Vector Databases and Beyond for RAG LLMs

Event: MEETUP | Date: Wednesday, November 29th 2023


Retrieval-augmented generation (RAG) for large language models (LLMs) aims to improve prediction quality by using an external datastore at inference time to build a richer prompt that includes some combination of context, history, and recent/relevant knowledge.

In this talk, we will introduce how two different datastores can be used for RAG - Vector Databases that retrieve documents related to the input prompt - and Feature Stores that can retrieve enterprise data through application-supplied information, such as a user-id or booking reference number.