Session: Understanding Vector Databases
We went from low background noise to loud assertion in regards to LLM and Vector Databases, in a matter of weeks. And while developers are getting better at understanding how to use LLM, most of us still don’t grasp how it’s made and how it can be used in real life use cases.
Together we will look at what makes LLM ticks, how they are built and trained, what exactly are those Vectors we keep hearing about, and why Vector Databases are such a good addition to LLMs. We will illustrate this with a Retrieval Augmented Generation(RAG) demo built with Couchbase, Streamlit, Langchain, and OpenAI.
