Spring Boot AI RAG ( Retrieval Augmented Generation) Tutorial

preview_player
Показать описание
Spring Boot AI RAG Tutorial

In this video you will learn how to implement Retrieval Augmented Generation techniques in your Spring Boot Applications.

You will learn how to implement a Spring Boot Reference Documentation Assistant with the help of Spring AI, Ollama with Mistal and PG Vector Database.

Рекомендации по теме
Комментарии
Автор

Wow, thank you for this insightful content, keep doing it.

ravi
Автор

You have to add the dependency in order to be able to use the QuestionAnswerAdvisors on the controlller.

SenseYuuna
Автор

can i use local postgres if i dont want use docker, provided the jdb cconnection for postgres and postgres service is running?

bittu
Автор

Thank you for your guid! Do you know how to ask ollama to use my GPU (nvidia)? Because now it use only CPU :(

Likrant
Автор

Data is not being stored in vector_store table! I am able to insert data in this table manually.

Does this take time, and how much does it take time? I have checked multiple times after server start between every 2 minutes for 10 minutes.

and the log.info("Completed Ingesting PDF file");


never gets printed!

I am able to access the ollama model through postman, it works fine, it takes time around 50-120 seconds.

rahulgupta
Автор

By default embed POST call to ollama is happening as a blocking IO operation. Is there any way to override this when building in a reactive context?

firozgg
join shbcf.ru