

Navigating the Nuances of Retrieval Augmented Generation
Oct 26, 2023
Philipp Moritz and Goku Mohandas of Anyscale discuss retrieval augmented generation (RAG) systems, challenges in evaluation, labeling and classification strategies, optimizing model inference, online software stack, and hyperparameter search in evaluation runs.
Chapters
Transcript
Episode notes
1 2 3 4 5 6
Introduction
00:00 • 4min
Challenges in Evaluating Retrieval Augmented Generation
03:50 • 17min
Labeling and Classification Strategies
21:08 • 14min
Optimizing Model Inference for Faster and More Efficient Results
35:27 • 2min
Discussing the Online Software Stack, Evaluation, and Model Fine-Tuning in Open-Source Models
37:17 • 2min
Exploring Tuning and Hyperparameter Search in Evaluation Runs
38:47 • 4min