Boosting LLMs Performance with Retrieval-Augmented Generation
Offered By: Data Science Dojo via YouTube
Course Description
Overview
Learn about Retrieval Augmented Generation (RAG), a powerful technique for enhancing the performance of large language models, in this 48-minute video from Data Science Dojo. Discover how RAG overcomes limitations of foundation models by incorporating external data from various sources into prompts. Explore the process of converting data into numerical representations using embedding language models and appending relevant context to user prompts. Understand the benefits of RAG, including improved model performance, personalization for specialized domains, and the ability to keep information current through asynchronous updates to knowledge libraries. Gain insights into key takeaways such as RAG's effectiveness in domain-specific tasks and its versatility in utilizing different data sources like documents, databases, and APIs.
Syllabus
Boosting LLMs Performance with Retrieval-Augmented Generation (RAG)
Taught by
Data Science Dojo
Related Courses
Data AnalysisJohns Hopkins University via Coursera Computing for Data Analysis
Johns Hopkins University via Coursera Scientific Computing
University of Washington via Coursera Introduction to Data Science
University of Washington via Coursera Web Intelligence and Big Data
Indian Institute of Technology Delhi via Coursera