Check back for future offerings.
NYU Data Services (NYU Libraries and IT), the Graduate School of Arts & Science Master’s College, and the Arts & Sciences Office of Teaching Excellence and Innovation are excited to launch a new extension of the Foundations of Research Computing (FORC) Camp training opportunity for graduate students! Given the strong interest in data skills development on the part of our students and the success of the summer FORC Camp offerings, we will pilot a JTerm offering of two new tracks. Grounded in the principle that foundational data skills are essential for early career researchers, these two new tracks will explore the potential of generative AI as a research tool. We’re grateful to our colleagues in NYU’s Research and Instructional Technology team for their partnership on this offering.
During this one day in-person learning opportunity, taking place January 16, 2025, interested students can select one of two tracks.
All sessions take place from 10am-12pm and 1pm-3pm in the Elmer Holmes Bobst Library.
The day’s schedule will include four hours of interactive instruction. Participants who complete all hours of the FORC curriculum will receive a letter of completion for their portfolio detailing the skills covered in their track.
Send inquiries to asteaching@nyu.edu.
Generative AI offers an exciting opportunity to interact with large amounts of data and discover connections in ways that were not previously possible with traditional research methods. However, commercial Generative AI products offer a “black box” for users, who may not know what Large Language Model (LLM) is being used or how queries are being modulated, all factors that can affect the quality and usefulness of outputs. In this track, you will learn about differences in LLM offerings and their applications, standard methods for modulating outputs, and basic contours for narrowing and improving outputs using a retrieval-augmented generation (RAG) workflow. No coding skills are required.
Located in Bobst room 745
In this track, users will learn about Retrieval Augmented Generation (RAG) and how it enhances AI models by combining external data retrieval with large language models (LLMs). They will explore the steps to build a RAG pipeline, including embedding text into vector representations, retrieving relevant context from databases, and augmenting prompts to generate accurate answers. The tutorial provides practical insights into when to use RAG over fine-tuning models and how to integrate this approach in building dynamic, context-aware AI solutions.
For additional information, see Retrieval Augmented Generation (RAG) page (may require NYU login to access).
Prerequisites: basic understanding of python
Located in Bobst room 743