Vectors in Java Code, Databases, and LLMs (#56)

Foojay Podcast published in July 2024  
All info, show notes, and links: https://foojay.io/today/category/podc...

In this Foojay podcast, we enter the world of mathematics by discussing Vectors and how they are crucial for AI and machine learning. As ChatGPT explains: "A Vector is a mathematical structure that holds numerical values. Vectors are fundamental to the field of Artificial Intelligence, as they allow mathematical operations to be performed efficiently and form the basis of many machine learning algorithms." OK, but how are these vectors crucial for the whole Artificial Intelligence evolution?

This is the last podcast of season 3, we're taking a summer break and will be back in September with the release of Java 23 and many more OpenJDK-related topics!

Guests
  Jonathan Ellis
     LinkedIn:  
     https://x.com/spyced  
  Alexander Chatzizacharias
     LinkedIn: alexander-chatzizacharias  
     https://x.com/alex90_ch  

Content

00:00 Introduction of the topic and guests
01:57 What is a Vector?
  https://github.com/openai/tiktoken
  https://arxiv.org/abs/1301.3781
  https://towardsdatascience.com/word2v...
  https://github.com/jbellis/jvector
07:14 Vectors explained as a game
  A fun and absurd introduction to Vector Databases: A fun and absurd introduction to Vect...
09:44 Understanding tokenizers
10:40 Do we need dedicated Vector databases?
13:39 Vectors, LLMs and hallucinations
  Crafting your own RAG system: Leveraging 30+ LLMs for enhanced performance by Stephan Janssen: Crafting your own RAG system: Leverag...
20:40 How LLM and chat interfaces are used in companies
  https://www.bbc.com/travel/article/20...
23:45 Indexing all of Wikipedia
  https://foojay.io/today/indexing-all-...
  Demo application: https://jvectordemo.com:8443/
  https://openjdk.org/projects/panama/
27:23 Evolutions in Java for vectors, LLMs, and AI
  Vector API (Eighth Incubator): https://openjdk.org/jeps/469
  Foreign Function & Memory API: https://openjdk.org/jeps/454
32:44 Is the GPU needed for vector use cases?
35:04 Can we already use the incubator Vector API in production?
38:27 Some predictions...
  Colbert project: https://github.com/stanford-futuredat...
  https://thenewstack.io/overcoming-the...
44:19 Make your vectors smaller to make them more efficient and less expensive
  https://www.sciencedirect.com/topics/...
  https://huggingface.co/blog/embedding...
  https://foojay.io/today/visualizing-b...
  Asteroids 3D in JavaFX made from AI Deep Fake Audio data: Asteroids 3D in JavaFX made from AI D...
49:19 Outro