In my talk, I'll dive into the world of semantic search using vector embeddings from modern LLMs. I'll lightly cover the three primary classes of transformer architectures and their role in Retrieval Augmented Generation (RAG). Then I'll give a quick demo showcasing how to utilize the open-source Milvus vector database to store, index, and search these embeddings as part of a live product demonstration. The product is live at https://osschat.io/.