Language models are limited by the information they have been exposed to at the time of training. This presents an information gap when a user queries the LLM. RAG offers a solution to this problem by augmenting the LLM with a retrieval mechanism to access data from an external database.
We will develop an intuition for RAG using a simple model, and review the process that includes indexing, retrieval, and generation. We will use open-source libraries in Python to build a simple RAG model.
Bring your laptops and follow along.
NOTE: This event will be at the University of St. Thomas St. Paul Campus in room OSS 313.
Presenter Bio
Sona Maniyan is a Data Scientist with over 8 years of experience building analytical and machine-learning models at scale. She is a Staff Data Scientist at Cohesity. She holds a master's degree in software engineering from the University of St. Thomas.
