required permissions. Copy the generated URL, open it in a browser, select your server, and click Authorize. 2️⃣ Deploy the Bot on Pella Create a new folder discord-bot and navigate into it: Create and configure an .env file to store your bot token: Copy the code to .env: (You can copy the webhook URL from the n8n workflow) TOKEN=your-bot-token-here WEBHOOK_URL=https://your-domain.tld/webhook/getmessage Create file main.py copy the below code and save it: Copy this Bot script to main.py: import discord import requests import json import os from dotenv import load_dotenv Load environment variables from .env file load_dotenv() TOKEN = os.getenv("TOKEN") WEBHOOK_URL = os.getenv("WEBHOOK_URL") Bot Configuration LISTEN_CHANNELS = ["YOUR_CHANNEL_ID_1", "YOUR_CHANNEL_ID_2"] # Replace with your target channel IDs Intents setup intents = discord.Intents.default() intents.messages = True # Enable message event intents.guilds = True intents.message_content = True # Required to read messages client = discord.Client(intents=intents) @client.event async def on_ready(): print(f'Logged in as {client.user}') @client.event async def on_message(message): if message.author == client.user: return # Ignore bot's own messages if str(message.channel.id) in LISTEN_CHANNELS: try: fetched_message = await message.channel.fetch_message(message.id) # Ensure correct fetching payload = { "channel_id": str(fetched_message.channel.id), # Ensure it's string "chat_message": fetched_message.content, "timestamp": str(fetched_message.created_at), # Ensure proper formatting "message_id": str(fetched_message.id), # Ensure ID is a string "user_id": str(fetched_message.author.id) # Ensure user ID is also string } headers = {'Content-Type': 'application/json'} response = requests.post(WEBHOOK_URL, data=json.dumps(payload), headers=headers) if response.status_code == 200: print(f"Message sent successfully: {payload}") else: print(f"Failed to send message: {response.status_code}, Response: {response.text}") except Exception as e: print(f"Error fetching message: {e}") client.run(TOKEN) Create requirements.txt and copy: discord python-dotenv 3️⃣ Follow the video to set up the bot which will run 24/7 Tutorial - https://www.youtube.com/watch?v=rNnK3XlUtYU Note: Free Plan will expire after 24 hours, so please opt for the Paid Plan in Pella to keep your bot running. 4️⃣ n8n Workflow Configuration The n8n workflow consists of the following nodes: Get Discord Messages (Webhook):** This node acts as the entry point for messages from the Discord bot. It receives the channel_id, chat_message, timestamp, message_id, and user_id from Discord when a new message is posted in the configured channel. Its webhook path is /getmessage and it expects a POST request. Chat Agent (Langchain Agent):** This node processes the incoming Discord message (chat_message). It is configured as a conversational agent, integrating the language model and memory to generate an appropriate response. It also has a prompt to keep the reply concise, under 1800 characters. OpenAI -4o-mini (Langchain Language Model):** This node connects to the OpenAI API and uses the gpt-4o-mini-2024-07-18 model for generating AI responses. It is the core AI component of the workflow. Message History (Redis Chat Memory):** This node manages the conversation history using Redis. It stores and retrieves chat messages, ensuring the Chat Agent maintains context for each user based on their user_id. This is critical for coherent multi-turn conversations. Calculator (Langchain Tool):** This node provides a calculator tool that the AI agent can utilize if a mathematical calculation is required within the conversation. This expands the capabilities of the AI beyond just text generation. Response fromAI (Discord):** This node sends the AI-generated response back to the Discord channel. It uses the Discord Bot API credentials and replies in a thread under the original message (message_id) in the specified channel_id. Sticky Note1, Sticky Note2, Sticky Note3, Sticky Note4, Sticky Note5, Sticky Note:** These are informational nodes within the workflow providing instructions, code snippets for the Discord bot, and setup guidance for the user. These notes guide the user on setting up the .env file, requirements.txt, the Python bot code, and general recommendations for channel configuration and adding tools. 5️⃣ Setting up Redis Choose a Redis Hosting Provider: You can use a cloud provider like Redis Labs, Aiven, or set up your own Redis instance on a VPS. Obtain Redis Connection Details: Once your Redis instance is set up, you will need the host, port, and password (if applicable). Configure n8n Redis Nodes: In your n8n workflow, configure the "Message History" node with your Redis connection details. Ensure the Redis credential ✅ redis-for-n8n is properly set up with your Redis instance details (host, port, password). 6️⃣ Customizing the Template AI Model:** You can easily swap out the "OpenAI -4o-mini" node with any other AI service supported by n8n (e.g., Cohere, Hugging Face) to use a different language model. Ensure the new language model node is connected to the ai_languageModel input of the "Chat Agent" node. Agent Prompt:** Modify the text parameter in the "Chat Agent" node to change the AI's persona, provide specific instructions, or adjust the response length. Additional Tools:** The "Calculator" node is an example of an AI tool. You can add more Langchain tool nodes (e.g., search, data lookup) and connect them to the ai_tool input of the "Chat Agent" node to extend the AI's capabilities. Refer to the "Sticky Note5" in the workflow for a reminder. Channel Filtering:** Adjust the LISTEN_CHANNELS list in the main.py file of your Discord bot to include or exclude specific Discord channel IDs where the bot should listen for messages. Thread Management:** The "Response fromAI" node can be modified to change how threads are created or managed, or to send responses directly to the channel instead of a thread. The current setup links the response to the original message ID (message_reference). 7️⃣ Testing Instructions Start the Discord Bot: Ensure your main.py script is running on Pella. Activate the n8n Workflow: Make sure your n8n workflow is active and listening for webhooks. Send a Message in Discord: Go to one of the LISTEN_CHANNELS in your Discord server and send a message. Verify Response: The bot should capture the message, send it to n8n, receive an AI-generated response, and post it as a thread under your original message. Check Redis: Verify that the conversation history is being stored and updated correctly in your Redis instance. Look for keys related to user IDs. ✅ Now your bot is running in the background! 🚀