Thisaccelerator is aimed at showing how we can useRetrieval Augmented Generationto build a conversational agent for Healthcare professionals. Healthcare professionals have to constantly keep abreast the latest research in not only their own specialization but also in complimentary fields as well. This means they have to constantly consume the latest research from trusted sources. While research papers are published at an alarming rate, it becomes necessary to filter out research which is robust and only trusted research should be used as the knowledge base for the Agent. As this agent's intended use is in healthcare, it is paramount that the agent operates with in the confines of the knowledge base without hallucinations.
With DataRobot, we will show how to use Predictive Modeling to identify trusted research and then build a knowledge base for the conversational agent using DataRobot'sGenerative AI offering.
What you will learn
In this notebook we will be illustrating the following;
use predictive models to classify text files
create a vector store out of research paper abstracts
use Retrieval Augmented Generation with Generative AI model
deploy said Generative AI model to the DataRobot platform