GenAI User Documentation
Rutgers
About the Platform
This innovative AI platform is a result of a partnership between Rutgers Business School and Google, allowing Business School faculty, staff, and students to access large language models (LLM's) vendors such as Google, Anthropic, Meta, and many more through a single user interface. The platform brings the power of generative AI to the classroom, allowing users to reference external sites & data sets to provide these modes with contextual information to ground the query results.
Any data uploaded to the platform will not be used to train the models; therefore, university data will be protected.
Accessing the Platform
Rutgers Business School faculty, staff, and students can access the GenAI platform through the URL below.
URL: https://ai.business.rutgers.edu
Available Models:
Google's Gemini 1.5 Flash
Google's Gemini 1.5 Pro
Anthropic's Claude Sonnet 3.5 v2
Meta's Llama 3.2
How current is the data in the responses?
First, like most large language models, these models are not connected to the Internet. Therefore, the models of responses will be based on the most recent data set that has been added to the model. Each vendor has a different timetable for when they update their models, and so, in addition to the way the models are structured, this will further contribute to the difference in their responses.
The Basics: New Chat vs. Query Engine
A chat is a simple query that allows you to use any of the available models to answer a query. Using the New Chat interface, you also have the ability to reference a single external document or URL to ground the response to your query.
The main difference between a new chat and the query engine is that the query engine allows you to reference multiple data sources as part of a query. This can be done from a location that contains multiple documents or a website URL that can be indexed to provide the model with information to ground your query. Before you can use a query engine, it must first be created, and then shared with your intended audience. Keep in mind, however, that once a query engine is made, the data contained within the engine will only be current as of that date and time in which the data was uploaded and indexed.