Project

Hypermart

1 completion
~ 15 hours
New

Learn to build an AI assistant with memory using Spring AI, semantic search with embeddings and a vector store, tools that change data under server-enforced rules and confirmations, and widgets rendered in Compose Multiplatform clients. By the end, you'll have an assistant that understands what users mean rather than just what they type, safely takes actions on their behalf, and responds with interactive cards and summaries in both the Android and desktop apps.

Provided by

JetBrains Academy JetBrains Academy

About

Online shops are much easier to use when you can simply ask for what you need. In this project, you'll add an AI shopping assistant to an existing grocery shop and its Android and desktop apps. Your assistant will chat with users, find products by meaning rather than exact words, add and remove items from their cart with confirmation where needed, and show its answers as product cards and cart summaries, just like a real shopping assistant.

Training project icon

Training project

This project allows you to practice and strengthen your coding skills, helping you get ready for more advanced tasks ahead.

What you'll learn

Once you choose a project, we'll provide you with a study plan that includes all the necessary topics from your course to get it built. Here’s what awaits you:
Give the assistant tools to search the catalog by meaning using local embeddings stored in a Qdrant vector store, and to look up individual products, so it can answer using real data while respecting allergies, diets, and budgets.
Add cart tools that the server validates like any other request, with confirmation required before removing or clearing items, and keep the apps' carts in sync with every change the assistant makes.
Turn the assistant's replies into widgets built by tools (product cards, cart summaries, and confirmation buttons) and display them in the Android and desktop chat.