37% Better Output with 15 Lines of Code - Llama 3 Improved RAG
Offered By: All About AI via YouTube
Course Description
Overview
Discover how to enhance RAG (Retrieval-Augmented Generation) performance by 37% with just 15 lines of code in this informative video tutorial. Explore the implementation of improved RAG techniques for Llama 3 8B on Ollama and Llama 3 70B on Groq. Learn about a common problem in local RAG systems and its solution, understand the mechanics behind the improvement, and see a comparison between different model sizes. Gain insights into practical AI engineering techniques and how to boost the output quality of language models significantly with minimal code changes.
Syllabus
Llama 3 Improved RAG Intro
Problem / Soulution
Brilliant.org
How this works
Llama 3 70B Groq
Conclusion
Taught by
All About AI
Related Courses
Pinecone Vercel Starter Template and RAG - Live Code Review Part 2Pinecone via YouTube Will LLMs Kill Search? The Future of Information Retrieval
Aleksa Gordić - The AI Epiphany via YouTube RAG But Better: Rerankers with Cohere AI - Improving Retrieval Pipelines
James Briggs via YouTube Advanced RAG - Contextual Compressors and Filters - Lecture 4
Sam Witteveen via YouTube LangChain Multi-Query Retriever for RAG - Advanced Technique for Broader Vector Space Search
James Briggs via YouTube