Understanding Generative AI: RAG, Semantic Search, Embeddings, and Vectors

Explore the key concepts behind Generative AI's data processing in this 29-minute video tutorial. Dive into Retrieval Augmented Generation (RAG), semantic indexing, semantic search, vectors, and embeddings. Learn how Large Language Models (LLMs) work with orchestrators to process information. Understand embedding models, vector creation, and the importance of semantic search in AI applications. Gain insights into two-dimensional representations and nearest neighbor algorithms. Discover why these technologies are crucial for enhancing AI capabilities and improving information retrieval.

- Introduction
- My typical day and need for information
- RAG
- LLM refresher
- Orchestrators and information to LLMs
- Semantic index, search, vector, embeddings?
- Embedding models and creating vector
- 2 dimensions
- Semantic search and nearest neighbor
- Why embeddings and semantic search are so important
- Summary and close