Integrate OpenAI Chat Model in your LLM apps and 422+ apps and services

This workflow employs OpenAI's language models and SerpAPI to create a responsive, intelligent conversational agent. It comes equipped with manual chat triggers and memory buffer capabilities to ensure seamless interactions. To use this template, you need to be on n8n version 1.50.0 or later.

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.

This n8n template showcases the new HTTP tool released in version 1.47.0. Overall, the tool helps simplify AI Agent workflows where custom sub-workflows were performing the same simple http requests. Comparisons 1. AI agent that can scrape webpages Remake of https://n8n.io/workflows/2006-ai-agent-that-can-scrape-webpages/ Changes: Replaces Execute Workflow Tool and Subworkflow Replaces Response Formatting 2. Allow your AI to call an API to fetch data Remake of https://n8n.io/workflows/2094-allow-your-ai-to-call-an-api-to-fetch-data/ Changes: Replaces Execute Workflow Tool and Subworkflow Replaces Manual Query Params Definitions Replaces Response Formatting

This n8n workflow demonstrates a simple approach to improve chat UX by staggering an AI Agent's reply for users who send in a sequence of partial messages and in short bursts. How it works Twilio webhook receives user's messages which are recorded in a message stack powered by Redis. The execution is immediately paused for 5 seconds and then another check is done against the message stack for the latest message. The purpose of this check lets use know if the user is sending more messages or if they are waiting for a reply. The execution is aborted if the latest message on the stack differs from the incoming message and continues if they are the same. For the latter, the agent receives the buffered messages up to that point and is able to respond to them in a single reply. Requirements A Twilio account and SMS-enabled phone number to receive messages. Redis instance for the messages stack. OpenAI account for the language model. Customising the workflow This workflow should work for other common messaging platforms such as Whatsapp and Telegram. 5 seconds too long or too short? Adjust the wait threshold to suit your customers.

This is a workflow that tries to answer user queries using the standard GPT-4 model. If it can't answer, it sends a message to Slack to ask for human help. It prompts the user to supply an email address. This workflow is used in Advanced AI examples | Ask a human in the documentation. To use this workflow: Load it into your n8n instance. Add your credentials as prompted by the notes. Configure the Slack node to use your Slack details, or swap out Slack for a different service.

This n8n template takes a video and extracts frames from it which are used with a multimodal LLM to generate a script. The script is then passed to the same multimodal LLM to generate a voiceover clip. This template was inspired by Processing and narrating a video with GPT's visual capabilities and the TTS API How it works Video is downloaded using the HTTP node. Python code node is used to extract the frames using OpenCV. Loop node is used o batch the frames for the LLM to generate partial scripts. All partial scripts are combined to form the full script which is then sent to OpenAI to generate audio from it. The finished voiceover clip is uploaded to Google Drive. Sample the finished product here: https://drive.google.com/file/d/1-XCoii0leGB2MffBMPpCZoxboVyeyeIX/view?usp=sharing Requirements OpenAI for LLM Ideally, a mid-range (16GB RAM) machine for acceptable performance! Customising this workflow For larger videos, consider splitting into smaller clips for better performance Use a multimodal LLM which supports fully video such as Google's Gemini.

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.

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

Create a Telegram bot that combines advanced AI functionalities with LangChain nodes and new tools. Nodes as tools and the HTTP request tool are a new n8n feature that extend custom workflow tool and simplify your setup. We used the workflow tool in the previous Telegram template to call the Dalle-3 model. In the new version, we've achieved similar results using the HTTP Request tool and the Telegram node tool instead. The main difference is that Telegram bot becomes more flexible. The LangChain Agent node can decide which tool to use and when. In the previous version, all steps inside the custom workflow tool were executed sequentially. ⚠️ Note that you'd need to select the Tools Agent to work with new tools. Before launching the template, make sure to set up your OpenAI and Telegram credentials. Here’s how the new Telegram bot works: Telegram Trigger listens for new messages in a specified Telegram chat. This node activates the rest of the workflow after receiving a message. AI Tool Agent receives input text, processes it using the OpenAI model and replies to a user. It addresses users by name and sends image links when an image is requested. The OpenAI GPT-4o model generates context-aware responses. You can configure the model parameters or swap this node entirely. Window buffer memory helps maintain context across conversations. It stores the last 10 interactions and ensures that the agent can access previous messages within a session. Conversations from different users are stored in different buffers. The HTTP request tool connects with OpenAI's DALL-E-3 API to generate images based on user prompts. The tool is called when the user asks for an image. Telegram node tool sends generated images back to the user in a Telegram chat. It retrieves the image from the URL returned by the DALL-E-3 model. This does not happen directly, however. The response from the HTTP request tool is first stored in the Agent’s scratchpad (think of it as a short-term memory). In the next iteration, the Agent sends the updated response to the GPT model once again. The GPT model will then create a new tool request to send the image back to the user. To pass the image URL, the tool uses the new $fromAI() expression. Send final reply node sends the final response message created by the agent back to the user on Telegram. Even though the image was already passed to the user, the Agent always stops with the final response that comes from dedicated output. ⚠️ Note, that the Agent may not adhere to the same sequence of actions in 100% of situations. For example, sometimes it could skip sending the file via the Telegram node tool and instead just send an URL in the final reply. If you have a longer series of predefined steps, it may be better to use the “old” custom workflow tool. This template is perfect as a starting point for building AI agentic workflow. Take a look at another agentic Telegram AI template that can handle both text and voice messages.

Video Guide I prepared a detailed guide that showed the whole process of building a resume analyzer. Who is this for? This workflow is ideal for developers, data analysts, and business owners who want to enable conversational interactions with their database. It’s particularly useful for cases where users need to extract, analyze, or aggregate data without writing SQL queries manually. What problem does this workflow solve? Accessing and analyzing database data often requires SQL expertise or dedicated reports, which can be time-consuming. This workflow empowers users to interact with a database conversationally through an AI-powered agent. It dynamically generates SQL queries based on user requests, streamlining data retrieval and analysis. What this workflow does This workflow integrates OpenAI with a Supabase database, enabling users to interact with their data via an AI agent. The agent can: Retrieve records from the database. Extract and analyze JSON data stored in tables. Provide summaries, aggregations, or specific data points based on user queries. Dynamic SQL Querying: The agent uses user prompts to create and execute SQL queries on the database. Understand JSON Structure: The workflow identifies JSON schema from sample records, enabling the agent to parse and analyze JSON fields effectively. Database Schema Exploration: It provides the agent with tools to retrieve table structures, column details, and relationships for precise query generation. Setup Preparation Create Accounts: N8N: For workflow automation. Supabase: For database hosting and management. OpenAI: For building the conversational AI agent. Configure Database Connection: Set up a PostgreSQL database in Supabase. Use appropriate credentials (username, password, host, and database name) in your workflow. N8N Workflow AI agent with tools: Code Tool: Execute SQL queries based on user input. Database Schema Tool: Retrieve a list of all tables in the database. Use a predefined SQL query to fetch table definitions, including column names, types, and references. Table Definition: Retrieve a list of columns with types for one table.

Who this is for This workflow is for sales people who want to quickly and efficiently follow up with their leads What this workflow does This workflow starts every time a new reply is received in lemlist. It then classifies the response using openAI and creates the correct follow up task. The follow-up tasks currently include: Slack alerts when a lead for each new replies Tag interested leads in lemlist Unsubscription of leads when they request it The Slack alerts include: Lead email address Sender email address Reply type (positive, not interested...etc) A preview of the reply Setup To set this template up, simply follow the stickies steps in it How to customize this workflow to your needs Adjust the follow up tasks to your needs Change the Slack notification to your needs ...

This n8n workflow is designed to work on the local network and assists with reconciling downloaded bank statements with internal tenant records to quickly highlight any issues with payments such as missed or late payments or those of incorrect amounts. This assistant can then generate a report to quick flag attention to ensure remedial action is taken. How it works The workflow monitors a local network drive to watch for new bank statements that are added. This bank statement is then imported into the n8n workflow, its contents extracted and sent to the AI Agent. The AI Agent analyses the line items to identify the dates and any incoming payments from tenants. The AI agent then uses an locally-hosted Excel ("XLSX") spreadsheet to get both tenant records and property records. From this data, it can determine for each active tenant when payment is due, the amount and the tenancy duration. Comparing to the bank statement, the AI Agent can now report on where tenants have missed their payments, made late payments or are paying the incorrect amounts. The final report is generated and logged in the same XLSX for a human to check and action. Requirements A self-hosted version of n8n is required. OpenAI account for the AI model Customising this workflow If you organisation has a Slack or Teams account, consider sending reports to a channel for increased productivity. Email may be a good choice too. 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/1YRKjfakpInm23F_g8AHupKPBN-fphWgK/view?usp=sharing

This AI agent can access data provided by another n8n workflow. Since that workflow can be used to retrieve any data from any service, this template can be used give an agent access to any data. Note that to use this template, you need to be on n8n version 1.19.4 or later.

With this workflow you get a fully automated AI powered Support-Agent for your WooCommerce webshop. It allows customers to request information about things like: the status of their order the ordered products shipping and billing address current DHL shipping status How it works The workflow receives chat messages from an in a website integrated chat. For security and data-privacy reasons, does the website transmit the email address of the user encrypted with the requests. That ensures that user can just request the information about their own orders. An AI agent with a custom tool supplies the needed information. The tool calls a sub-workflow (in this case, in the same workflow for convenience) to retrieve the required information. This includes the full information of past orders plus the shipping information from DHL. If otherr shipping providers are used it should be simple to adjust the workflow to query information from other APIs like UPS, Fedex or others.

This workflow allows you to ask questions about the data in a Google Sheet over a chat interface. It uses n8n's built-in chat, but could be modified to work with Slack, Teams, WhatsApp, etc. Behind the scenes, the workflow uses GPT4, so you'll need to have an OpenAI API key that supports it. How it works The workflow uses an AI agent with custom tools that call a sub-workflow. That sub-workflow reads the Google Sheet and returns information from it. Because models have a context window (and therefore a maximum number of characters they can accept), we can't pass the whole Google Sheet to GPT - at least not for big sheets. So we provide three ways of querying less data, that can be used in combination to answer questions. Those three functions are: List all the columns in the sheet Get all values of a single column Get all values of a single row Note that to use this template, you need to be on n8n version 1.19.4 or later.

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.

How it works: This project creates a personal AI assistant named Angie that operates through Telegram. Angie can summarize daily emails, look up calendar entries, remind users of upcoming tasks, and retrieve contact information. The assistant can interact with users via both voice and text inputs. Step-by-step: Telegram Trigger: The workflow starts with a Telegram trigger that listens for incoming message events. The system determines if the incoming message is voice or text. If voice, the voice file is retrieved and transcribed to text using OpenAI's API Speech to Text AI Assistant: The telegram request is passed to the AI assistant (Angie). Tools Integration: The AI assistant is equipped with several tools: Get Email: Uses Gmail API to fetch recent emails, filtering by date. Get Calendar: Retrieves calendar entries for specified dates. Get Tasks: Connects to a Baserow (open-source Airtable alternative) database to fetch to-do list items. Get Contacts: Also uses Baserow to retrieve contact information. Response Generation: The AI formulates a response based on the gathered information and sends back to the user on Telegram

🚀 Local Multi-LLM Testing & Performance Tracker This workflow is perfect for developers, researchers, and data scientists benchmarking multiple LLMs with LM Studio. It dynamically fetches active models, tests prompts, and tracks metrics like word count, readability, and response time, logging results into Google Sheets. Easily adjust temperature 🔥 and top P 🎯 for flexible model testing. Level of Effort: 🟢 Easy – Minimal setup with customizable options. Setup Steps: Install LM Studio and configure models. Update IP to connect to LM Studio. Create a Google Sheet for result tracking. Key Outcomes: Benchmark LLM performance. Automate results in Google Sheets for easy comparison. Version 1.0

This template demonstrates how to trigger an AI Agent with Siri and Apple Shortcuts, showing a simple pattern for voice-activated workflows in n8n. It's easy to customize—add app nodes before the AI Agent step to pass additional context, or modify the Apple Shortcut to send inputs like text, geolocation, images, or files. Set Up Basic instructions in template itself. Requirements n8n account** (cloud or self-hosted) Apple Shortcuts app** on iOS or macOS. Dictation ("Siri") must be activated. Download the Shortcuts template here. Key Features: Voice-Controlled AI:** Trigger AI Agent via Siri for real-time voice replies. Customizable Inputs:** Modify Apple Shortcut to send text, images, geolocation, and more. Flexible Outputs:** Siri can return the AI’s response as text, files, or customize it to trigger CRUD actions in connected apps. Context-Aware:** Automatically feeds the current date and time to the AI Agent, with easy options to pass in more data. How It Works: Activate Siri and speak your request. Siri sends the transcribed text to the n8n workflow via Apple Shortcuts. AI Agent processes the request and generates a response. Siri reads the response, or the workflow can return geolocation, files, or even perform CRUD actions in apps. Inspiration: Custom Use Cases Tweak this template and make it your own. Capture Business Cards:** Snap a photo of a business card and record a voice note. Have the AI Agent draft a follow-up email in Gmail, ready to send. Voice-to-Task Automation:** Speak a new to-do item, and the workflow will add it to a Notion task board. Business English on the Fly:** Convert casual speech into polished business language, and save the refined text directly to your pasteboard, ready to be pasted into any app. "It's late because of you" -> "There has been a delay, and I believe your input may have contributed to it."

This n8n workflow is a fun way to query and search over your credentials on your n8n instance. Good to know Your credentials should remain safe as this workflow does not decrypt or use any decrypted data. Example Usage "Which workflows are using Slack and Google Calendar?" "Which workflows have AI in their name but are not using openAI?" How it works Using the n8n API, it fetches all workflow data on the instance. Workflow data contains references to credentials used so this will be extracted. With some necessary reformatting, the workflows and their credentials metadata are stored to a SQLite database. Next, an AI agent is used with a custom SQL tool that reads the SQLite database created in the previous step. The AI agent is instructed to perform SQL queries against our workflow credential table when asked about credentials by the user. Requirements You'll need an n8n API key. Please note that only workflows will be scoped to your API key. Customising the workflow Add extra table fields to the SQLite database to answer even more complex queries such as: workflow status to differentiate between active and inactive workflows.

Purpose of workflow: The purpose of this workflow is to automate scraping of a website, transforming it into a structured format, and loading it directly into a Google Sheets spreadsheet. How it works: Web Scraping: Uses the Jina AI service to scrape website data and convert it into LLM-friendly text. Information Extraction: Employs an AI node to extract specific book details (title, price, availability, image URL, product URL) from the scraped data. Data Splitting: Splits the extracted information into individual book entries. Google Sheets Integration: Automatically populates a Google Sheets spreadsheet with the structured book data. Step by step setup: Set up Jina AI service: Sign up for a Jina AI account and obtain an API key. Configure the HTTP Request node: Enter the Jina AI URL with the target website. Add the API key to the request headers for authentication. Set up the Information Extractor node: Use Claude AI to generate a JSON schema for data extraction. Upload a screenshot of the target website to Claude AI. Ask Claude AI to suggest a JSON schema for extracting required information. Copy the generated schema into the Information Extractor node. Configure the Split node: Set it up to separate the extracted data into individual book entries. Set up the Google Sheets node: Create a Google Sheets spreadsheet with columns for title, price, availability, image URL, and product URL. Configure the node to map the extracted data to the appropriate columns.

This workflow connects Telegram bots with LangChain nodes in n8n. The main AI Agent Node is configured as a Conversation Agent. It has a custom System Prompt which explains the reply formatting and provides some additional instructions. The AI Agent has several connections: OpenAI GPT-4 model is called to generate the replies Window Buffer Memory stores the history of conversation with each user separately There is an additional Custom n8n Workflow tool (Dall-E 3 Tool). AI Agent uses this tool when the user requests an image generation. In the lower part of the workflow, there is a series of nodes that call Dall-E 3 model with the user Telegram ID and a prompt for a new image. Once image is ready, it is sent back to the user. Finally, there is an extra Telegram node that masks HTML syntax for improved stability in case the AI Agent replies using the unsupported format.

This workflow automatically generates draft replies in Gmail. It's designed for anyone who manages a high volume of emails or often face writer's block when crafting responses. Since it doesn't send the generated message directly, you're still in charge of editing and approving emails before they go out. How It Works: Email Trigger: activates when new emails reach the Gmail inbox Assessment: uses OpenAI gpt-4o and a JSON parser to determine if a response is necessary. Reply Generation: crafts a reply with OpenAI GPT-4 Turbo Draft Integration: after converting the text to html, it places the draft into the Gmail thread as a reply to the first message Set Up Overview (~10 minutes): OAuth Configuration (follow n8n instructions here): Setup Google OAuth in Google Cloud console. Make sure to add Gmail API with the modify scope. Add Google OAuth credentials in n8n. Make sure to add the n8n redirect URI to the Google Cloud Console consent screen settings. OpenAI Configuration: add OpenAI API Key in the credentials Tweaking the prompt: edit the system prompt in the "Generate email reply" node to suit your needs Detailed Walkthrough Check out this blog post where I go into more details on how I built this workflow. Reach out to me here if you need help building automations for your business.

Free template for voice & text messages with short-term memory This n8n workflow template is a blueprint for an AI Telegram bot that processes both voice and text messages. Ready to use with minimal setup. The bot remembers the last several messages (10 by default), understands commands and provides responses in HTML. You can easily swap GPT-4 and Whisper for other language and speech-to-text models to suit your needs. Core Features Text: send or forward messages Voice: transcription via Whisper Extend this template by adding LangChain tools. Requirements Telegram Bot API OpenAI API (for GPT-4 and Whisper) 💡 New to Telegram bots? Check our step-by-step guide on creating your first bot and setting up OpenAI access. Use Cases Personal AI assistant Customer support automation Knowledge base interface Integration hub for services that you use: Connect to any API via HTTP Request Tool Trigger other n8n workflows with Workflow Tool

Overview This workflow takes some French text, and translates it into spoken audio. It then transcribes that audio back into text, translates it into English and generates an audio file of the English text. To do so, it uses ElevenLabs (which has a free tier) and OpenAI. Setup These steps should only take a few minutes: In ElevenLabs, add a voice to your voice lab and copy its ID. Add it to the 'Set voice ID' node Get your ElevenLabs API key (click your name in the bottom-left of ElevenLabs and choose ‘profile’) In the 'Generate French audio' node, create a new header auth cred. Set the name to xi-api-key and the value to your API key In the 'credential' field of the 'Transcribe audio' node, create a new OpenAI cred with your OpenAI API key Run the workflow by clicking the orange button at the bottom of the canvas

This n8n workflow assists property managers and surveyors by reducing the time and effort it takes to complete property inventory surveys. In such surveys, articles and goods within a property may need to be captured and reported as a matter of record. This can take a sizable amount of time if the property or number of items is big enough. Our solution is to delegate this task to a capable AI Agent who can identify and fill out the details of each item automatically. How it works An AirTable Base is used to capture just the image of an item within the property Our workflow monitoring this AirTable Base sends the photo to an AI image recognition model to describe the item for purpose of identification. Our AI agent uses this description and the help of Google's reverse image search in an attempt to find an online product page for the item. If found, the product page is scraped for the item's specifications which are then used to fill out the rest of the details of the item in our Airtable. Requirements Airtable for capturing photos and product information OpenAI account to for image recognition service and AI for agent SerpAPI account for google reverse image search. Firecrawl.dev account for webspacing. Customising this workflow Try building an internal inventory database to query and integrate into the workflow. This could save on costs by avoiding fetching new each time for common items.

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.

With this workflow you can extract data from resume documents uploaded via a Telegram bot. Workflow transform readable content of PDF resume into structured data, using AI nodes and returns PDF with formatted, plain HTML. You can modify this workflow to perform other actions with structured data (e.g. insert it into database or create other, well-formatted documents). Functionality of this workflow was presented during the n8n community call on March 7, 2024 - recording of presentation available here. ⚠️ Workflow made for demo purposes. If you want to use it in real life, please make sure necessary measures for personal data protection are set. How it works? User uploads readable PDF resume document into Telegram bot. After authentication based on chat ID parameter, workflow extracts text from the PDF and transfers it into AI chain with connected sub-nodes: OpenAI Chat Model and Structured Output (JSON) Parser. Then, each extracted section (employment history, projects etc.) is formatted into desired HTML structure. Finally, the document is converted into new, structured PDF using Gotenberg. 💡 This workflow requires installed Gotenberg. If you are not familiar with this software, please have a look on my YouTube tutorial. You can also replace call to Gotenberg with other PDF generation service (such as PDFMonkey or ApiTemplate). Set up steps Create Telegram bot and add its credentials in n8n. Set your chat ID parameter in Auth node. Adjust JSON schema in Structured Output Parser according to your needs. Optionally: replace HTTP call to Gotenberg with PDF generation service of your choice. If you like this workflow, please subscribe to my YouTube channel and/or my newsletter.

This workflow is designed for dynamic and intelligent conversational capabilities. It incorporates OpenAI's GPT-4o model for natural language understanding and generation. Additional tools include SerpAPI and Wikipedia for enriched, data-driven responses. The workflow is triggered manually, and utilizes a 'Window Buffer Memory' to maintain the context of the last 20 interactions for better conversational continuity. All these components are orchestrated through n8n nodes, ensuring seamless interconnectivity. To use this template, you need to be on n8n version 1.50.0 or later.

This n8n workflow builds an appointment scheduling AI agent which can Take enquiries from prospective customers and help them book an appointment by checking appointment availability Where no appointment is booked, the Agent is able to send follow-up messages to re-engage leads. After an appointment is booked, the agent is able reschedule or even cancel the booking for the user without human intervention. For small outfits, this workflow could contribute the necessary "man-power" required to increase business sales. The sample Airtable can be found here: https://airtable.com/appO2nHiT9XPuGrjN/shroSFT2yjf87XAox 2024-10-22 Updated to Cal.com API v2. How it works The customer sends an enquiry via SMS to trigger our workflow. For this trigger, we'll use a Twilio webhook. The prospective or existing customer's number is logged in an Airtable Base which we'll be using to track all our enquries. Next, the message is sent to our AI Agent who can reply to the user and decide if an appointment booking can be made. The reply is made via SMS using Twilio. A scheduled trigger which runs every day, checks our chat logs for a list of prospective customers who have yet to book an appointment but still show interest. This list is sent to our AI Agent to formulate a personalised follow-up message to each lead and ask them if they want to continue with the booking. The follow-up interaction is logged so as to not to send too many messages to the customer. Requirements A Twilio account to receive customer messages. An Airtable account and Base to use as our datastore for enquiries. Cal.com account to use as our scheduling service. OpenAI account for our AI model. Customising this workflow Not using Airtable? Swap this out for your CRM of choice such as hubspot or your own service. Not using Cal.com? Swap this out for API-enabled services such as Acuity Scheduling or your own service.

This n8n template builds upon a simple appointment request form design which uses AI to qualify if the incoming enquiry is suitable and/or time-worthy of an appointment. This demonstrates a lighter approach to using AI in your templates but handles a technically difficult problem - contextual understanding! This example can be used in a variety of contexts where figuring out what is and isn't relevant can save a lot of time for your organisation. How it works We start with a form trigger which asks for the purpose of the appointment. Instantly, we can qualify this by using a text classifier node which uses AI's contextual understanding to ensure the appointment is worthwhile. If not, an alternative is suggested instead. Multi-page forms are then used to set the terms of the appointment and ask the user for a desired date and time. An acknowledgement is sent to the user while an approval by email process is triggered in the background. In a subworkflow, we use Gmail with the wait for approval operation to send an approval form to the admin user who can either confirm or decline the appointment request. When approved, a Google Calendar event is created. When declined, the user is notified via email that the appointment request was declined. How to use Modify the enquiry classifier to determine which contexts are relevant to you. Configure the wait for approval node to send to an email address which is accessible to all appropriate team members. Requirements OpenAI for LLM Gmail for Email Google Calendar for Appointments Customising this workflow Not using Google Mail or Calendar? Feel free to swap this with other services. The wait for approval step is optional. Remove if you wish to handle appointment request resolution in another way.

Who is this for? This workflow is designed for: Database administrators and developers working with MongoDB Content managers handling movie databases Organizations looking to implement AI-powered search and recommendation systems Developers interested in combining LangChain, OpenAI, and MongoDB capabilities What problem does this workflow solve? Traditional database queries can be complex and require specific MongoDB syntax knowledge. This workflow addresses: The complexity of writing MongoDB aggregation pipelines The need for natural language interaction with movie databases The challenge of maintaining user preferences and favorites The gap between AI language models and database operations What this workflow does This workflow creates an intelligent agent that: Accepts natural language queries about movies Translates user requests into MongoDB aggregation pipelines Queries a movie database containing detailed information including: Plot summaries Genre classifications Cast and director information Runtime and release dates Ratings and awards Provides contextual responses using OpenAI's language model Allows users to save favorite movies to the database Maintains conversation context using a window buffer memory Setup Required Credentials: OpenAI API credentials MongoDB connection details Node Configuration: Configure the MongoDB connection in the MongoDBAggregate node Set up the OpenAI Chat Model with your API key Ensure the webhook trigger is properly configured for receiving chat messages Database Requirements: A MongoDB collection named "movies" with the specified document structure Proper indexes for efficient querying Appropriate user permissions for read/write operations How to customize this workflow Modify the Document Structure: Update the tool description in the MongoDBAggregate node to match your collection schema Adjust the aggregation pipeline templates for your specific use case Enhance the AI Agent: Customize the prompt in the "AI Agent - Movie Recommendation" node Modify the window buffer memory size based on your context needs Add additional tools for more functionality Extend Functionality: Add more MongoDB operations beyond aggregation Implement additional workflows for different types of queries Create custom error handling and validation Add user authentication and rate limiting Integration Options: Connect to external APIs for additional movie data Add webhook endpoints for different platforms Implement caching mechanisms for frequent queries Add data transformation nodes for specific output formats This workflow serves as a foundation that can be adapted to various use cases beyond movie recommendations, such as e-commerce product search, content management systems, or any scenario requiring intelligent database interaction.

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.

This n8n workflow demonstrates how to create an agent using LangChain and SQLite. The agent can understand natural language queries and interact with a SQLite database to provide accurate answers. 💪 🚀 Setup Run the top part of the workflow once. It downloads the example SQLite database, extracts from a ZIP file and saves locally (chinook.db). 🗣️ Chatting with Your Data Send a message in a chat window. Locally saved SQLite database loads automatically. User's chat input is combined with the binary data. The LangChain Agend node gets both data and begins to work. The AI Agent will process the user's message, perform necessary SQL queries, and generate a response based on the database information. 🗄️ 🌟 Example Queries Try these sample queries to see the AI Agent in action: "Please describe the database" - Get a high-level overview of the database structure, only one or two queries are needed. "What are the revenues by genre?" - Retrieve revenue information grouped by genre, LangChain agent iterates several time before producing the answer. The AI Agent will store the final answer in its memory, allowing for context-aware conversations. 💬 Read the full article: 👉 https://blog.n8n.io/ai-agents/

The purpose of this n8n workflow is to automate the process of identifying incoming Gmail emails that are requesting an appointment, evaluating their content, checking calendar availability, and then composing and sending a response email. Note that to use this template, you need to be on n8n version 1.19.4 or later.

Purpose of workflow: This workflow transforms spreadsheet data into an interactive, AI-powered knowledge base that enables users to gain deep insights through natural language queries, searchability, and comparative analysis. How it works: Data Storage & Integration: Spreadsheet data is imported into a no-code database (NocoDB) System connects with an AI data analyst agent Agent accesses table metadata and column information Query Processing: Users input natural language questions AI agent interprets queries and converts them to database filters System retrieves relevant data using filter formulas AI synthesizes responses with analysis and insights Advanced Capabilities: Performs comparative analysis across multiple data points Handles complex multi-part queries Step by step setup: Create account on nocodb.com Create table by importing csv, copy table id Create API token https://app.nocodb.com/#/account/tokens In workflow, settings node, update with table id In NocoDB tool node, setup authentication with API token created in step 3 Specify the workspace and base fields after connecting to NocoDB

This workflow implements a custom tool via JavaScript code which returns a random color to users and excludes the given colors. Note that to use this template, you need to be on n8n version 1.19.4 or later.

This workflow allows you to ask questions about data stored in a database using AI. To use it, you'll need an OpenAI API key (although you could also swap in a model from another service). Supported databases: Postgres MySQL SQLite The workflow uses n8n's embedded chat, but you could also modify it to work with a chat service such as Slack, MS Teams or WhatsApp. Note that to use this template, you need to be on n8n version 1.19.4 or later.

⚙️🛠️🚀🤖🦾 This template is a PoC of a ReAct AI Agent capable of fetching random pages (not only Wikipedia or Google search results). On the top part there's a manual chat node connected to a LangChain ReAct Agent. The agent has access to a workflow tool for getting page content. The page content extraction starts with converting query parameters into a JSON object. There are 3 pre-defined parameters: url** – an address of the page to fetch method** = full / simplified maxlimit** - maximum length for the final page. For longer pages an error message is returned back to the agent Page content fetching is a multistep process: An HTTP Request mode tries to get the page content. If the page content was successfuly retrieved, a series of post-processing begin: Extract HTML BODY; content Remove all unnecessary tags to recude the page size Further eliminate external URLs and IMG scr values (based on the method query parameter) Remaining HTML is converted to Markdown, thus recuding the page lengh even more while preserving the basic page structure The remaining content is sent back to an Agent if it's not too long (maxlimit = 70000 by default, see CONFIG node). NB: You can isolate the HTTP Request part into a separate workflow. Check the Workflow Tool description, it guides the agent to provide a query string with several parameters instead of a JSON object. Please reach out to Eduard is you need further assistance with you n8n workflows and automations! Note that to use this template, you need to be on n8n version 1.19.4 or later.

This workflow allows you to ask questions about a PDF document. The answers are provided by an AI model of your choice, and the answer includes a citation pointing to the information it used. You can use n8n’s built-in chat interface to ask the questions, or you could customise this workflow to use another one (e.g. Slack, Teams, etc.) Example The workflow is set up with the Bitcoin whitepaper. So you could ask things like: Question: “Which email provider does the creator of Bitcoin use?“ Answer: “GMX [Bitcoin whitepaper.pdf, lines 1-35]” Requirements A Pinecone account (they have a free tier at the time of writing that is easily enough for this workflow) Access to a large language model (e.g. an OpenAI account) Customizing this workflow The workflow only reads in one document, but you could customise it to read in all the documents in a folder (or more). The workflow is set up to use GPT 3.5, but you could swap that out for any other model (including self-hosted ones).

Overview This workflow aims at providing data visualization to a native SQL Agent. Together, they can help with fostering data analysis and data visualization within a team. It uses the native SQL Agent that works well and adds some visualization capabilities thanks to OpenAI Structured Output and Quickchart.io. How it works The first part of the workflow is a regular SQL Agent: it connects to a Database and is able to query it and translate the response in a human format. Then, the Text Classifier is deciding if the user would benefit from a chart, supporting the SQL Agent's response. If it does, then it executes the subworkflow to dynamically generate a chart and append the chart to the response from the SQL Agent. If it doesn't, then the SQL Agent response is directly outputted. The sub-workflow calls OpenAI through the HTTP Request node to retrieve a chart definition. In the "set response" node, the chart definition is added at the end of a quickchart.io URL - the URL to the chart image. It is sent back to the AI Agent. How to use it Use an existing or create a new database. For example, I've used this Kaggle dataset and uploaded it to a Supabase DB. Add the PostgreSQL or MySQL credentials. Alternatively, you can use SQLite binary files (check this template). Activate the workflow. Start chatting with the AI SQL Agent. If the Text Classifier considers a chart would be useful, it will generate a chart in addition to the response from the SQL Agent. Notes The full Quickchart.io specifications have not been integrated, thus there are some possible glitches (e.g., due to the size of the graph, radar graphs are not displayed properly).

Transforming Emails into Podcasts 🎙️ Check out this channel for example. The n8n workflow described here aims to revolutionize the way users engage with promotional emails by converting them into entertaining audio podcasts. This innovative project leverages automation through n8n to streamline tasks and enhance user experience. Project Benefit 🎧🌟 The primary goal of this project is to transform "CATEGORY_PROMOTIONS" emails into engaging audio content. By converting text into speech, users can enjoy promotional material hands-free, making it easier to consume information while on the go or relaxing. The workflow consists of several key steps orchestrated seamlessly to deliver a delightful experience to users. How to Use the Workflow: Gmail trigger Node: Initiates the workflow by fetching "CATEGORY_PROMOTIONS" emails at regular intervals. The Gmail Trigger node in your N8N workflow is set to poll for new emails every minute and is configured to filter emails with the label "CATEGORY_PROMOTIONS" before triggering the workflow. Steps to Use Filters Inside the Gmail Trigger Node: Configure Gmail Trigger Node: Set "Poll Times" to "Every Minute" to check for new emails at regular intervals. Enable the "Simple" toggle if you want to simplify the node interface. Under "Filters", specify the label IDs you want to filter by. In this case, it's set to "CATEGORY_PROMOTIONS". Adjust any additional options as needed. // Configure Gmail Trigger node pollTimes: { item: [ { mode: "everyMinute" } ] }, simple: false, filters: { labelIds: [ "CATEGORY_PROMOTIONS" ] }, options: {} Save and Execute: Save your workflow and execute it to start monitoring your Gmail account for new emails with the specified label filter. By following these steps, your workflow will effectively trigger based on new emails that match the "CATEGORY_PROMOTIONS" label in your Gmail account. Get message content Node: Extracts the email content for processing. Summarization Chain Node: Generates concise summaries using advanced methods for better readability. Delete the unnecessary items Node: Removes irrelevant details from the email content. Text to Free TTS Node: Converts the summary text into speech using Free TTS technology. Convert from base64 to File Node: Transforms the audio data into a compatible file format. Merge Text with Audio Node: Combines the text and audio components seamlessly. Aggregate in same cell Node: Gathers all processed data for finalization. Send Message to Telegram Node: Dispatches the audio message along with a caption to a designated Telegram chat ID. By automating these tasks, the workflow ensures efficient communication and delivers content in a more engaging format, fostering a positive user experience. Configuration Instructions: The configuration of this workflow involves setting up the necessary nodes and establishing connections between them. Each node performs a specific function crucial to the overall operation of the workflow. Additionally, credentials need to be provided for accessing Gmail and OpenAI services to enable seamless data processing and summarization. Utilizing Text-to-Speech API 🎧 In addition to n8n automation, an external Text-to-Speech API plays a pivotal role in generating audio content from text data. By sending a POST request with JSON data containing the text and voice preferences, users can quickly receive audio files of the converted content. The API offers a straightforward interface for text-to-speech conversion, making it ideal for creating audio clips efficiently. To access this API, simply submit the desired text and voice selection to receive the generated speech audio file. The API endpoint can be accessed at https://tiktok-tts.weilnet.workers.dev/api/generation or through https://tiktokvoicegenerator.com/. In conclusion, this n8n workflow coupled with a Text-to-Speech API presents a powerful solution for transforming emails into captivating podcasts, enhancing user engagement and communication effectiveness. By embracing automation and innovative technologies, this project aims to improve user experience and streamline content delivery processes. 🌈✨🚀

Use case LLMs have provided a lot of value for several use cases. Especially some OpenAI models are proving to be quite valuable. However, it's sometimes not super accessible to chat with these models. This workflow enables you to chate directly with OpenAI's GPT-3.5 via Telegram. How it works A simple telegram bot that connects to your botfather bot to give AI responses, using OpenAI's GPT 3.5 model, to a user's messages with emojis. What to do Add your telegram API key and your OpenAI api key and have fun!

How it works: Using a Crew of AI agents (Senior Researcher, Visionary, and Senior Editor), this crew will automatically determine the right questions to ask to produce a detailed fundamental stock analysis. This application has two components: a front-end and a Stock Q&A engine. The front end is the team of agents automatically figuring out the questions to ask, and the back-end part is the ability to answer those questions with the SEC 10K data. This template implements the Stock Q&A engine. For the front-end of the application, you can choose one of two options: using CrewAI with the Replit environment (code approach) fully visual approach with n8n template (AI-powered automated stock analysis) Setup steps: Use first workflow in template to upsert a company annual report PDF (such as from SEC 10K filling) Get URL for Webhook in second workflow template CrewAI front-end: Youtube overview video Fork this AI Agent environment Crew Agent Environment Set the webhook URL into N8N_WEBHOOK_URL variable Set OpenAI_API_KEY variable

This workflow is an experiment to integrate charts in AI Agents, using the new Structured Output from OpenAI and Quickchart.io. How it works Users chat with an AI Agent. Anytime the AI Agent considers a chart is needed, it calls a tool to generate a chart OpenAI generates a chart using the Quickchart definition This object is added at the end of a Quickchart.io URL (see documentation) The url is added in the conversation via the AI Agent as markdown. Set up steps Create an OpenAI API Key Create the OpenAI credentials Use the credentials for the HTTP Request node (as Predefined Credential type) Activate your workflow Start chatting For example, you can ask the AI Agent to generate a chart about the top 5 movies at the box office Start exploring the limits Shout-out Quickchart.io is an amazing open source project that provides a free API to test. Go check them out! Example of chart

Time Logging on Clockify Using Slack How it works This workflow simplifies time tracking for teams and agencies by integrating Slack with Clockify. It enables users to log, update, or delete time entries directly within Slack, leveraging an AI-powered assistant for seamless and conversational interactions. Key features include: Effortless Time Logging**: Create and manage time entries in Clockify without leaving Slack. AI-Powered Assistant**: Get step-by-step guidance to ensure accurate and efficient time logging. Project and Client Management**: Retrieve project and client information from Clockify effortlessly. Overlap Prevention**: Avoid overlapping entries with built-in time validation. Automated Descriptions**: Generate ethical, grammatically correct descriptions for time logs. Set up steps 1. Prepare your integrations Ensure you have active accounts for both Slack and Clockify. Generate your Clockify API credentials for integration. 2. Import the workflow Download and import the workflow template into your n8n instance. Configure the workflow to connect with your Slack and Clockify accounts. 3. Configure the workflow Add your Clockify API credentials in the workflow settings. Set up the Slack Trigger to listen for app mentions or specific commands. 4. Test the workflow Use Slack to create a time entry and verify it in Clockify. Test updating and deleting existing entries to ensure smooth functionality. Check for any overlapping time logs or incorrect data entries. Why use this workflow? Efficiency**: Eliminate the need to switch between tools for time tracking. Accuracy**: AI-driven validation ensures error-free entries. Automation**: Simplify repetitive tasks like updating or deleting time logs. Proactive Guidance**: Conversational assistant ensures smooth operations.

This is a demo workflow to showcase how to use Supabase to embed a document, retrieve information from the vector store via chat and update the database. Setup steps: set your credentials for Supabase set your credentials for an AI model of your choice set credentials for any service you want to use to upload documents please follow the guidelines in the workflow itself (Sticky Notes) Feedback & Questions If you have any questions or feedback about this workflow - Feel free to get in touch at [email protected]

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.

This n8n template scrapes a list of AI grants from grants.gov and qualifies them using AI; determining interest and eligibility for the business. It then sends an email alert of interesting items to team members in an email. The template also shows how you can use the "Remove Duplicates" node to simplify deduplication of external listings without the need to manage this yourself. Not particularly interested in AI Grants? This template works for other tender websites as long as you're able to scrape them. How it works A scheduled trigger is set to fetch a list of AI grants listed on the grants.gov website in the past day. A Remove Duplicates node is used to track Grant IDs to filter out those already processed by the workflow. New grants are summarized and analysed by AI nodes to determine eligibility and interest which is then saved to an Airtable database. Another scheduled trigger starts a little later than the first to collect and summarize the new grants The results are then compiled into an email template using the HTML node, in the form of a newsletter designed to alert and brief team members of new AI grants. This email is then sent to a list of subscribers using the gmail node. How to use Make a copy of sample Airtable here: https://airtable.com/appiNoPRvhJxz9crl/shrRdP6zstgsxjDKL The filters for fetching the grants is currently set to the "AI" category. Feel free to change this to include more categories. Not interested in grants, this template can works for other sources of leads just change the endpoint and how you're defining the item ID to track. Requirements Airtable for database OpenAI for LLM Note: These are not hard requirements and can be exchanged for services available to you. customising the workflow "Eligibility" criteria at this stage may be better served by identifying hard blockers instead ie. certifications, geographical considerations or certain legal checks. Be sure to mention any hard blockers into the Eligibility prompt. Not particularly interested in AI prompts? This template works for other tender websites as long as you're able to scrape them.

Who is this for? This workflow is for all sales reps and lead generation manager who need to prepare their prospecting activities, and find relevant information to personalize their outreach. Use Case This workflow allows you to do account research with the web using AI. It has the potential to replace manual work done by sales rep when preparing their prospecting activities by searching complex information available online. What this workflow does The advanced AI module has 2 capabilities: Research Google using SerpAPI Visit and get website content using a sub-workflow From an unstructured input like a domain or a company name. It will return the following properties: domain company Linkedin Url cheapest plan has free trial has entreprise plan has API market (B2B or B2C) The strength of n8n here is that you can adapt this workflow to research whatever information you need. You just have to precise it in the prompt and to precise the output format in the "Strutured Output Parser" module. Detailed instructions + video guide can be found by following this link.

Video Guide I prepared a detailed guide explaining how to set up and implement this scenario, enabling you to chat with your documents stored in Supabase using n8n. Youtube Link Who is this for? This workflow is ideal for researchers, analysts, business owners, or anyone managing a large collection of documents. It's particularly beneficial for those who need quick contextual information retrieval from text-heavy files stored in Supabase, without needing additional services like Google Drive. What problem does this workflow solve? Manually retrieving and analyzing specific information from large document repositories is time-consuming and inefficient. This workflow automates the process by vectorizing documents and enabling AI-powered interactions, making it easy to query and retrieve context-based information from uploaded files. What this workflow does The workflow integrates Supabase with an AI-powered chatbot to process, store, and query text and PDF files. The steps include: Fetching and comparing files to avoid duplicate processing. Handling file downloads and extracting content based on the file type. Converting documents into vectorized data for contextual information retrieval. Storing and querying vectorized data from a Supabase vector store. File Extraction and Processing: Automates handling of multiple file formats (e.g., PDFs, text files), and extracts document content. Vectorized Embeddings Creation: Generates embeddings for processed data to enable AI-driven interactions. Dynamic Data Querying: Allows users to query their document repository conversationally using a chatbot. Setup N8N Workflow Fetch File List from Supabase: Use Supabase to retrieve the stored file list from a specified bucket. Add logic to manage empty folder placeholders returned by Supabase, avoiding incorrect processing. Compare and Filter Files: Aggregate the files retrieved from storage and compare them to the existing list in the Supabase files table. Exclude duplicates and skip placeholder files to ensure only unprocessed files are handled. Handle File Downloads: Download new files using detailed storage configurations for public/private access. Adjust the storage settings and GET requests to match your Supabase setup. File Type Processing: Use a Switch node to target specific file types (e.g., PDFs or text files). Employ relevant tools to process the content: For PDFs, extract embedded content. For text files, directly process the text data. Content Chunking: Break large text data into smaller chunks using the Text Splitter node. Define chunk size (default: 500 tokens) and overlap to retain necessary context across chunks. Vector Embedding Creation: Generate vectorized embeddings for the processed content using OpenAI's embedding tools. Ensure metadata, such as file ID, is included for easy data retrieval. Store Vectorized Data: Save the vectorized information into a dedicated Supabase vector store. Use the default schema and table provided by Supabase for seamless setup. AI Chatbot Integration: Add a chatbot node to handle user input and retrieve relevant document chunks. Use metadata like file ID for targeted queries, especially when multiple documents are involved. Testing Upload sample files to your Supabase bucket. Verify if files are processed and stored successfully in the vector store. Ask simple conversational questions about your documents using the chatbot (e.g., "What does Chapter 1 say about the Roman Empire?"). Test for accuracy and contextual relevance of retrieved results.

Use n8n to bring data from any API to your AI. This workflow uses the Chat Trigger to provide the chat interface, and the Custom n8n Workflow Tool to call a second workflow that calls the API. The second workflow uses AI functionality to refine the API request based on the user's query. It then makes an API call, and returns the response to the main workflow. This workflow is used in Advanced AI examples | Call an API to fetch data in the documentation. To use this workflow: Load it into your n8n instance. Add your credentials as prompted by the notes. Requires n8n 1.28.0 or above

This n8n template demonstrates a simple approach to using AI to automate the generation of blog content which aligns to your organisation's brand voice and style by using examples of previously published articles. In a way, it's quick and dirty "training" which can get your automated content generation strategy up and running for very little effort and cost whilst you evaluate our AI content pipeline. How it works In this demonstration, the n8n.io blog is used as the source of existing published content and 5 of the latest articles are imported via the HTTP node. The HTML node is extract the article bodies which are then converted to markdown for our LLMs. We use LLM nodes to (1) understand the article structure and writing style and (2) identify the brand voice characteristics used in the posts. These are then used as guidelines in our final LLM node when generating new articles. Finally, a draft is saved to Wordpress for human editors to review or use as starting point for their own articles. How to use Update Step 1 to fetch data from your desired blog or change to fetch existing content in a different way. Update Step 5 to provide your new article instruction. For optimal output, theme topics relevant to your brand. Requirements A source of text-heavy content is required to accurately breakdown the brand voice and article style. Don't have your own? Maybe try your competitors? OpenAI for LLM - though I recommend exploring other models which may give subjectively better results. Wordpress for blog but feel free to use other preferred publishing platforms. Customising this workflow Ideally, you'd want to "train" your agent on material which is similar to your output ie. your social media post may not get the best results from your blog content due to differing formats. Typically, this brand voice extraction exercise should run once and then be cached somewhere for reuse later. This would save on generation time and overall cost of the workflow.

Video Guide I prepared a detailed guide to help you set up your workflow effectively, enabling you to extract insights from YouTube for content generation using an AI agent. Youtube Link Who is this for? This workflow is ideal for content creators, marketers, and analysts looking to enhance their YouTube strategies through data-driven insights. It’s particularly beneficial for individuals wanting to understand audience preferences and improve their video content. What problem does this workflow solve? Navigating the content generation and optimization process can be complex, especially without significant audience insight. This workflow automates insights extraction from YouTube videos and comments, empowering users to create more engaging and relevant content effectively. What this workflow does The workflow integrates various APIs to gather insights from YouTube videos, enabling automated commentary analysis, video transcription, and thumbnail evaluation. The main functionalities include: Extracting user preferences from comments. Transcribing video content for enhanced understanding. Analyzing thumbnails via AI for maximum viewer engagement insights. AI Insights Extraction: Automatically pulls comments and metrics from selected YouTube creators to evaluate trends and gaps. Dynamic Video Planning: Uses transcriptions to help creators outline video scripts and topics based on audience interest. Thumbnail Assessment: Provides analysis on thumbnail designs to improve click-through rates and viewer attraction. Setup N8N Workflow API Setup: Create a Google Cloud project and enable the YouTube Data API. Generate an API key to be included in your workflow requests. YouTube Creator and Video Selection: Start by defining a request to identify top creators based on their video views. Capture the YouTube video IDs for further analysis of comments and other video metrics. Comment Analysis: Gather comments associated with the selected videos and analyze them for user insights. Video Transcription: Utilize the insights from transcriptions to formulate content plans. Thumbnail Analysis: Evaluate your video thumbnails by submitting the URL through the OpenAI API to gain insights into their effectiveness.

Who is this for? This workflow is for everyone who wants to have easier access to their Odoo sales data without complex queries. Use Case To have a clear overview of your sales data in Odoo you typically needs to extract data from it manually to analyse it. This workflow uses OpenAI's language models to create an intelligent chatbot that provides conversational access to your Odoo sales opportunity data. How it works Creates a summary of all Odoo sales opportunities using OpenAI Uses that summary as context for the OpenAI chat model Keeps the summary up to date using a schedule trigger Set up steps: Configure the Odoo credentials Configure OpenAI credentials Toggle "Make Chat Publicly Available" from the Chat Trigger node.

Video Demo: Click here to see a video of this workflow in action. Summary Description: The "IT Department Q&A Workflow" is designed to streamline and automate the process of handling IT-related inquiries from employees through Slack. When an employee sends a direct message (DM) to the IT department's Slack channel, the workflow is triggered. The initial step involves the "Receive DMs" node, which listens for new messages. Upon receiving a message, the workflow verifies the webhook by responding to Slack's challenge request, ensuring that the communication channel is active and secure. Once the webhook is verified, the workflow checks if the message sender is a bot using the "Check if Bot" node. If the sender is identified as a bot, the workflow terminates the process to avoid unnecessary actions. If the sender is a human, the workflow sends an acknowledgment message back to the user, confirming that their query is being processed. This is achieved through the "Send Initial Message" node, which posts a simple message like "On it!" to the user's Slack channel. The core functionality of the workflow is powered by the "AI Agent" node, which utilizes the OpenAI GPT-4 model to interpret and respond to the user's query. This AI-driven node processes the text of the received message, generating an appropriate response based on the context and information available. To maintain conversation context, the "Window Buffer Memory" node stores the last five messages from each user, ensuring that the AI agent can provide coherent and contextually relevant answers. Additionally, the workflow includes a custom Knowledge Base (KB) tool (see that tool template here) that integrates with the AI agent, allowing it to search the company's internal KB for relevant information. After generating the response, the workflow cleans up the initial acknowledgment message using the "Delete Initial Message" node to keep the conversation thread clean. Finally, the generated response is sent back to the user via the "Send Message" node, providing them with the information or assistance they requested. This workflow effectively automates the IT support process, reducing response times and improving efficiency. To quickly deploy the Knowledge Ninja app in Slack, use the app manifest below and don't forget to replace the two sample urls: { "display_information": { "name": "Knowledge Ninja", "description": "IT Department Q&A Workflow", "background_color": "#005e5e" }, "features": { "bot_user": { "display_name": "IT Ops AI SlackBot Workflow", "always_online": true } }, "oauth_config": { "redirect_urls": [ "Replace everything inside the double quotes with your slack redirect oauth url, for example: https://n8n.domain.com/rest/oauth2-credential/callback" ], "scopes": { "user": [ "search:read" ], "bot": [ "chat:write", "chat:write.customize", "groups:history", "groups:read", "groups:write", "groups:write.invites", "groups:write.topic", "im:history", "im:read", "im:write", "mpim:history", "mpim:read", "mpim:write", "mpim:write.topic", "usergroups:read", "usergroups:write", "users:write", "channels:history" ] } }, "settings": { "event_subscriptions": { "request_url": "Replace everything inside the double quotes with your workflow webhook url, for example: https://n8n.domain.com/webhook/99db3e73-57d8-4107-ab02-5b7e713894ad", "bot_events": [ "message.im" ] }, "org_deploy_enabled": false, "socket_mode_enabled": false, "token_rotation_enabled": false } }

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.

Workflow Description This workflow is a powerful, fully automated web query and semantic reranking system that allows users to perform precise, detailed searches, intelligently rank search results and provide high-quality, structured output. Built with AI-powered components, the workflow leverages semantic query generation, result re-ranking, and real-time reporting to deliver actionable insights. It is particularly well-suited for real-time data retrieval, market research, and any domain requiring automated yet customizable search result processing. How It Works Webhook Integration for Input: The workflow begins with a Webhook Node that captures the user's search query as input, enabling seamless integration with other systems. Step 1: Semantic Query Generation (Powered by "Semantic Search - Query Maker"): Using AI (Google Gemini), the initial query is refined and transformed into a context-aware, expert-level search query. The process ensures that the search engine retrieves the most relevant and precise results. Step 2: Web Search Execution: A free Brave Search API processes the refined query to fetch search results, ensuring speed and cost efficiency. Step 3: Semantic Re-Ranking of Results (Powered by "Semantic Search - Result Re-Ranker"): The workflow reranks the search results based on relevance to the original question, prioritizing the most relevant URLs dynamically. Results are passed through AI-powered intelligent reranking to ensure the final output reflects optimal relevance and quality. Step 4: Structured Output Generation: Results are converted into a well-structured, organized JSON format, ranking the top 10 search results with their titles, links, and descriptions. Missing ranks (if fewer than 10 results) are handled gracefully with placeholders, ensuring consistency. Step 5: Real-Time Reporting: The reranked search results are sent back to the user or integrated system via the Webhook Node in a JSON-formatted response. Reports are highly structured and ready for downstream processing or consumption. Key Features AI-Powered Query Refinement: Transforms basic queries into detailed, expert-level search terms for optimal results. Dual-Stage Semantic Search: Combines query generation and result reranking for precise, high-relevance outputs. Top 10 Result Reranking: Dynamically ranks and organizes the top 10 results based on semantic relevance to the query. Customizable Integration: Fully modifiable for alternative APIs or integrations, such as other search engines or custom ranking logic. JSON-Formatted Structured Results: Outputs reranked results in a standardized format, ideal for integration into systems requiring machine-readable data. Webhook-Based Flexibility: Works seamlessly with Webhook inputs for easy deployment in diverse workflows. Cost-Effective API Usage: Pre-integrated with the free Brave Search API, minimizing operational costs while delivering accurate search results. Instructions for API Setup Brave Search API: Visit api.search.brave.com to obtain a free-tier API key for web search. AI Integration (Google Gemini): Visit Google AI Studio and generate an API key for semantic query generation and reranking. Webhook Configuration: Set up the input Webhook to capture search queries and the output Webhook to deliver reranked results. Why Choose This Workflow? Precision and Relevance**: Combines AI-based query generation with advanced reranking for accurate results. Fully Customizable**: Easily adapt the workflow to alternative APIs, search engines, or ranking logic. Real-Time Insights**: Provides structured, real-time output ready for immediate use. Scalable and Modular**: Ideal for businesses, researchers, and data analysts needing a robust, repeatable solution. Tags AI Workflow, Semantic Search, Query Refinement, Search Result Reranking, Real-Time Search, Web Search Automation, Google Search, Brave Search, News Search, API Integration, Market Research, Competitive Intelligence, Business Intelligence,Google Gemini, Anthropic Claude, OpenAI, GPT, LLM

This workflow uses AI to analyze customer sentiment from product feedback. If the sentiment is negative, AI will determine whether offering a coupon could improve the customer experience. Upon completing the sentiment analysis, the workflow creates a personalized email templates. This solution streamlines the process of engaging with customers post-purchase, particularly when addressing dissatisfaction, and ensures that outreach is both personalized and automated. This workflow won the 1st place in our last AI contest. Note that to use this template, you need to be on n8n version 1.19.4 or later.

Use case This workflow enables a Telegram bot that can: Accept speech input in one of 55 supported languages Automatically detect the language spoken and translate the speech to another language Responds back with the translated speech output. This allows users to communicate across language barriers by simply speaking to the bot, which will handle the translation seamlessly. How does it work? Translation In the translation step the workflow converts the user's speech input to text and detects the language of the input text. If it's English, it will translate to French. If it's French, it will translate to English. To change the default translation languages, you can update the prompt in the AI node. Output In the output step, we provide the translated text output back to the user and speech output is generated in the translated language. Setup steps Obtain Telegram API Token Start a chat with the BotFather. Enter /newbot and reply with your new bot's display name and username. Copy the bot token and use it in the Telegram node credentials in n8n. Update the Settings node to customize the desired languages Activate the flow Full list of supported languages All supported languages:

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!

The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message is turned into a vector and compared to the vectors in Pinecone. The most similar vectors are retrieved and passed to OpenAI for generating a chat response. Note that to use this template, you need to be on n8n version 1.19.4 or later.

This n8n template builds a meeting assistant that compiles timely reminders of upcoming meetings filled with email history and recent LinkedIn activity of other people on the invite. This is then discreetly sent via WhatsApp ensuring the user is always prepared, informed and ready to impress! How it works A scheduled trigger fires hourly to check for upcoming personal meetings. When found, the invite is analysed by an AI agent to pull email and LinkedIn details of the other invitees. 2 subworkflows are then triggered for each invitee to (1) search for last email correspondence with them and (2) scrape their LinkedIn profile + recent activity for social updates. Using both available sources, another AI agent is used to summarise this information and generate a short meeting prep message for the user. The notification is finally sent to the user's WhatsApp, allowing them ample time to review. How to use There are a lot of moving parts in this template so in it's current form, it's best to use this for personal rather than team calendars. The LinkedIn scraping method used in this workflow requires you to paste in your LinkedIn cookies from your browser which essentially let's n8n impersonate you. You can retrieve this from dev console or ask someone technical for help! Note: It may be wise to switch to other LinkedIn scraping approaches which do not impersonate your own account for production. Requirements OpenAI for LLM Gmail for Email Google Calendar for upcoming events WhatsApp Business account for notifications Customising this workflow Try adding information sources which are relevant to you and your invitees. Such as company search, other social media sites etc. Create an on-demand version which doesn't rely on the scheduled trigger. Sometimes you want to know prepare for meetings hours or days in advance where this could help immensely.

Hacker News to Video Content Overview This workflow converts trending articles from Hacker News into engaging video content. It integrates AI-based tools to analyze, summarize, and generate multimedia content, making it ideal for content creators, educators, and marketers. Features Article Retrieval: Pulls trending articles from Hacker News. Limits the number of articles to process (configurable). Content Analysis: Uses OpenAI's GPT model to: Summarize articles. Assess their relevance to specific topics like automation or AI. Extract key image URLs. Image and Video Generation: Leonardo.ai: Creates stunning AI-generated images based on extracted prompts. RunwayML: Converts images into high-quality videos. Structured Content Creation: Parses content into structured formats for easy reuse. Generates newsletter-friendly blurbs and social media-ready captions. Cloud Integration: Uploads generated assets to: Dropbox Google Drive Microsoft OneDrive MinIO Social Media Posting (Optional): Supports posting to YouTube, X (Twitter), LinkedIn, and Instagram. Workflow Steps 1. Trigger Initiated manually via the "Test Workflow" button. 2. Fetch Articles Retrieves articles from Hacker News. Limits the results to avoid processing overload. 3. Content Filtering Evaluates if articles are related to AI/Automation using OpenAI's language model. 4. Image and Video Generation Generates: AI-driven image prompts via Leonardo.ai. Videos using RunwayML. 5. Asset Management Saves the output to cloud storage services or uploads directly to social media platforms. Prerequisites API Keys**: Hacker News OpenAI Leonardo.ai RunwayML Creatomate n8n Installation**: Ensure n8n is installed and configured locally or on a server. Credentials**: Set up credentials in n8n for all external services used in the workflow. Customization Replace Hacker News with any other data source node if needed. Configure the "Article Analysis" node for different topics. Adjust the cloud storage services or add custom storage options. Usage Import this workflow into your n8n instance. Configure your API credentials. Trigger the workflow manually or schedule it as needed. Check the outputs in your preferred cloud storage or social media platform. Notes Extend this workflow further by automating social media posting or newsletter integration. For any questions, refer to the official documentation or reach out to the creator. About the Creator This workflow was built by AlexK1919, an AI-native workflow automation architect. Check out the overview video for a quick demo. Tools Used Leonardo.ai** RunwayML** Creatomate** Hacker News API** OpenAI GPT** Feel free to adapt and extend this workflow to meet your specific needs! 🎉

Purpose Use a lightweight Voice Interface, for you and your entire organization, to interact with an AI Supervisor, a personal AI Assistant, which has access to your custom workflows. You can also connect the supervisor to your already existing Agents. Demo & Explanation How it works After recording a message in the Vagent App, it gets transcribed and sent in combination with a session ID to the registered webhook The Main Agent acts as a router. I interprets the message while using the stored chat history (bound to the session ID) and chooses which tool to use to perform the required action and. Tools on this level are workflows, which contain subordinated Agents. Since the Main Agent interprets the original message, the raw input is passed to the Tools/Sub-Agents as a separate parameter Within the Sub-Agents the actual processing takes place. Each of those has it’s separate chat memory (with a suffix to the main session ID), to achieve a clear separation of concerns Depending on the required action an HTTP Request Tool is called. The result is being formatted in Markdown and returned to the Main Agent with an additional short prompt, so it does not get interpreted by the Main Agent. Drafts are separated from a short message by added indentation (angle brackets). If some information is missing, no tool is called just yet, instead a message is returned back to the user The Main Agent then outputs the result from the called Sub-Agent. If a draft is included, it gets separated from the spoken output Finally the formatted output is returned as response to the webhook. The message is split into a spoken and a text version, which enables the App to read out loud unnecessary information like drafts in this example See the full documentation of Vagent: https://vagent.io/docs Setup Import this workflow into your n8n instance Follow the instructions given in the sticky notes on the canvas Setup your credentials. OpenAI can be replaced by another LLM in the workflow, but is required for the App to work. Google Calendar and Notion are required for all scenarios to work Copy the Webhook URL from the Webhook node of the main workflow Download the Vagent App from https://vagent.io In the settings paste your OpenAI API Token, the Webhook URL and the password defined for Header Auth Now you can use the App to interact with the Multi-Agent using your Voice by tapping the Mic symbol in the App to record your message. To use the chat trigger (for testing) properly, temporarily disable the nodes after the Tools Agent.

Instructions This automation enables you to just upload any Image (via Form) of a Logo Sheet, containing multiple Images of Product Logos (most likely) which brings them in some context to one another. After submitting an AI-Agent eats that Logo Sheet, turning it into an List of "Productname" and "Attributes", also checks if Tools are kind of similar to another, given the Context of the Image. We utilize AI Vision capabilities for that. NOTE: It might not be able to extract all informations. For a "upload and forget it" Workflow it works for me. You can even run it multiple times, to be sure. But if you need to make sure it extracts everything you might need to think about an Multi-Agent Setup with Validation-Agent Steps. Once the Agent finishes the extraction, it will traditionally and deterministicly add those Attributes to Airtable (Creates those, if not already existing.) and also Upserts the Tool Informations. It uses MD5 Hashes for turning Product Names into.. something fancy really, you could also use it without that, but I wanted to have something that looks atleast like an ID. Setup Set Up the Airtable like shown below. Update and set Credentials for all Airtable Nodes. Check or Adjust the Prompt of the Agent matching your use-case. Activate the Workflow. Open the Form (default: https://your-n8n.io/form/logo-sheet-feeder) Enjoy growing your Airtable. Enjoy the workflow! ❤️ let the work flow — Workflow Automation & Development

This workflow has multiple functionalities. It starts with a manual trigger, "When clicking 'Execute Workflow'", that activates two separate paths. The first path takes a preset string "Tell me a joke" and processes it through a custom Language Learning Model (LLM) chain node. This node interacts with an OpenAI node for query processing. The second path takes another preset string "What year was Einstein born?" and passes it to an "Agent" node. This agent further interacts with a Chat OpenAI node and a custom Wikipedia node to produce the required information. The workflow uses both built-in and custom nodes, and integrates with OpenAI for both paths. It's built for experimenting with language models, specifically in the context of conversational agents and information retrieval. Note that to use this template, you need to be on n8n version 1.19.4 or later.

This n8n template monitors active support issues in Linear.app to track the mood of their ongoing conversation between reporter and assignee using Sentiment Analysis. When sentiment dips into the negative, a notification is sent via Slack to alert the team. How it works A scheduled trigger is used to fetch recently updated issues in Linear using the GraphQL node. Each issue's comments thread is passed into a simple Information Extractor node to identify the overall sentiment. The resulting sentiment analysis combined with the some issue details are uploaded to Airtable for review. When the template is re-run at a later date, each issue is re-analysed for sentiment Each issue's new sentiment state is saved to the airtable whilst its previous state is moved to the "previous sentiment" column. An Airtable trigger is used to watch for recently updated rows Each matching Airtable row is filtered to check if it has a previous non-negative state but now has a negative state in its current sentiment. The results are sent via notification to a team slack channel for priority. Check out the sample Airtable here: https://airtable.com/appViDaeaFw4qv9La/shrq6HgeYzpW6uwXL How to use Modify the GraphQL filter to fetch issues to a relevant issue type, team or person. Update the Slack channel to ensure messages are sent to the correct location or persons. The Airtable also serves to give a snapshot of Sentiment across support tickets for a given period. It's possible to use this to assess the daily operations. Requirements Linear for issue tracking (but feel free to use another system if preferred) Airtable for Database OpenAI for LLM and Sentiment Analysis Customising the workflow Add more granular levels of sentiment to reduce the number of alerts. Explore different types of sentiment based on issue types and customer types. This may help prioritise alerts and response. Run across teams or categories of issues to get an overview of sentiment across the support organisation.

Purpose of workflow: The purpose of this workflow is to create a news reporter AI agent that automatically monitors specific news events and sends summary emails to the user. This tool aims to keep users up-to-date with the latest happenings on topics of interest without the need to constantly check multiple news sources manually. It's particularly useful for investors or researchers who must stay informed about specific events that may impact their work or investments. How it works: It leverages the power of large language models, specifically Perplexity's (perplexity.ai) online models accessed through Open Router (openrouter.ai), to understand and summarize up-to-date news. The workflow is scheduled to run at predetermined intervals (e.g., daily at 7 AM), automatically scanning for news on the specified topic, generating a summary, and sending it via email to the user. Setup: Sign up and generate an API key from Openrouter.ai This provides access to Perplexity's online language models Update Perplexity node with Openrouter.ai API key Specify the event/topic to monitor in the News Reporter node Activate workflow to turn on scheduling feature

Unleashing Creativity: Transforming Children's English Storytelling with Automation and AI Check this example: https://t.me/st0ries95 Summary In the realm of children's storytelling, automation is revolutionizing the way captivating tales are created and shared. This article highlights the transformative power of setting up a workflow for AI-powered children's English storytelling on Telegram. By delving into the use cases and steps involved, we uncover how this innovative approach is inspiring young minds and fostering a love for storytelling in children. Usecase The workflow for children's stories is a game-changer for content creators, educators, and parents seeking to engage children through imaginative and educational storytelling. Here's how this workflow is making a difference: Streamlined Content Creation: By providing a structured framework and automation for story generation, audio creation, and image production, the workflow simplifies the process of crafting captivating children's stories. Enhanced Educational Resources: Teachers can leverage this workflow to develop interactive educational materials that incorporate storytelling, making learning more engaging for students. Personalized Parental Engagement: Parents can share personalized stories with their children, nurturing a passion for reading and creativity while strengthening family bonds through shared storytelling experiences. Community Connection: Organizations and community groups can use the workflow to connect with their audience and promote literacy and creativity by creating and sharing children's stories. Inspiring Imagination: Through automated creation and sharing of enchanting stories, the workflow aims to spark imagination, inspire young minds, and instill a love for storytelling in children. Node Explanation OpenAI Chat Model: Utilizes the OpenAI Chat Model to generate text for the children's stories. Schedule Trigger: Triggers the workflow at set intervals (every 12 hours) to generate new stories. Recursive Character Text Splitter: Splits text into smaller chunks for processing. OpenAI Chat Model2: Another OpenAI Chat Model node for generating prompts for image creation. Send Story Text: Sends the generated story text to a specified Telegram chat. Send Audio for the Story: Sends audio files of the stories to the Telegram chat. Send Story Picture: Shares images related to the stories on Telegram. Create a Kids Stories: Generates captivating short tales for kids using prompts provided. Generate Audio for the Story: Converts generated text into audio files for storytelling. Create a Prompt for DALL-E: Creates prompts for generating images related to the stories. Generate a Picture for the Story: Generates pictures based on the prompts for visual storytelling. By embracing automation in children's storytelling, we unleash creativity, inspire young minds, and create magical experiences that resonate with both storytellers and listeners alike.

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 demonstrates how to create a really simple yet effective customer support channel and pipeline by combining Slack, Linear and AI tools. Built on n8n's ability to integrate anything, this workflow is intended for small support teams who want to maximise re-use of the tools they already have with an interface which is doesn't require any onboarding. Read the blog post here: https://blog.n8n.io/automated-customer-support-tickets-with-n8n-slack-linear-and-ai/ How it works The workflow is connected to a slack channel setup with the customer to capture support issues. Only messages which are tagged with a "✅" reaction are captured by the workflow. Messages are tagged by the support team in the channel. Each captured support issue is sent to the AI model to classify, prioritise and rewrite into a support ticket. The generated support ticket is uploaded to Linear for the support team to investigate and track. Support team is able to report back to the user via the channel when issue is fixed. Requirements Slack channel to be monitored Linear account and project Customising this workflow Don't have Linear? This workflow can work just as well with traditional ticketing systems like JIRA.

The workflow automates the process of creating a summarized and enriched podcast digest, which is then sent via email. Note that to use this template, you need to be on n8n version 1.19.4 or later.

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.

From PDF to Powerful Blog Posts: AI-Powered Content Transformation Turn complex documents into engaging digital content that drives results. This n8n Workflow uses AI to transforms lengthy PDFs into compelling blog posts that attract and retain readers while you focus on strategic initiatives. Time-Saving Innovation 🚅Lightning-Fast Processing Transform lengthy documents into polished blog content in under 1 minute, eliminating hours of manual work. Our system handles the heavy lifting, delivering up to a 95% reduction in content production time. 📱Intelligent Analysis The AI engine identifies and extracts key insights, organizing information for maximum impact. Each document undergoes comprehensive analysis to ensure no valuable content is overlooked. Advanced Content Optimization ✍️Dynamic Writing Styles Possible Adjust the prompt for multiple tone options: Professional for corporate communications Conversational for engaging blogs Thought leadership for industry authority 📊SEO-Ready Content Potential Adjust the prompt to automatically optimized for search engines, incorporating relevant keywords and semantic structure to improve visibility and drive organic traffic. Ideal Applications 🤼Content Marketing Teams Scale content production without sacrificing quality or consistency. Perfect for teams looking to maintain a robust publishing schedule while maximizing resource efficiency. 🏫Academic Communication Help researchers and institutions share complex findings with broader audiences through accessible, engaging content that maintains academic integrity. 🧑‍💻Digital Publishers Streamline the content transformation process while ensuring each piece meets modern digital standards and reader expectations. Transform your content strategy with an intelligent system that delivers consistent, high-quality results while dramatically reducing production time.

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.

Edit 19/11/2024: As explained on the workflow, the AI Agent with the original system prompt was not effective when using gpt4-o-mini. To address this, I optimized the prompt to work better with this model. You can find the prompts I’ve tested on this Notion Page. And yes, there is one that works well with gpt4-o-mini. AI Agent to chat with you Search Console Data, using OpenAI and Postgres This AI Agent enables you to interact with your Search Console data through a chat interface. Each node is documented within the template, providing sufficient information for setup and usage. You will also need to configure Search Console OAuth credentials. Follow this n8n documentation to set up the OAuth credentials. Important Notes Correctly Configure Scopes for Search Console API Calls It’s essential to configure the scopes correctly in your Google Search Console API OAuth2 credentials. Incorrect configuration can cause issues with the refresh token, requiring frequent reconnections. Below is the configuration I use to avoid constant re-authentication: Of course, you'll need to add your client_id and client_secret from the Google Cloud Platform app you created to access your Search Console data. Configure Authentication for the Webhook Since the webhook will be publicly accessible, don’t forget to set up authentication. I’ve used Basic Auth, but feel free to choose the method that best meets your security requirements. 🤩💖 Example of awesome things you can do with this AI Agent

This workflow was presented at the AI Developers meet up in San Fransico on 24 July, 2024. AI workflows Categorize incoming Gmail emails and assign custom Gmail labels. This example uses the Text Classifier node, simplifying this usecase. Ingest a PDF into a Pinecone vector store and chat with it (RAG example) AI Agent example showcasing the HTTP Request tool. We teach the agent how to check availability on a Google Calendar and book an appointment.

LangChain is a framework for building AI functionality that users large language models. By leveraging the functionality of LangChain, you can write even more powerful workflows. This workflow shows how you can write LangChain code within n8n, including importing LangChain modules. The workflow itself produces a summary of a YouTube video, when given the video's ID. Note that to use this template, you need to be on n8n version 1.19.4 or later.

This workflow demonstrates how to enrich data from a list of companies in a spreadsheet. While this workflow is production-ready if all steps are followed, adding error handling would enhance its robustness. Important notes Check legal regulations**: This workflow involves scraping, so make sure to check the legal regulations around scraping in your country before getting started. Better safe than sorry! Mind those tokens**: OpenAI tokens can add up fast, so keep an eye on usage unless you want a surprising bill that could knock your socks off! 💸 Main Workflow Node 1 - Webhook This node triggers the workflow via a webhook call. You can replace it with any other trigger of your choice, such as form submission, a new row added in Google Sheets, or a manual trigger. Node 2 - Get Rows from Google Sheet This node retrieves the list of companies from your spreadsheet. here is the Google Sheet Template you can use. The columns in this Google Sheet are: Company**: The name of the company Website**: The website URL of the company These two fields are required at this step. Business Area**: The business area deduced by OpenAI from the scraped data Offer**: The offer deduced by OpenAI from the scraped data Value Proposition**: The value proposition deduced by OpenAI from the scraped data Business Model**: The business model deduced by OpenAI from the scraped data ICP**: The Ideal Customer Profile deduced by OpenAI from the scraped data Additional Information**: Information related to the scraped data, including: Information Sufficiency: Description: Indicates if the information was sufficient to provide a full analysis. Options: "Sufficient" or "Insufficient" Insufficient Details: Description: If labeled "Insufficient," specifies what information was missing or needed to complete the analysis. Mismatched Content: Description: Indicates whether the page content aligns with that of a typical company page. Suggested Actions: Description: Provides recommendations if the page content is insufficient or mismatched, such as verifying the URL or searching for alternative sources. Node 3 - Loop Over Items This node ensures that, in subsequent steps, the website in "extra workflow input" corresponds to the row being processed. You can delete this node, but you'll need to ensure that the "query" sent to the scraping workflow corresponds to the website of the specific company being scraped (rather than just the first row). Node 4 - AI Agent This AI agent is configured with a prompt to extract data from the content it receives. The node has three sub-nodes: OpenAI Chat Model: The model used is currently gpt4-o-mini. Call n8n Workflow: This sub-node calls the workflow to use ScrapingBee and retrieves the scraped data. Structured Output Parser: This parser structures the output for clarity and ease of use, and then adds rows to the Google Sheet. Node 5 - Update Company Row in Google Sheet This node updates the specific company's row in Google Sheets with the enriched data. Scraper Agent Workflow Node 1 - Tool Called from Agent This is the trigger for when the AI Agent calls the Scraper. A query is sent with: Company name Website (the URL of the website) Node 2 - Set Company URL This node renames a field, which may seem trivial but is useful for performing transformations on data received from the AI Agent. Node 3 - ScrapingBee: Scrape Company's Website This node scrapes data from the URL provided using ScrapingBee. You can use any scraper of your choice, but ScrapingBee is recommended, as it allows you to configure scraper behavior directly. Once configured, copy the provided "curl" command and import it into n8n. Node 4 - HTML to Markdown This node converts the scraped HTML data to Markdown, which is then sent to OpenAI. The Markdown format generally uses fewer tokens than HTML. Improving the Workflow It's always a pleasure to share workflows, but creators sometimes want to keep some magic to themselves ✨. Here are some ways you can enhance this workflow: Handle potential errors Configure the scraper tool to scrape other pages on the website. Although this will cost more tokens, it can be useful (e.g., scraping "Pricing" or "About Us" pages in addition to the homepage). Instead of Google Sheets, connect directly to your CRM to enrich company data. Trigger the workflow from form submissions on your website and send the scraped data about the lead to a Slack or Teams channel.

This n8n template is designed to assist and improve customer support team member capacity by automating the resolution of long-lived and forgotten JIRA issues. How it works Schedule Trigger runs daily to check for long-lived unresolved issues and imports them into the workflow. Each Issue is handled as a separate subworkflow by using an execute workflow node. This allows parallel processing. A report is generated from the issue using its comment history allowing the issue to be classified by AI - determining the state and progress of the issue. If determined to be resolved, sentiment analysis is performed to track customer satisfaction. If negative, a slack message is sent to escalate, otherwise the issue is closed automatically. If no response has been initiated, an AI agent will attempt to search and resolve the issue itself using similar resolved issues or from the notion database. If a solution is found, it is posted to the issue and closed. If the issue is blocked and waiting for responses, then a reminder message is added. How to use This template searches for JIRA issues which are older than 7 days which are not in the "Done" status. Ensure there are some issues that meet this criteria otherwise adjust the search query to suit. Works best if you frequently have long-lived issues that need resolving. Ensure the notion tool is configured as to not read documents you didn't intend it to ie. private and/or internal documentation. Requirements JIRA for issues management OpenAI for LLM Slack for notifications Customising this workflow Why not try classifying issues as they are created? One use-case may be for quality control such as ensuring reporting criteria is adhered to, summarising and rephrasing issue for easier reading or adjusting priority.

This workflow is a modification of the previous template on how to create an SQL agent with LangChain and SQLite. The key difference – the agent has access only to the database schema, not to the actual data. To achieve this, SQL queries are made outside the AI Agent node, and the results are never passed back to the agent. This approach allows the agent to generate SQL queries based on the structure of tables and their relationships, without having to access the actual data. This makes the process more secure and efficient, especially in cases where data confidentiality is crucial. 🚀 Setup To get started with this workflow, you’ll need to set up a free MySQL server and import your database (check Step 1 and 2 in this tutorial). Of course, you can switch MySQL to another SQL database such as PostgreSQL, the principle remains the same. The key is to download the schema once and save it locally to avoid repeated remote connections. Run the top part of the workflow once to download and store the MySQL chinook database schema file on the server. With this approach, we avoid the need to repeatedly connect to a remote db4free database and fetch the schema every time. As a result, we reach greater processing speed and efficiency. 🗣️ Chat with your data Start a chat: send a message in the chat window. The workflow loads the locally saved MySQL database schema, without having the ability to touch the actual data. The file contains the full structure of your MySQL database for analysis. The Langchain AI Agent receives the schema, your input and begins to work. The AI Agent generates SQL queries and brief comments based solely on the schema and the user’s message. An IF node checks whether the AI Agent has generated a query. When: Yes: the AI Agent passes the SQL query to the next MySQL node for execution. No: You get a direct answer from the Agent without further action. The workflow formats the results of the SQL query, ensuring they are convenient to read and easy to understand. Once formatted, you get both the Agent answer and the query result in the chat window. 🌟 Example queries Try these sample queries to see the schema-driven AI Agent in action: Would you please list me all customers from Germany? What are the music genres in the database? What tables are available in the database? Please describe the relationships between tables. - In this example, the AI Agent does not need to create the SQL query. And if you prefer to keep the data private, you can manually execute the generated SQL query in your own environment using any database client or tool you trust 🗄️ 💭 The AI Agent memory node does not store the actual data as we run SQL-queries outside the agent. It contains the database schema, user questions and the initial Agent reply. Actual SQL query results are passed to the chat window, but the values are not stored in the Agent memory.

Purpose This workflow adds the capability to build a RAG on living data. In this case Notion is used as a Knowledge Base. Whenever a page is updated, the embeddings get upserted in a Supabase Vector Store. It can also be fairly easily adapted to PGVector, Pinecone, or Qdrant by using a custom HTTP request for the latter two. Demo How it works A trigger checks every minute for changes in the Notion Database. The manual polling approach improves accuracy and prevents changes from being lost between cached polling intervals. Afterwards every updated page is processed sequentially The Vector Database is searched using the Notion Page ID stored in the metadata of each embedding. If old entries exist, they are deleted. All blocks of the Notion Database Page are retrieved and combined into a single string The content is embedded and split into chunks if necessary. Metadata, including the Notion Page ID, is added during storage for future reference. A simple Question and Answer Chain enables users to ask questions about the embedded content through the integrated chat function Prerequisites To setup a new Vector Store in Supabase, follow this guide Prepare a simple Database in Notion with each Database Page containing at least a title and some content in the blocks section. You can of course also connect this to an existing Database of your choice. Setup Select your credentials in the nodes which require those If you are on an n8n cloud plan, switch to the native Notion Trigger by activating it and deactivating the Schedule Trigger along with its subsequent Notion Node Choose your Notion Database in the first Node related to Notion Adjust the chunk size and overlap in the Token Splitter to your preference Activate the workflow How to use Populate your Notion Database with useful information and use the chat mode of this workflow to ask questions about it. Updates to a Notion Page should quickly reflect in future conversations.

How it works Automates the retrieval of Calvin and Hobbes daily comics. Extracts the comic image URL from the website. Translates comic dialogues to English and Korean. Posts the comic and translations to Discord daily. Set up steps Estimated setup time: ~10-15 minutes. Use a Schedule Trigger to automate the workflow at 9 AM daily. Add nodes for parameter setup, HTTP request, data extraction, and integration with Discord. Add detailed notes to each node in the workflow for easy understanding.

This n8n template builds a simple WhatsApp chabot acting as a Sales Agent. The Agent is backed by a product catalog vector store to better answer user's questions. This template is intended to help introduce n8n users interested in building with WhatsApp. How it works This template is in 2 parts: creating the product catalog vector store and building the WhatsApp AI chatbot. A product brochure is imported via HTTP request node and its text contents extracted. The text contents are then uploaded to the in-memory vector store to build a knowledgebase for the chatbot. A WhatsApp trigger is used to capture messages from customers where non-text messages are filtered out. The customer's message is sent to the AI Agent which queries the product catalogue using the vector store tool. The Agent's response is sent back to the user via the WhatsApp node. How to use Once you've setup and configured your WhatsApp account and credentials First, populate the vector store by clicking the "Test Workflow" button. Next, activate the workflow to enable the WhatsApp chatbot. Message your designated WhatsApp number and you should receive a message from the AI sales agent. Tweak datasource and behaviour as required. Requirements WhatsApp Business Account OpenAI for LLM Customising this workflow Upgrade the vector store to Qdrant for persistance and production use-cases. Handle different WhatsApp message types for a more rich and engaging experience for customers.

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.

Purpose This workflow automatically creates Tasks from forwarded Emails, similar to Asana, but better. Emails are processed by AI and converted to rather actionable task. In addition this workflow is build in a way, that multiple users can share this single process by setting up their individual configuration through a user friendly portal (internal tool) instead of the need to manage their own workflows. Demo How it works One Gmail account is used to process inbound mails from different users. A custom web portal enables users to define “routes”. Thats where the mapping between an automatically generated Gmail Alias and a Notion Database URL, including the personal API Token, happens. Using a Gmail Trigger, new entries are split by the Email Alias, so the corresponding route can be retrieved from the Database connected to the portal. Every Email then gets processed by AI to get generate an actionable task and get a short summary of the original Email as well as some metadata. Based on a predefined structure a new Page is created in the corresponding Notion Database. Finally the Email is marked as “processed” in Gmail. If an error happens, the route gets paused for a possible overflow and the user gets notified by Email. Setup Create a new Google account (alternatively you can use an existing one and set up rules to keep your inbox organized) Create two Labels in Gmail: “Processed” and “Error” Clone this Softr template including the Airtable dataset and publish the application Clone this workflow and choose credentials (Gmail, Airtable) Follow the additional instructions provided within the workflow notes Enable the workflow, so it runs automatically in the background How to use Open published Softr application Register as a new user Create a new route containing the Notion API key and the Notion Database URL Expand the new entry to copy the Email address Save the address as a new contact in your Email provider of choice Forward an Email to it and watch how it gets converted to an actionable task Disclamer Airtable was chosen, so you can setup this template fairly quickly. It is advised to replace the persistence by something you own, like a self hosted SQL server, since we are dealing with sensitive information of multiple users This solution is only meant for building internal tools, unless you own an embed license for n8n.

This n8n workflow demonstrates how to automate oftern time-consuming form filling tasks in the early stages of the tendering process; the Request for Proposal document or "RFP". It does this by utilising a company's knowledgebase to generating question-and-answer pairs using Large Language Models. How it works A buyer's RFP is submitted to the workflow as a digital document that can be parsed. Our first AI agent scans and extracts all questions from the document into list form. The supplier sets up an OpenAI assistant prior loaded with company brand, marketing and technical documents. The workflow loops through each of the buyer's questions and poses these to the OpenAI assistant. The assistant's answers are captured until all questions are satisified and are then exported into a new document for review. A sales team member is then able to use this document to respond quickly to the RFP before their competitors. Example Webhook Request curl --location 'https://<n8n_webhook_url>' \ --form 'id="RFP001"' \ --form 'title="BlueChip Travel and StarBus Web Services"' \ --form 'reply_to="[email protected]"' \ --form 'data=@"k9pnbALxX/RFP Questionnaire.pdf"' Requirements An OpenAI account to use AI services. Customising the workflow OpenAI assistants is only one approach to hosting a company knowledgebase for AI to use. Exploring different solutions such as building your own RAG-powered database can sometimes yield better results in terms of control of how the data is managed and cost.

This is the first version of a template for a RAG/GenAI App using WordPress content. As creating, sharing, and improving templates brings me joy 😄, feel free to reach out on LinkedIn if you have any ideas to enhance this template! How It Works This template includes three workflows: Workflow 1**: Generate embeddings for your WordPress posts and pages, then store them in the Supabase vector store. Workflow 2**: Handle upserts for WordPress content when edits are made. Workflow 3**: Enable chat functionality by performing Retrieval-Augmented Generation (RAG) on the embedded documents. Why use this template? This template can be applied to various use cases: Build a GenAI application that requires embedded documents from your website's content. Embed or create a chatbot page on your website to enhance user experience as visitors search for information. Gain insights into the types of questions visitors are asking on your website. Simplify content management by asking the AI for related content ideas or checking if similar content already exists. Useful for internal linking. Prerequisites Access to Supabase for storing embeddings. Basic knowledge of Postgres and pgvector. A WordPress website with content to be embedded. An OpenAI API key Ensure that your n8n workflow, Supabase instance, and WordPress website are set to the same timezone (or use GMT) for consistency. Workflow 1 : Initial Embedding This workflow retrieves your WordPress pages and posts, generates embeddings from the content, and stores them in Supabase using pgvector. Step 0 : Create Supabase tables Nodes : Postgres - Create Documents Table: This table is structured to support OpenAI embedding models with 1536 dimensions Postgres - Create Workflow Execution History Table These two nodes create tables in Supabase: The documents table, which stores embeddings of your website content. The n8n_website_embedding_histories table, which logs workflow executions for efficient management of upserts. This table tracks the workflow execution ID and execution timestamp. Step 1 : Retrieve and Merge WordPress Pages and Posts Nodes : WordPress - Get All Posts WordPress - Get All Pages Merge WordPress Posts and Pages These three nodes retrieve all content and metadata from your posts and pages and merge them. Important: ** **Apply filters to avoid generating embeddings for all site content. Step 2 : Set Fields, Apply Filter, and Transform HTML to Markdown Nodes : Set Fields Filter - Only Published & Unprotected Content HTML to Markdown These three nodes prepare the content for embedding by: Setting up the necessary fields for content embeddings and document metadata. Filtering to include only published and unprotected content (protected=false), ensuring private or unpublished content is excluded from your GenAI application. Converting HTML to Markdown, which enhances performance and relevance in Retrieval-Augmented Generation (RAG) by optimizing document embeddings. Step 3: Generate Embeddings, Store Documents in Supabase, and Log Workflow Execution Nodes: Supabase Vector Store Sub-nodes: Embeddings OpenAI Default Data Loader Token Splitter Aggregate Supabase - Store Workflow Execution This step involves generating embeddings for the content and storing it in Supabase, followed by logging the workflow execution details. Generate Embeddings: The Embeddings OpenAI node generates vector embeddings for the content. Load Data: The Default Data Loader prepares the content for embedding storage. The metadata stored includes the content title, publication date, modification date, URL, and ID, which is essential for managing upserts. ⚠️ Important Note : Be cautious not to store any sensitive information in metadata fields, as this information will be accessible to the AI and may appear in user-facing answers. Token Management: The Token Splitter ensures that content is segmented into manageable sizes to comply with token limits. Aggregate: Ensure the last node is run only for 1 item. Store Execution Details: The Supabase - Store Workflow Execution node saves the workflow execution ID and timestamp, enabling tracking of when each content update was processed. This setup ensures that content embeddings are stored in Supabase for use in downstream applications, while workflow execution details are logged for consistency and version tracking. This workflow should be executed only once for the initial embedding. Workflow 2, described below, will handle all future upserts, ensuring that new or updated content is embedded as needed. Workflow 2: Handle document upserts Content on a website follows a lifecycle—it may be updated, new content might be added, or, at times, content may be deleted. In this first version of the template, the upsert workflow manages: Newly added content** Updated content** Step 1: Retrieve WordPress Content with Regular CRON Nodes: CRON - Every 30 Seconds Postgres - Get Last Workflow Execution WordPress - Get Posts Modified After Last Workflow Execution WordPress - Get Pages Modified After Last Workflow Execution Merge Retrieved WordPress Posts and Pages A CRON job (set to run every 30 seconds in this template, but you can adjust it as needed) initiates the workflow. A Postgres SQL query on the n8n_website_embedding_histories table retrieves the timestamp of the latest workflow execution. Next, the HTTP nodes use the WordPress API (update the example URL in the template with your own website’s URL and add your WordPress credentials) to request all posts and pages modified after the last workflow execution date. This process captures both newly added and recently updated content. The retrieved content is then merged for further processing. Step 2 : Set fields, use filter Nodes : Set fields2 Filter - Only published and unprotected content The same that Step 2 in Workflow 1, except that HTML To Makrdown is used in further Step. Step 3: Loop Over Items to Identify and Route Updated vs. Newly Added Content Here, I initially aimed to use 'update documents' instead of the delete + insert approach, but encountered challenges, especially with updating both content and metadata columns together. Any help or suggestions are welcome! :) Nodes: Loop Over Items Postgres - Filter on Existing Documents Switch Route existing_documents (if documents with matching IDs are found in metadata): Supabase - Delete Row if Document Exists: Removes any existing entry for the document, preparing for an update. Aggregate2: Used to aggregate documents on Supabase with ID to ensure that Set Fields3 is executed only once for each WordPress content to avoid duplicate execution. Set Fields3: Sets fields required for embedding updates. Route new_documents (if no matching documents are found with IDs in metadata): Set Fields4: Configures fields for embedding newly added content. In this step, a loop processes each item, directing it based on whether the document already exists. The Aggregate2 node acts as a control to ensure Set Fields3 runs only once per WordPress content, effectively avoiding duplicate execution and optimizing the update process. Step 4 : HTML to Markdown, Supabase Vector Store, Update Workflow Execution Table The HTML to Markdown node mirrors Workflow 1 - Step 2. Refer to that section for a detailed explanation on how HTML content is converted to Markdown for improved embedding performance and relevance. Following this, the content is stored in the Supabase vector store to manage embeddings efficiently. Lastly, the workflow execution table is updated. These nodes mirros the **Workflow 1 - Step 3 nodes. Workflow 3 : An example of GenAI App with Wordpress Content : Chatbot to be embed on your website Step 1: Retrieve Supabase Documents, Aggregate, and Set Fields After a Chat Input Nodes: When Chat Message Received Supabase - Retrieve Documents from Chat Input Embeddings OpenAI1 Aggregate Documents Set Fields When a user sends a message to the chat, the prompt (user question) is sent to the Supabase vector store retriever. The RPC function match_documents (created in Workflow 1 - Step 0) retrieves documents relevant to the user’s question, enabling a more accurate and relevant response. In this step: The Supabase vector store retriever fetches documents that match the user’s question, including metadata. The Aggregate Documents node consolidates the retrieved data. Finally, Set Fields organizes the data to create a more readable input for the AI agent. Directly using the AI agent without these nodes would prevent metadata from being sent to the language model (LLM), but metadata is essential for enhancing the context and accuracy of the AI’s response. By including metadata, the AI’s answers can reference relevant document details, making the interaction more informative. Step 2: Call AI Agent, Respond to User, and Store Chat Conversation History Nodes: AI Agent** Sub-nodes: OpenAI Chat Model Postgres Chat Memories Respond to Webhook** This step involves calling the AI agent to generate an answer, responding to the user, and storing the conversation history. The model used is gpt4-o-mini, chosen for its cost-efficiency.

Introduction The Traveler Co-Pilot empowers you to confidently traverse the world, connecting with ease and breaking language barriers: Engage in conversations with locals Navigate menus at foreign eateries Comprehend road signs effortlessly. Features Seamless Speech-to-Speech Translation** Communicate in any of the 55 supported languages, and witness the bot translate your words into another language in real-time, all through speech. Visual Translation Magic** Capture images containing text, and the bot will work its magic by recognizing and translating the text into the desired language, right before your eyes. Setup Steps Open the Settings node and specify the languages you would like to work with

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

Who is this for This workflow is perfect for teams and individuals who manage extensive data in Notion and need a quick, AI-powered way to interact with their databases. If you're looking to streamline your knowledge management, automate searches, and get faster insights from your Notion databases, this workflow is for you. It’s ideal for support teams, project managers, or anyone who needs to query specific data across multiple records or within individual pages of their Notion setup. Check out the Notion template this Assistant is set up to use: https://www.notion.so/templates/knowledge-base-ai-assistant-with-n8n How it works The Notion Database Assistant uses an AI Agent built with Retrieval-Augmented Generation (RAG) to query this Knowledge Base style Notion database. The assistant can search across multiple properties like tags or question and retrieves content from inside individual Notion pages for additional context. Key features include: Querying the database with flexible filters. Searching within individual Notion pages and extracting relevant blocks. Providing a reference link to the exact Notion pages used to inform its responses, ensuring transparency and easy verification. This assistant uses two HTTP request tools—one for querying the Notion database and another for pulling data from within specific pages. It streamlines knowledge retrieval, offering a conversational, AI-driven way to interact with large datasets. Set up Find basic set up instructions inside the workflow itself or watch a quickstart video 👇

This n8n template leverages n8n's multi-form feature to build a 2 part job application submission journey which aims to eliminate the need for applicants to re-enter data found on their CVs/Resumes. How it works The application submission process starts with an n8n form trigger to accept CV files in the form of PDFs. The PDF is validated using the text classifier node to determine if it is a valid CV else the applicant is asked to reupload. A basic LLM node is used to extract relevant information from the CV as data capture. A copy of the original job post is included to ensure relevancy. Applicant's data is then sent to an ATS for processing. For our demo, we used airtable because we could attach PDFs to rows. Finally, a second form trigger is used for the actual application form. However, it is prefilled to save the applicant's time and allow them to amend any of the generated application fields. How to use Ensure to change the redirect URL in the form ending node to use the host domain of your n8n instance. Requirements OpenAI for LLM Airtable to capture applicant data Customising the workflow Application form is pretty basic for this demonstration but could be extended to ask more in-depth questions. If it fits the job, why not ask applicants to upload portfolio works and have AI describe/caption them.

Purpose of workflow: This AI-powered workflow is designed to automatically generate comprehensive, well-researched articles on any given topic. It utilizes a team of AI agents to streamline the research and writing process, producing high-quality content with proper citations and credible sources. How it works Multi-agent team: Research Leader: Plans and conducts initial research, creating a table of contents. Project Planner: Breaks down the table of contents into manageable sections. Research Assistants: Multiple agents that conduct in-depth research on assigned sections. Editor: Compiles and refines the final article, ensuring coherence and proper citations. Key features: Utilizes Perplexity AI for internet search and citation capabilities Produces well-structured articles with proper citations Customizable parameters (topic, tone, word count, number of sections) Step by step setup: Get account from OpenRouter.ai to access Perplexity API Set API key in the Perplexity API node Credential key name : Authorization and key value Bearer <api-key value>

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.

Template for Kids' Story in Arabic The n8n template for creating kids' stories in Arabic offers a versatile platform for storytellers to captivate young audiences with educational and interactive tales. It allows for customization to suit various use cases and can be set up effortlessly. Check this example: https://t.me/st0ries95 Use Cases Educational Platforms: Educational platforms can automate the creation and distribution of educational stories in Arabic for children using this template. By incorporating visual and auditory elements into the storytelling process, educational platforms can enhance learning experiences and engage young learners effectively. Children's Libraries: Children's libraries can utilize this template to curate and share a diverse collection of Arabic stories with young readers. The automated generation of visual content and audio files enhances the storytelling experience, encouraging children to immerse themselves in new worlds and characters through captivating narratives. Language Learning Apps: Language learning apps focused on Arabic can integrate this template to offer culturally rich storytelling experiences for children learning the language. By translating stories into Arabic and supplementing them with visual and auditory components, these apps can facilitate language acquisition in an enjoyable and interactive manner. Configuration Guide for Nodes OpenAI Chat Model Nodes: Functionality**: Allows interaction with the OpenAI GPT-4 Turbo model. Purpose**: Enables communication with advanced chat capabilities. Create a Prompt for DALL-E Node: Customization**: Tailor prompts for generating relevant visual content. Summarization**: Define prompts for visual content generation without text. Generate an Image for the Story Node: Resource Type**: Specifies image as the resource. Prompt Setup**: Configures prompt for textless image creation within the visual content. Generate Audio for the Story Node: Resource Type**: Chooses audio as the resource. Input Definition**: Sets input text for audio file generation. Translate the Story to Arabic Node: Chunking Mode Selection**: Allows advanced chunking mode choice. Summarization Configuration**: Sets method and prompts for story translation into Arabic. Send the Story To Channel Node: Channel ID**: Specifies the channel ID for sending the story text. Text Configuration**: Sets up the text to be sent to the channel. By following these node descriptions, users can effectively configure the n8n template for kids' stories in Arabic, tailoring it to specific use cases for a seamless and engaging storytelling experience for young audiences.