Notion AI Assistant Generator

This n8n workflow demonstrates how to automate customer interactions and appointment management via WhatsApp Business bot. After submitting a Google Form, the user receives a notification via WhatsApp. These notifications are sent via a template message. In case user sends a message to the bot, the text and user data is stored in Google Sheets. To reply back to the user, fill in the ReplyText column and change the Status to 'Ready'. In a few seconds n8n will fetch the unsent replies and deliver them one by one via WhatsApp Business node. Customize this workflow to fit your specific needs, connect different online services and enhance your customer communication! 🎉 Setup Instructions To get this workflow up and running, you'll need to: 👇 Create a WhatsApp template message on the Meta Business portal. Obtain an Access Token and WhatsApp Business Account ID from the Meta Developers Portal. This is needed for the WhatsApp Business Node to send messages. Set up a WhatsApp Trigger node with App ID and App Secret from the Meta Developers Portal. Right after that copy the WhatsApp Trigger URL and add it as a Callback URL in the Meta Developers Portal. This trigger is needed to receive incoming messages and their status updates. Connect your Google Sheets account for data storage and management. Check out the documentation page. ⚠️ Important Notes WhatsApp allows automatic custom text messages only within 24 hours of the last user message. Outside with time frame only approved template messages can be sent. The workflow uses a Google Sheet to manage form submissions, incoming messages and prepare responses. You can replace these nodes and connect the WhatsApp bot with other systems.

This workflow offers an effective way to handle a chatbot's functionality, making use of multiple tools for information retrieval, conversation context storage, and message sending. It's a setup tailored for a Slack environment, aiming to offer an interactive, AI-driven chatbot experience. Note that to use this template, you need to be on n8n version 1.19.4 or later.

A robust n8n workflow designed to enhance Telegram bot functionality for user management and broadcasting. It facilitates automatic support ticket creation, efficient user data storage in Redis, and a sophisticated system for message forwarding and broadcasting. How It Works Telegram Bot Setup: Initiate the workflow with a Telegram bot configured for handling different chat types (private, supergroup, channel). User Data Management: Formats and updates user data, storing it in a Redis database for efficient retrieval and management. Support Ticket Creation: Automatically generates chat tickets for user messages and saves the corresponding topic IDs in Redis. Message Forwarding: Forwards new messages to the appropriate chat thread, or creates a new thread if none exists. Support Forum Management: Handles messages within a support forum, differentiating between various chat types and user statuses. Broadcasting System: Implements a broadcasting mechanism that sends channel posts to all previous bot users, with a system to filter out blocked users. Blocked User Management: Identifies and manages blocked users, preventing them from receiving broadcasted messages. Versatile Channel Handling: Ensures that messages from verified channels are properly managed and broadcasted to relevant users. Set Up Steps Estimated Time**: Around 30 minutes. Requirements**: A Telegram bot, a Redis database, and Telegram group/channel IDs are necessary. Configuration**: Input the Telegram bot token and relevant group/channel IDs. Configure message handling and user data processing according to your needs. Detailed Instructions**: Sticky notes within the workflow provide extensive setup information and guidance. Live Demo Workflow Bot: Telegram Bot Link (Click here) Support Group: Telegram Group Link (Click here) Broadcasting Channel: Telegram Channel Link (Click here) Keywords: n8n workflow, Telegram bot, chat ticket system, Redis database, message broadcasting, user data management, support forum automation

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

Who is this 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 workflow demonstrates how we can use Multimodal LLMs to parse and extract from PDF documents in n8n. In this particular scenario, we're passing a candidate's CV/resume to an AI which filters out unqualified applications. However, this sneaky candidate has added in hidden prompt to bypass our bot! Whatever will we do? No fret, using AI Vision is one approach to solve this problem... read on! How it works Our candidate's CV/Resume is a PDF downloaded via Google Drive for this demonstration. The PDF is then converted into an image PNG using a tool called Stirling PDF. Since the hidden prompt has a white font color, it is is invisible in the converted image. The image is then forwarded to a Basic LLM node to process using our multimodal model - in this example, we'll use Google's Gemini 1.5 Pro. In the Basic LLM node, we'll need to set a User Message with the type of Binary. This allows us to directly send the image file in our request. The LLM is now immune to the hidden prompt and its response is has expected. The example CV/Resume with hidden prompt can be found here: https://drive.google.com/file/d/1MORAdeev6cMcTJBV2EYALAwll8gCDRav/view?usp=sharing Requirements Google Gemini API Key. Alternatively, GPT4 will also work for this use-case. Stirling PDF or another service which can convert PDFs into images. Note for data privacy, this example uses a public API and it is recommended that you self-host and use a private instance of Stirling PDF instead. Customising the workflow Swap out the manual trigger for another trigger such as a webhook to integrate into your existing services. This example demonstrates a validation use-case ie. "does the candidate look qualified?". You can try additionally extracting data points instead such as years of experiences, previous companies etc.

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 recruitment agencies, HR professionals, and hiring managers looking to automate the initial screening of CVs. It is especially useful for organizations handling large volumes of applications and seeking to streamline their recruitment process. What problem does this workflow solve? Manually screening resumes is time-consuming and prone to human error. This workflow automates the process, providing consistent and objective analysis of CVs against job descriptions. It helps filter out unsuitable candidates early, reducing workload and improving the overall efficiency of the recruitment process. What this workflow does This workflow automates the resume screening process using OpenAI for analysis. It provides a matching score, a summary of candidate suitability, and key insights into why the candidate fits (or doesn’t fit) the job. Retrieve Resume: The workflow downloads CVs from a direct link (e.g., Supabase storage or Dropbox). Extract Data: Extracts text data from PDF or DOC files for analysis. Analyze with OpenAI: Sends the extracted data and job description to OpenAI to: Generate a matching score. Summarize candidate strengths and weaknesses. Provide actionable insights into their suitability for the job. Setup Preparation Create Accounts: N8N: For workflow automation. OpenAI: For AI-powered CV analysis. Get CV Link: Upload CV files to Supabase storage or Dropbox to generate a direct link for processing. Prepare Artifacts for OpenAI: Define Metrics: Identify the metrics you want from the analysis (e.g., matching percentage, strengths, weaknesses). Generate JSON Schema: Use OpenAI to structure responses, ensuring compatibility with your database. Write a Prompt: Provide OpenAI with a clear and detailed prompt to ensure accurate analysis. N8N Scenario Download File: Fetch the CV using its direct URL. Extract Data: Use N8N’s PDF or text extraction nodes to retrieve text from the CV. Send to OpenAI: URL: POST to OpenAI’s API for analysis. Parameters: Include the extracted CV data and job description. Use JSON Schema to structure the response. Summary This workflow provides a seamless, automated solution for CV screening, helping recruitment agencies and HR teams save time while maintaining consistency in candidate evaluation. It enables organizations to focus on the most suitable candidates, improving the overall hiring process.

This workflow checks a Google Calendar at 8am on the first of each month to get anything that has been marked as a Holiday or Illness. It then merges the count for each person and sends an email with the list. To use this workflow you will need to set the credentials to use for the Google Calendar node and Send Email node. You will also need to select the calendar ID and fill out the information in the send email node. This workflow searches for Events that contain "Holiday" or "Illness" in the summary. If you want to change this you can modify it in the Switch node.

his workflow automates time tracking using location-based triggers. How it works Trigger: It starts when you enter or exit a specified location, triggering a shortcut on your iPhone. Webhook: The shortcut sends a request to a webhook in n8n. Check-In/Check-Out: The webhook receives the request and records the time and whether it was a "Check-In" or "Check-Out" event. Google Sheets: This data is then logged into a Google Sheet, creating a record of your work hours. Set up steps Google Drive: Connect your Google Drive account. Google Sheets: Connect your Google Sheets account. Webhook: Set up a webhook node in n8n. iPhone Shortcuts: Create two shortcuts on your iPhone, one for "Check-In" and one for "Check-Out." Configure Shortcuts: Configure each shortcut to send a request to the webhook with the appropriate "Direction" header. It's easy to setup, around 5 minutes.

This n8n workflow demonstrates how to automate customer interactions and appointment management via WhatsApp Business bot. After submitting a Google Form, the user receives a notification via WhatsApp. These notifications are sent via a template message. In case user sends a message to the bot, the text and user data is stored in Google Sheets. To reply back to the user, fill in the ReplyText column and change the Status to 'Ready'. In a few seconds n8n will fetch the unsent replies and deliver them one by one via WhatsApp Business node. Customize this workflow to fit your specific needs, connect different online services and enhance your customer communication! 🎉 Setup Instructions To get this workflow up and running, you'll need to: 👇 Create a WhatsApp template message on the Meta Business portal. Obtain an Access Token and WhatsApp Business Account ID from the Meta Developers Portal. This is needed for the WhatsApp Business Node to send messages. Set up a WhatsApp Trigger node with App ID and App Secret from the Meta Developers Portal. Right after that copy the WhatsApp Trigger URL and add it as a Callback URL in the Meta Developers Portal. This trigger is needed to receive incoming messages and their status updates. Connect your Google Sheets account for data storage and management. Check out the documentation page. ⚠️ Important Notes WhatsApp allows automatic custom text messages only within 24 hours of the last user message. Outside with time frame only approved template messages can be sent. The workflow uses a Google Sheet to manage form submissions, incoming messages and prepare responses. You can replace these nodes and connect the WhatsApp bot with other systems.

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.

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.

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

Important Notes: Check Legal Regulations: This workflow involves scraping, so ensure you comply with the legal regulations in your country before getting started. Better safe than sorry! Workflow Description: 😮‍💨 Tired of struggling with XPath, CSS selectors, or DOM specificity when scraping ? This AI-powered solution is here to simplify your workflow! With a vision-based AI Agent, you can extract data effortlessly without worrying about how the DOM is structured. This workflow leverages a vision-based AI Agent, integrated with Google Sheets, ScrapingBee, and the Gemini-1.5-Pro model, to extract structured data from webpages. The AI Agent primarily uses screenshots for data extraction but switches to HTML scraping when necessary, ensuring high accuracy. Key Features: Google Sheets Integration**: Manage URLs to scrape and store structured results. ScrapingBee**: Capture full-page screenshots and retrieve HTML data for fallback extraction. AI-Powered Data Parsing**: Use Gemini-1.5-Pro for vision-based scraping and a Structured Output Parser to format extracted data into JSON. Token Efficiency**: HTML is converted to Markdown to optimize processing costs. This template is designed for e-commerce scraping but can be customized for various use cases.

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

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 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.

The workflow starts by listening for messages from Telegram users. The message is then processed, and based on its content, different actions are taken. If it's a regular chat message, the workflow generates a response using the OpenAI API and sends it back to the user. If it's a command to create an image, the workflow generates an image using the OpenAI API and sends the image to the user. If the command is unsupported, an error message is sent. Throughout the workflow, there are additional nodes for displaying notes and simulating typing actions.

Enrich your company lists with OpenAI GPT-3 ↓ You’ll get valuable information such as: Market (B2B or B2C) Industry Target Audience Value Proposition This will help you to: add more personalization to your outreach make informed decisions about which accounts to target I've made the process easy with an n8n workflow. Here is what it does: Retrieve website URLs from Google Sheets Extract the content for each website Analyze it with GPT-3 Update Google Sheets with GPT-3 data

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.

Temporary solution using the undocumented REST API for backups using Google drive. Please note that there are issues with this workflow. It does not support versioning, so please know that it will create multiple copies of the workflows so if you run this daily it will make the folder grow quickly. Once I figure out how to version in Gdrive I'll update it here.

A robust n8n workflow designed to enhance Telegram bot functionality for user management and broadcasting. It facilitates automatic support ticket creation, efficient user data storage in Redis, and a sophisticated system for message forwarding and broadcasting. How It Works Telegram Bot Setup: Initiate the workflow with a Telegram bot configured for handling different chat types (private, supergroup, channel). User Data Management: Formats and updates user data, storing it in a Redis database for efficient retrieval and management. Support Ticket Creation: Automatically generates chat tickets for user messages and saves the corresponding topic IDs in Redis. Message Forwarding: Forwards new messages to the appropriate chat thread, or creates a new thread if none exists. Support Forum Management: Handles messages within a support forum, differentiating between various chat types and user statuses. Broadcasting System: Implements a broadcasting mechanism that sends channel posts to all previous bot users, with a system to filter out blocked users. Blocked User Management: Identifies and manages blocked users, preventing them from receiving broadcasted messages. Versatile Channel Handling: Ensures that messages from verified channels are properly managed and broadcasted to relevant users. Set Up Steps Estimated Time**: Around 30 minutes. Requirements**: A Telegram bot, a Redis database, and Telegram group/channel IDs are necessary. Configuration**: Input the Telegram bot token and relevant group/channel IDs. Configure message handling and user data processing according to your needs. Detailed Instructions**: Sticky notes within the workflow provide extensive setup information and guidance. Live Demo Workflow Bot: Telegram Bot Link (Click here) Support Group: Telegram Group Link (Click here) Broadcasting Channel: Telegram Channel Link (Click here) Keywords: n8n workflow, Telegram bot, chat ticket system, Redis database, message broadcasting, user data management, support forum automation

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.

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 👇

Note: This workflow uses the internal API which is not official. This workflow might break in the future. The workflow executes every night at 23:59. You can configure a different time bin the Cron node. Configure the GitHub nodes with your username, repo name, and the file path. In the HTTP Request nodes (making a request to localhost:5678), create Basic Auth credentials with your n8n instance username and password.

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