This is where the earlier modules come together. A working AI product is more than a prompt and an API call: it needs a frontend people can use, a backend that holds your API keys and talks to the model, and the glue between them, including streaming the answer into the interface.
The lessons walk through building complete applications. You will see a chatbot built with Next.js and the OpenAI API, a version with a separate Python backend, and a chatbot that answers from a website’s own content using a vector store and caching. Follow along with one, then adapt it to your own idea.
Watch the lessons in order, then continue on to Evaluation, Safety & Cost.
A step-by-step build of a full AI-powered app, integrating the OpenAI API into a Next.js application.
A full-stack chatbot with a Next.js frontend, a FastAPI backend, and OpenAI as the model.
A chatbot that answers questions from your own website’s content, using Next.js 14, LangChain.js, the OpenAI API, a vector store, and Redis caching.
Creating a full-stack AI chatbot with Next.js 14 and GPT-4o through the API, with a polished component-library interface.