Welcome to “AI-Powered E-Commerce App with .NET 9, Angular 20 & RAG”Have you ever imagined transforming a standard e-commerce store into an intelligent, AI-enabled platform that understands your users’ intent? In this course, you’ll learn to build a modern, semantic search and chatbot-powered online store that’s ready for Retrieval-Augmented Generation (RAG) — using .NET 9, Angular 20, Azure OpenAI, and PostgreSQL (pgvector). In this hands-on course, you’ll go far beyond theory. You’ll build, run, and integrate AI capabilities step by step — from foundational architecture to advanced generative intelligence — all within a clean, scalable, production-ready system.
Course Phases
Phase 1 – Building the AI-Enabled Foundation (Completed)
In this phase, you’ll develop a fully functional, AI-ready e-commerce system powered by .NET 9 and Angular 20. This is not a toy project — you’ll build real, production-grade components and integrate intelligent features end to end.
You will:
- Design a modular backend using Clean Architecture principles and the repository pattern.
- Implement semantic search by generating and storing embeddings using Azure OpenAI or Ollama, backed by PostgreSQL + pgvector.
- Create an AI chatbot assistant capable of natural language understanding and contextual product recommendations.
- Integrate multiple search modes — Catalog, Semantic, and Hybrid — that deliver smart, intent-based results.
- Develop a dynamic Angular 20 frontend using standalone components and Signals API for responsive data binding.
- Add a complete basket and checkout flow with persistent data management.
- Configure Ocelot API Gateway for service routing and Docker Compose for containerized deployment.
By the end of Phase 1, you will have a fully operational AI-driven store capable of handling real-time chat queries, intelligent product discovery, and hybrid semantic search — ready for the next phase of true RAG integration.
Phase 2 – Advancing to RAG-Powered Intelligence (Coming Soon)
In Phase 2, you’ll take your AI assistant to the next level by introducing Retrieval-Augmented Generation (RAG), Voice Assistant Integration, and Web Search Augmentation.
You will:
- Implement a RAG pipeline that combines vector search, document retrieval, and generative AI for context-aware answers.
- Add voice input and output, enabling users to interact naturally through speech.
- Extend the chatbot with web search fallback — if a product isn’t in the store, the assistant will fetch live recommendations from the internet.
- Integrate context memory, allowing the assistant to maintain awareness across multiple turns in the conversation.
- Add analytics and telemetry dashboards to monitor user queries, AI accuracy, and engagement trends.
By the end of Phase 2, your application will evolve into a fully RAG-powered conversational shopping assistant that can reason, retrieve, and respond like a true AI companion.
