Build Industry-Specific LLMs Using Retrieval Augmented Generation

In the Microsoft Build session Vector Search Isn’t Enough, they lay out their product that combines less context-aware LLMs with vector search, to create a more engaging experience. The talk starts from the opposite direction of this piece — from the point of view of Elastic Search (or vector search) — and the idea that search by itself is limited, and adding the layer of LLMs can vastly improve the search experience. The basic idea is that adding relevant context to LLMs can vastly improve user experience especially in most commercial cases, where LLMs haven’t seen these sorts of data. Vector search helps in choosing what the relevant context is, when you have vast amounts of data, including 100s (or more) documents. <a href="https://towardsdatascience.com/build-industry-specific-llms-using-retrieval-augmented-generation-af9e98bb6f68">Click Here</a>