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

Foojay.io, the Friends Of OpenJDK! - A podcast by Foojay.io

Categories:

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 much more OpenJDK-related topics!GuestsJonathan Ellishttps://www.linkedin.com/in/jbellis/https://x.com/spyced Alexander Chatzizachariashttps://www.linkedin.com/in/alexander-chatzizacharias/https://x.com/alex90_ch   Content00:00 Introduction of the topic and guests01:57 What is a Vector?   https://github.com/openai/tiktoken    https://arxiv.org/abs/1301.3781    https://towardsdatascience.com/word2vec-research-paper-explained-205cb7eecc30    https://github.com/jbellis/jvector  07:14 Vectors explained as a game   A fun and absurd introduction to Vector Databases: https://www.youtube.com/watch?v=mQGf9hWTqSw 09:44 Understanding tokenizers10:40 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: https://www.youtube.com/watch?v=9PX5l4ETn0g 20:40 How LLM and chat interfaces are used in companies   https://www.bbc.com/travel/article/20240222-air-canada-chatbot-misinformation-what-travellers-should-know 23:45 Indexing all of Wikipedia   https://foojay.io/today/indexing-all-of-wikipedia-on-a-laptop/    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-futuredata/ColBERT    https://thenewstack.io/overcoming-the-limits-of-rag-with-colbert/ 44:19 Make your vectors smaller to make them more efficient and less expensive   https://www.sciencedirect.com/topics/engineering/vector-quantization    https://huggingface.co/blog/embedding-quantization    https://foojay.io/today/visualizing-brain-computer-interface-data-using-javafx/    Asteroids 3D in JavaFX made from AI Deep Fake Audio data: https://www.youtube.com/watch?v=vFThM9BoTLg 49:19 Outro