Chat with documents via RAG: Google Drive to GPT-5 with Supabase vector database
📄 n8n RAG Ingestion & Query Workflow
Overview
This workflow is your all-in-one pipeline to turn any document into a powerful searchable knowledge base using RAG (Retrieval-Augmented Generation).
From the moment a file lands in your Google Drive, it’s automatically processed, understood, and made ready for instant AI-powered answers.
If you’re looking to unlock hidden value in your files and get answers in seconds instead of hours, this workflow is the foundation you need.
What It Does for You
- 📥 Automatic Ingestion – New files in a designated Google Drive folder are instantly picked up.
- 🔍 OCR Extraction – Extracts all text, whether it’s plain or inside tables.
- 📚 Vector Database Storage – Keeps your documents in Supabase for lightning-fast semantic search.
- 🧩 Smart Chunking – Each page becomes a single chunk for better understanding.
- 💡 AI-Powered Answers – Ask questions in natural language and get precise, context-aware responses.
- 🧠 Persistent Memory – Remembers previous chats for more coherent conversations.
- ⚡ GPT-5 Intelligence – Uses OpenAI’s most advanced model for deep, accurate answers.
How It Works
- Detect → Watches your Google Drive folder for new files.
- Extract → Uses Mistral AI to read all text, including tables.
- Chunk → Splits content so one page = one chunk for better context.
- Embed → Generates vector embeddings with OpenAI for semantic search.
- Store → Inserts processed content into Supabase.
- Retrieve & Answer → When you ask, the system searches the database and passes the results to GPT-5.
- Remember → Stores conversation history in Postgres for continuity.
Why You Want This
- Stop wasting time digging through files.
- Get fast, AI-driven answers from your own documents.
- Keep your data organized and searchable at any scale.
- Designed for businesses, researchers, and teams who want instant access to the right information.
- You get the template + setup guide and description
Key Highlights
- End-to-End Automation – From upload to query, no manual steps needed.
- Flexible – Works with any document type.
- High Accuracy – Large chunk size preserves full page context.
- Scalable – Add as many files as you want without slowing down.
- Future-Ready – Built to grow with your needs.
🚀 Imagine having your own private ChatGPT trained on your files.
This workflow makes it happen. Upload, search, and get answers — all automatically.
n8n Chat with Documents via RAG (Google Drive to GPT-5 with Supabase Vector Database)
This n8n workflow demonstrates a powerful Retrieval-Augmented Generation (RAG) system, enabling users to chat with documents stored in Google Drive using an OpenAI (GPT-5) chat model, with Supabase serving as the vector database for efficient document retrieval. The workflow supports multiple communication channels for user interaction.
What it does
This workflow automates the following steps:
- Listens for User Input: The workflow can be triggered by incoming messages from various platforms:
- Telegram Trigger: Responds to messages received via Telegram.
- Slack Trigger: Reacts to messages posted in a configured Slack channel.
- WhatsApp Trigger: Processes messages from WhatsApp Business Cloud.
- Gmail Trigger: Initiates a chat based on new emails received.
- Chat Trigger: Acts as a generic chat input for testing or integration with custom chat interfaces.
- Loads Documents from Google Drive: It can be triggered by new or updated files in Google Drive.
- Google Drive Trigger: Detects changes in specified Google Drive folders/files.
- Google Drive Node: Manually fetches documents from Google Drive.
- Prepares Documents for AI:
- Default Data Loader: Processes the raw document content.
- Character Text Splitter: Breaks down documents into smaller, manageable chunks suitable for embedding and retrieval.
- Embeds and Stores Documents:
- Embeddings OpenAI: Converts the text chunks into numerical vector embeddings using OpenAI's embedding models.
- Supabase Vector Store: Stores these embeddings in a Supabase vector database for fast similarity searches.
- Processes User Queries with AI:
- AI Agent: Orchestrates the RAG process, combining the user's query with relevant information retrieved from the vector database.
- OpenAI Chat Model: Utilizes an OpenAI GPT-5 model to generate coherent and contextually relevant responses.
- Mistral AI (Optional/Alternative): Provides an alternative or additional language model for generating responses.
- Postgres Chat Memory: Maintains conversational history, allowing the AI to remember previous interactions within a chat session.
- Delivers AI Responses: The generated AI response is sent back to the user via the original communication channel:
- Telegram: Sends the AI's response back to the Telegram chat.
- Slack: Posts the AI's response to the Slack channel.
- WhatsApp Business Cloud: Sends the AI's response to the WhatsApp chat.
- Gmail: Replies to the original email with the AI's response.
- Data Transformation:
- Edit Fields (Set): Allows for modification or addition of data fields within the workflow.
- Split Out: Divides incoming items into multiple outputs, useful for processing lists of documents or messages.
- Sticky Note: Provides a way to add comments or notes within the workflow for documentation purposes.
Prerequisites/Requirements
To use this workflow, you will need:
- n8n Instance: A running n8n instance.
- OpenAI Account & API Key: For generating embeddings and chat responses (GPT-5).
- Supabase Account: To host your vector database. You'll need your Supabase URL and API Key.
- Google Drive Account: Where your documents are stored. Requires Google Drive credentials configured in n8n.
- Communication Platform Accounts:
- Telegram Bot Token: For Telegram integration.
- Slack Bot Token: For Slack integration.
- WhatsApp Business Cloud API Access: For WhatsApp integration.
- Gmail Account: For email-based interactions.
- Mistral AI API Key (Optional): If you choose to use Mistral AI for language model capabilities.
Setup/Usage
- Import the Workflow: Download the JSON provided and import it into your n8n instance.
- Configure Credentials:
- For each service (OpenAI, Supabase, Google Drive, Telegram, Slack, WhatsApp, Gmail, Mistral AI), you will need to set up the corresponding credentials within n8n. Refer to the n8n documentation for detailed instructions on configuring each credential type.
- Configure Trigger Nodes:
- Select your preferred trigger node(s) (e.g., "Telegram Trigger", "Slack Trigger", "Google Drive Trigger").
- Configure the specific settings for each trigger, such as the Telegram bot, Slack channel, or Google Drive folder to monitor.
- Configure AI Nodes:
- Embeddings OpenAI: Ensure your OpenAI credential is selected.
- Supabase Vector Store: Provide your Supabase URL, API Key, and specify the table name for your vector store.
- OpenAI Chat Model: Select your OpenAI credential.
- Mistral AI: If used, select your Mistral AI credential.
- Configure Output Nodes:
- For each output node (e.g., "Telegram", "Slack", "WhatsApp Business Cloud", "Gmail"), ensure the correct credentials are selected and the target chat/email recipient is configured.
- Activate the Workflow: Once all configurations are complete, activate the workflow.
This workflow provides a robust framework for building interactive AI assistants that can leverage your existing document knowledge base.
Related Templates
Automate Dutch Public Procurement Data Collection with TenderNed
TenderNed Public Procurement What This Workflow Does This workflow automates the collection of public procurement data from TenderNed (the official Dutch tender platform). It: Fetches the latest tender publications from the TenderNed API Retrieves detailed information in both XML and JSON formats for each tender Parses and extracts key information like organization names, titles, descriptions, and reference numbers Filters results based on your custom criteria Stores the data in a database for easy querying and analysis Setup Instructions This template comes with sticky notes providing step-by-step instructions in Dutch and various query options you can customize. Prerequisites TenderNed API Access - Register at TenderNed for API credentials Configuration Steps Set up TenderNed credentials: Add HTTP Basic Auth credentials with your TenderNed API username and password Apply these credentials to the three HTTP Request nodes: "Tenderned Publicaties" "Haal XML Details" "Haal JSON Details" Customize filters: Modify the "Filter op ..." node to match your specific requirements Examples: specific organizations, contract values, regions, etc. How It Works Step 1: Trigger The workflow can be triggered either manually for testing or automatically on a daily schedule. Step 2: Fetch Publications Makes an API call to TenderNed to retrieve a list of recent publications (up to 100 per request). Step 3: Process & Split Extracts the tender array from the response and splits it into individual items for processing. Step 4: Fetch Details For each tender, the workflow makes two parallel API calls: XML endpoint - Retrieves the complete tender documentation in XML format JSON endpoint - Fetches metadata including reference numbers and keywords Step 5: Parse & Merge Parses the XML data and merges it with the JSON metadata and batch information into a single data structure. Step 6: Extract Fields Maps the raw API data to clean, structured fields including: Publication ID and date Organization name Tender title and description Reference numbers (kenmerk, TED number) Step 7: Filter Applies your custom filter criteria to focus on relevant tenders only. Step 8: Store Inserts the processed data into your database for storage and future analysis. Customization Tips Modify API Parameters In the "Tenderned Publicaties" node, you can adjust: offset: Starting position for pagination size: Number of results per request (max 100) Add query parameters for date ranges, status filters, etc. Add More Fields Extend the "Splits Alle Velden" node to extract additional fields from the XML/JSON data, such as: Contract value estimates Deadline dates CPV codes (procurement classification) Contact information Integrate Notifications Add a Slack, Email, or Discord node after the filter to get notified about new matching tenders. Incremental Updates Modify the workflow to only fetch new tenders by: Storing the last execution timestamp Adding date filters to the API query Only processing publications newer than the last run Troubleshooting No data returned? Verify your TenderNed API credentials are correct Check that you have setup youre filter proper Need help setting this up or interested in a complete tender analysis solution? Get in touch 🔗 LinkedIn – Wessel Bulte
By Wessel Bulte🎓 How to transform unstructured email data into structured format with AI agent
This workflow automates the process of extracting structured, usable information from unstructured email messages across multiple platforms. It connects directly to Gmail, Outlook, and IMAP accounts, retrieves incoming emails, and sends their content to an AI-powered parsing agent built on OpenAI GPT models. The AI agent analyzes each email, identifies relevant details, and returns a clean JSON structure containing key fields: From – sender’s email address To – recipient’s email address Subject – email subject line Summary – short AI-generated summary of the email body The extracted information is then automatically inserted into an n8n Data Table, creating a structured database of email metadata and summaries ready for indexing, reporting, or integration with other tools. --- Key Benefits ✅ Full Automation: Eliminates manual reading and data entry from incoming emails. ✅ Multi-Source Integration: Handles data from different email providers seamlessly. ✅ AI-Driven Accuracy: Uses advanced language models to interpret complex or unformatted content. ✅ Structured Storage: Creates a standardized, query-ready dataset from previously unstructured text. ✅ Time Efficiency: Processes emails in real time, improving productivity and response speed. *✅ Scalability: Easily extendable to handle additional sources or extract more data fields. --- How it works This workflow automates the transformation of unstructured email data into a structured, queryable format. It operates through a series of connected steps: Email Triggering: The workflow is initiated by one of three different email triggers (Gmail, Microsoft Outlook, or a generic IMAP account), which constantly monitor for new incoming emails. AI-Powered Parsing & Structuring: When a new email is detected, its raw, unstructured content is passed to a central "Parsing Agent." This agent uses a specified OpenAI language model to intelligently analyze the email text. Data Extraction & Standardization: Following a predefined system prompt, the AI agent extracts key information from the email, such as the sender, recipient, subject, and a generated summary. It then forces the output into a strict JSON structure using a "Structured Output Parser" node, ensuring data consistency. Data Storage: Finally, the clean, structured data (the from, to, subject, and summarize fields) is inserted as a new row into a specified n8n Data Table, creating a searchable and reportable database of email information. --- Set up steps To implement this workflow, follow these configuration steps: Prepare the Data Table: Create a new Data Table within n8n. Define the columns with the following names and string type: From, To, Subject, and Summary. Configure Email Credentials: Set up the credential connections for the email services you wish to use (Gmail OAuth2, Microsoft Outlook OAuth2, and/or IMAP). Ensure the accounts have the necessary permissions to read emails. Configure AI Model Credentials: Set up the OpenAI API credential with a valid API key. The workflow is configured to use the model, but this can be changed in the respective nodes if needed. Connect the Nodes: The workflow canvas is already correctly wired. Visually confirm that the email triggers are connected to the "Parsing Agent," which is connected to the "Insert row" (Data Table) node. Also, ensure the "OpenAI Chat Model" and "Structured Output Parser" are connected to the "Parsing Agent" as its AI model and output parser, respectively. Activate the Workflow: Save the workflow and toggle the "Active" switch to ON. The triggers will begin polling for new emails according to their schedule (e.g., every minute), and the automation will start processing incoming messages. --- Need help customizing? Contact me for consulting and support or add me on Linkedin.
By DavideTax deadline management & compliance alerts with GPT-4, Google Sheets & Slack
AI-Driven Tax Compliance & Deadline Management System Description Automate tax deadline monitoring with AI-powered insights. This workflow checks your tax calendar daily at 8 AM, uses GPT-4 to analyze upcoming deadlines across multiple jurisdictions, detects overdue and critical items, and sends intelligent alerts via email and Slack only when immediate action is required. Perfect for finance teams and accounting firms who need proactive compliance management without manual tracking. 🏛️🤖📊 Good to Know AI-Powered: GPT-4 provides risk assessment and strategic recommendations Multi-Jurisdiction: Handles Federal, State, and Local tax requirements automatically Smart Alerts: Only notifies executives when deadlines are overdue or critical (≤3 days) Priority Classification: Categorizes deadlines as Overdue, Critical, High, or Medium priority Dual Notifications: Critical alerts to leadership + daily summaries to team channel Complete Audit Trail: Logs all checks and deadlines to Google Sheets for compliance records How It Works Daily Trigger - Runs at 8:00 AM every morning Fetch Data - Pulls tax calendar and company configuration from Google Sheets Analyze Deadlines - Calculates days remaining, filters by jurisdiction/entity type, categorizes by priority AI Analysis - GPT-4 provides strategic insights and risk assessment on upcoming deadlines Smart Routing - Only sends alerts if overdue or critical deadlines exist Critical Alerts - HTML email to executives + Slack alert for urgent items Team Updates - Slack summary to finance channel with all upcoming deadlines Logging - Records compliance check results to Google Sheets for audit trail Requirements Google Sheets Structure Sheet 1: TaxCalendar DeadlineID | DeadlineName | DeadlineDate | Jurisdiction | Category | AssignedTo | IsActive FED-Q1 | Form 1120 Q1 | 2025-04-15 | Federal | Income | John Doe | TRUE Sheet 2: CompanyConfig (single row) Jurisdictions | EntityType | FiscalYearEnd Federal, California | Corporation | 12-31 Sheet 3: ComplianceLog (auto-populated) Date | AlertLevel | TotalUpcoming | CriticalCount | OverdueCount 2025-01-15 | HIGH | 12 | 3 | 1 Credentials Needed Google Sheets - Service Account OAuth2 OpenAI - API Key (GPT-4 access required) SMTP - Email account for sending alerts Slack - Bot Token with chat:write permission Setup Steps Import workflow JSON into n8n Add all 4 credentials Replace these placeholders: YOURTAXCALENDAR_ID - Tax calendar sheet ID YOURCONFIGID - Company config sheet ID YOURLOGID - Compliance log sheet ID C12345678 - Slack channel ID tax@company.com - Sender email cfo@company.com - Recipient email Share all sheets with Google service account email Invite Slack bot to channels Test workflow manually Activate the trigger Customizing This Workflow Change Alert Thresholds: Edit "Analyze Deadlines" node: Critical: Change <= 3 to <= 5 for 5-day warning High: Change <= 7 to <= 14 for 2-week notice Medium: Change <= 30 to <= 60 for 2-month lookout Adjust Schedule: Edit "Daily Tax Check" trigger: Change hour/minute for different run time Add multiple trigger times for tax season (8 AM, 2 PM, 6 PM) Add More Recipients: Edit "Send Email" node: To: cfo@company.com, director@company.com CC: accounting@company.com BCC: archive@company.com Customize Email Design: Edit "Format Email" node to change colors, add logo, or modify layout Add SMS Alerts: Insert Twilio node after "Is Critical" for emergency notifications Integrate Task Management: Add HTTP Request node to create tasks in Asana/Jira for critical deadlines Troubleshooting | Issue | Solution | |-------|----------| | No deadlines found | Check date format (YYYY-MM-DD) and IsActive = TRUE | | AI analysis failed | Verify OpenAI API key and account credits | | Email not sending | Test SMTP credentials and check if critical condition met | | Slack not posting | Invite bot to channel and verify channel ID format | | Permission denied | Share Google Sheets with service account email | 📞 Professional Services Need help with implementation or customization? Our team offers: 🎯 Custom workflow development 🏢 Enterprise deployment support 🎓 Team training sessions 🔧 Ongoing maintenance 📊 Custom reporting & dashboards 🔗 Additional API integrations Discover more workflows – Get in touch with us
By Oneclick AI Squad