NVIDIA Deep Learning Institute Workshop: Building RAG Agents with LLMs
Muzeum Sztuki i Techniki Japońskiej Manggha
Overview
Agents powered by large language models (LLMs) are quickly gaining popularity as people are finding new capabilities and opportunities to greatly improve their productivity. An especially powerful recent development has been the popularization of retrieval-based LLM systems that can hold informed conversations by using tools, looking at documents, and planning their approaches. These systems are fun to experiment with and offer unprecedented opportunities to make life easier, but they also require many queries to large deep learning models and need to be implemented efficiently. This course will observe how you can deploy an agent system in practice and scale up your system to meet the demands of users and customers. Along the way, you’ll learn advanced LLM orchestration techniques for internal reasoning, dialog management, tooling, and retrieval.
By the end of this workshop, participants will have a solid understanding of RAG agents and the tools necessary to develop their own LLM applications, and have the opportunity to earn a certificate to demonstrate subject matter competency and support professional career growth.
Outline
- Introduction to the workshop and setting up the environment
- Exploration of LLM inference interfaces and microservices
- Designing LLM pipelines using LangChain, Gradio, and LangServe
- Managing dialog states and integrating knowledge extraction
- Strategies for working with long-form documents
- Utilizing embeddings for semantic similarity and guardrailing
- Implementing vector stores for efficient document retrieval
- Evaluation, assessment, and certification
Prerequisites:
- Introductory deep learning, with comfort with PyTorch and transfer learning preferred.
- Intermediate Python experience, including object-oriented programming and libraries.
Participants should use their own laptops. Course access happens through a web browser and there is no need to install any software locally.
Language: English
Instructor: Szymon Mazurek, Cyfronet
Please note this is an in-person-only event. Register only if you can attend in Krakow. Please await confirmation of your registration.
The event is free of charge.
