Today every developer is using LLMs in different forms and shapes. Lots of products have introduced embedded AI capabilities, and in this workshop you’ll learn how to build your own AI application. No experience in building LLMs or machine learning is needed. Instead, we’ll use web technologies such as JavaScript, React and GraphQL which you already know and love.
This workshop has been presented at React Day Berlin 2023, check out the latest edition of this React Conference.
Participants will build a custom MyGPT application that can ask questions against OpenAI and other models from different providers. The application will include components for prompt engineering and data retrieval.
Participants need to clone the GitHub repo for the workshop, have a code editor (like VS Code), and an OpenAI API key. A free trial API key can be obtained from OpenAI's website.
The workshop is scheduled to last between two and a half to three hours, with potential breaks in between.
LangChain JS is primarily used to interface with language models and use them in your own applications. It is not recommended for building your own models or very complex AI backend services.
The workshop will include exercises on setting up the MyGPT application, integrating LangChain JS, prompt engineering, and data retrieval to enhance the AI model's responses.
Yes, participants can swap out OpenAI with other LLM providers, such as IBM Watson, Google Vertex, or open-source providers like Mistral, using LangChain JS.
Participants can send a private message to the instructor for assistance. If needed, the instructor can create a temporary API key for them, which will be deleted after the workshop.
Today's workshop focuses on AI for front-end developers, specifically on writing code using LangChain JS.
No, the workshop will not cover AI-prompting tools like GPT or GitHub Copilot. It will focus on writing code using LangChain JS.
LangChain JS is a JavaScript version of LangChain, which is a tool designed to interface with models and use them in your own applications. It is suitable for frontend or TypeScript developers and offers similar functionalities to the Python version.
Comments