HumationHuman + Automation
Back to Catalog

WhatsApp RAG chatbot with Supabase, Gemini 2.5 Flash, and OpenAI embeddings

Manav DesaiManav Desai
6486 views
2/3/2026
HTTPWebhookJSONDebuggerEcho
Official Page

WhatsApp RAG Chatbot with Supabase, Gemini 2.5 Flash, and OpenAI Embeddings

This n8n template demonstrates how to build a WhatsApp-based AI chatbot that answers user questions using document retrieval (RAG) powered by Supabase for storage, OpenAI embeddings for semantic search, and Gemini 2.5 Flash LLM for generating high-quality responses.

Use cases are many: Turn your WhatsApp into a knowledge assistant for FAQs, customer support, or internal company documents — all without coding.

Good to know

  • The workflow uses OpenAI embeddings for both document embeddings and query embeddings, ensuring accurate semantic search.
  • Gemini 2.5 Flash LLM is used to generate user-friendly answers from the retrieved context.
  • Messages are processed in real-time and sent back directly to WhatsApp.
  • Workflow is modular — you can split document ingestion and query handling for large-scale setups.
  • Supabase and WhatsApp API credentials must be configured before running.

How it works

  1. Trigger: A new WhatsApp message triggers the workflow via webhook.
  2. Message Check: Determines if the message is a query or a document upload.
  3. Document Handling:
    • Fetch file URL from WhatsApp.
    • Convert binary to text.
    • Generate embeddings with OpenAI and store them in Supabase.
  4. Query Handling:
    • Generate query embeddings with OpenAI.
    • Retrieve relevant context from Supabase.
    • Pass context to Gemini 2.5 Flash LLM to compose a response.
  5. Response: Send the answer back to the user on WhatsApp.

Optional: Add Gmail node to forward chat logs or daily summaries.

How to use

  • Configure WhatsApp Business API webhook for incoming messages.
  • Add your Supabase and OpenAI credentials in n8n’s credentials manager.
  • Upload documents via WhatsApp to populate the Supabase vector store.
  • Ask queries — the bot retrieves context and answers using Gemini 2.5 Flash.

Requirements

  • WhatsApp Business API (or Twilio WhatsApp Sandbox)
  • Supabase account (vector storage for embeddings)
  • OpenAI API key (for generating embeddings)
  • Gemini API access (for LLM responses)

Customising this workflow

  • Swap WhatsApp with Telegram, Slack, or email for different chat channels.
  • Extend ingestion to other sources like Google Drive or Notion.
  • Adjust the number of retrieved documents or prompt style in Gemini for tone control.
  • Add a Gmail output node to send logs or alerts automatically.

n8n WhatsApp RAG Chatbot with Supabase and Gemini-25-Flash

This n8n workflow creates a powerful Retrieval Augmented Generation (RAG) chatbot accessible via WhatsApp. It leverages Google Gemini-25-Flash for chat generation and OpenAI Embeddings with Supabase as a vector store for retrieving relevant context.

Description

This workflow simplifies the creation of an intelligent WhatsApp chatbot that can answer user queries by retrieving information from a knowledge base stored in Supabase. It uses RAG to enhance the chatbot's responses, making them more accurate and contextually relevant.

What it does

  1. Listens for WhatsApp messages: The workflow is triggered whenever a new message is received on a configured WhatsApp Business Cloud account.
  2. Initializes an AI Agent: It sets up an AI Agent with a Google Gemini Chat Model (specifically Gemini-25-Flash) and configures it to use a Supabase Vector Store for context retrieval.
  3. Embeds user queries: User messages are converted into vector embeddings using OpenAI Embeddings.
  4. Retrieves relevant documents: The Supabase Vector Store is queried using the user's message embeddings to find the most relevant documents from the knowledge base.
  5. Generates a response: The AI Agent uses the retrieved documents as context to generate an informed and accurate response to the user's query.
  6. Sends WhatsApp reply: The generated response is sent back to the user via WhatsApp.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • WhatsApp Business Cloud Account: Configured with n8n credentials.
  • Google Gemini API Key: For the Google Gemini Chat Model.
  • OpenAI API Key: For the OpenAI Embeddings.
  • Supabase Project: With a configured vector store (e.g., pg_vector extension enabled and a table for your knowledge base).
    • Supabase URL and Service Role Key: To connect n8n to your Supabase project.

Setup/Usage

  1. Import the workflow: Download the JSON provided and import it into your n8n instance.
  2. Configure Credentials:
    • WhatsApp Business Cloud: Set up your WhatsApp Business Cloud credential.
    • Google Gemini: Create a new credential for Google Gemini and provide your API Key.
    • OpenAI: Create a new credential for OpenAI and provide your API Key.
    • Supabase: Create a new credential for Supabase, providing your Supabase URL and Service Role Key.
  3. Configure the AI Agent node (ID: 1119):
    • Ensure the "Chat Model" is set to your Google Gemini credential.
    • Ensure the "Embeddings" is set to your OpenAI credential.
    • Ensure the "Vector Store" is set to your Supabase credential and configured with the correct table name and embedding column.
  4. Activate the workflow: Once all credentials and configurations are set, activate the workflow.

Your WhatsApp RAG Chatbot should now be live and ready to answer queries!

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

Wessel BulteBy Wessel Bulte
247

🎓 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.

DavideBy Davide
1616

Tax 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

Oneclick AI SquadBy Oneclick AI Squad
93