Overview
This course dives into the nuances of deploying and orchestrating multiple Large Language Models (LLM) in production using a RAG (Retrieval Augmented Generation) framework via Langchain.
Participants will learn about advanced design patterns, LLM architectures, and the broader LLM ecosystem. The course also delves into the risks, ethics, and pitfalls of LLM utilization. Through hands-on sessions, discussions, and comprehensive assessments, the course concludes with a collaborative project, offering insights into the Artificial Intelligence (AI) transformation.
This course targets professionals, business analysts, and forwardthinking executives keen on applying LLMs to specific business contexts, and seamlessly orchestrating multiple LLMs for AI in various business-specific applications. Ideal for those looking to stay at the forefront of AI-driven business solutions.
Course Description & Learning Outcomes
At the end of the course, participants will be able to:
Customise LLMs to cater to specific business goals and industrial contexts.
Understand production considerations for deploying LLMs-based services.
Utilise advance techniques in orchestrating and evaluating LLMs
Understand the capabilities, ethics, and governance aspects of using LLMs in various scenarios.
Schedule
End Date: 18 Mar 2025, Tuesday
Location: 11 Research Link, COM 3, 119391
Pricing
Skills Covered
PROFICIENCY LEVEL GUIDE
Beginner: Introduce the subject matter without the need to have any prerequisites.
Proficient: Requires learners to have prior knowledge of the subject.
Expert: Involves advanced and more complex understanding of the subject.
- Machine Learning (Proficiency level: Beginner)
