Build a healthcare conversation agent using medical research¶
Access this AI accelerator on GitHub
This accelerator shows how you can use Retrieval Augmented Generation to build a conversational agent for healthcare professionals. Healthcare professionals have to constantly stay informed of the latest research in not only their own specialization but also in complimentary fields. This means they have to constantly consume the latest research from trusted sources. Because new research papers are published at an astonishing rate, it is important to filter out irrelevant and untrusted research and focus on trusted research that is important to healthcare in this agent's knowledge base. As this agent's intended use is in healthcare, it is of paramount importance that the agent operates with in the confines of the knowledge base without hallucinations.
With DataRobot, this accelerator shows how to use predictive modeling to identify trusted research and then build a knowledge base for the conversational agent using DataRobot's generative AI offering.
This accelerator illustrates the following;
- Use predictive models to classify text files
- Create a vector store out of research paper abstracts
- Use Retrieval Augmented Generation with a generative AI model
- Deploy a Generative AI model to the DataRobot platform