NOTE: Hands-On AI Software Training (3 1/2 hours) – See Prerequisites
Workshop will be held in AM and repeated in PM (Limit of 20 attendees each session)
Workshop Title: Building a GPU-Accelerated Retrieval Augmented Generation (RAG) Pipeline
Presenters: Kevin Lee, Deep Learning Institute Team, Nvidia and Suchismita Sahu, Senior Data Scientist, Generative AI, Nvidia
Abstract:
Large language models (LLMs) show promising results in understanding and generating text. One limitation of the LLMs is that they are prone to hallucinate — to generate false knowledge. One reason for that is because they are agnostic to up-to-date and domain-specific data. Retrieval augmented generation (RAG) is a proposed solution for that issue, helping practitioners use current domain-specific data to augment LLM capabilities. Learn to create a RAG pipeline on GPU for the Q&A task, going over these steps:
— Understand the main concepts of LLMs and the RAG
— Pre-process the documents in the given document store
— Set up a vector database for retrieving relevant context from an embedding language model
— Combine the retrieved context with query + prompt and feed to an LLM to generate a response
Hands-on: Yes
Takeaways:
You will complete the first hours of Nvidia’s hands-on course, and receive credentials to then complete it on your own, leading to a Certificate of Competence. This may open opportunities for the mid-career SW/CS engineer.
Attendees:
Mid-career software developers (see prerequisites) Class limited to 20.
Equipment and software installed:
Bring your own laptop (cannot be corporate locked-down). Workshop includes working with Nvidia courseware and a dedicated Azure-based development environment.
Prerequisites:
The target audience is expected to have intermediate-level understanding of ML/DL and NLP pipelines. Basic knowledge of LLMs, [TensorFlow/Pytorch] and Python programming is required.
Presenter Bio:
Kevin Lee, Deep Learning Institute Team, Nvidia
Kevin Lee is a senior technical content developer on the Deep Learning Institute Team at NVIDIA. Kevin’s work focuses on raising awareness and driving adoption for GPU-accelerated technologies by creating developer-focused, hands-on training with an emphasis on Data Science, Computer Vision, and Large Language Models. Prior to NVIDIA, Kevin led a risk analytics team at Morgan Stanley and taught Data Science and Machine Learning at the University of California, Berkeley.
Suchismita Sahu, Senior Data Scientist, Generative AI, Nvidia
Suchismita Sahu is a Senior Data Scientist at NVIDIA, where she works on cutting-edge Generative AI projects across diverse domains. With over 7 years of industry experience in Machine Learning, Deep Learning, and Conversational AI, she has a strong background in developing and deploying innovative AI solutions for real-world use cases. She enjoys mentoring and coaching the next generation of AI talent, as part of the Break Through Tech AI program, helping them gain the skills and confidence to pursue their AI career goals. She holds a Master’s degree in Electrical Engineering from USC, and multiple certifications in Deep Learning from Coursera and NVIDIA.