Vector search for LLM's w/ Qdrant's David Myriel | GenAI Summit SF 2024

How do you give LLMs domain expertise? How do you reduce hallucinations?
A common pattern is Retrieval Augmentation Generation (RAG), and if you're going to do that, then you need a vector database to do it well and at scale.
I had an opportunity to talk to David Myriel of Qdrant about how he sees the use cases, considerations, and evaluation metrics developers are looking at when thinking about vector database options.
hashtag#genaisummit