How to build a retrieval-augmented generation (RAG) AI system in Java (Spring Boot + LangChain4j)

preview_player
Показать описание
Learn how to build an AI powered application that knows your business context and is able to interact with your Java code. Recorded at Vaadin Create 2023.

Speaker: Marcus Hellberg, VP of DevRel, Vaadin
Рекомендации по теме
Комментарии
Автор

Yo I have a question: You've specified some arbitrary embedding model to convert the text chunks into vectors to be stored into the database. Are these vectors also sent to GPT-4 as context? Doesn't GPT-4 only accept their proprietary embedding models such as ada-002 and their new v3 models?

mustiosrs
Автор

"and it all of a sudden knows everything about Vaadin, and can put me out of a job. So I don`t know why I created that" 🤣

MiguelAngel-ugbh