Let's explore how to interact with LLM (large language models) to leverage their superpower! In this workshop, we'll create an OpenAI-powered chatbot in React that can hold conversations using your own data! While building, you will learn about Prompt Engineering (an emerging discipline with its own methodologies, tools, and best practices), Chat Markup Language (ChatML), and multiple ways to let OpenAI use your own data - the mainstream option for using LLM in the real world!

Outline:

- Introduction
-- Setting up the goal
-- Pre-requisites and technical setup

- Generative AI introduction
-- Key terms, main models, and services
-- Completions API and Chat Completion API: when to use what
-- Prompt Engineering: the art of communication with LLM

- Connecting your app with API
-- Setting up and running the app
-- Calling Completion API and displaying result

- Building chat with out-of-the-box ChatGPT
-- Two ways to build chat-like experience: Chat Completions API and ChatML
-- Experimenting with metaprompt
-- Controlling request length to follow the token limit

- Grounding ChatGPT to use your data
-- Various ways to use your own data
-- Using prompt engineering to generate request to the database
-- Using prompt engineering to generate the answer

- Conclusion
-- Ways to continue learning
-- Useful resources