This project automates the complete customer support process using n8n, Ollama, Supabase Vector Database, and Retrieval-Augmented Generation (RAG). When a customer submits a question through the website or application, the workflow is automatically triggered via a webhook. An AI classifier first determines whether the message is related to customer support or is an unrelated request. If the query is not support-related, the system immediately returns a predefined response. If it is a valid support request, the message is forwarded to an AI Agent for intelligent processing. The AI Agent is connected to a semantic search tool powered by a Supabase Vector Database. Instead of relying solely on the language model's internal knowledge, the agent searches the company's knowledge base for the most relevant document chunks before generating a response. PDF documents containing product information, shipping policies, return policies, warranty details, FAQs, and troubleshooting guides are automatically converted into embeddings and stored as vectors. During every customer interaction, the system retrieves only the most relevant information, ensuring that responses remain accurate, context-aware, and consistent with the latest company documentation while significantly reducing hallucinations. To simplify knowledge management, the project includes a dedicated RAG data upload workflow. Whenever administrators upload a new PDF document, the system automatically extracts the text, splits it into meaningful chunks, generates vector embeddings using Ollama, and stores them in the Supabase Vector Database. This allows the AI assistant to instantly access newly added information without requiring any model retraining. As a result, businesses can continuously update policies, product documentation, and support articles while keeping the AI assistant synchronized with the latest knowledge base.
AI Customer Support with RAG & Workflow AutomationRAG & Vector Search Automation
Built an AI-powered customer support system using n8n that automatically classifies customer queries, retrieves relevant information from a company knowledge base using Retrieval-Augmented Generation (RAG), and generates accurate AI responses through semantic search, significantly reducing manual support effort and AI hallucinations.
Key Features & System Capabilities
Visual Demonstration
Step 1: Knowledge Base Upload — The administrator uploads company PDF documents through the admin dashboard. Once uploaded, the document is processed automatically, allowing the AI assistant to answer customer queries using the latest company information.
Step 2: Document Processing & Vector Storage — After a document is uploaded, the system automatically processes its text, splits it into structured chunks, and stores it in the database. This enables fast and accurate search when the AI responds to customer queries.
Step 3: AI Query Processing & Response Generation — When a customer submits a query, the system classifies the request and passes valid queries to the AI Agent. The agent retrieves relevant information from the knowledge base and generates accurate, up-to-date responses.
Step 1: Knowledge Base Upload — The administrator uploads company PDF documents through the admin dashboard. Once uploaded, the document is processed automatically, allowing the AI assistant to answer customer queries using the latest company information.
Step 2: Document Processing & Vector Storage — After a document is uploaded, the system automatically processes its text, splits it into structured chunks, and stores it in the database. This enables fast and accurate search when the AI responds to customer queries.
Step 3: AI Query Processing & Response Generation — When a customer submits a query, the system classifies the request and passes valid queries to the AI Agent. The agent retrieves relevant information from the knowledge base and generates accurate, up-to-date responses.