Intro to RAG (Retrieval Augmented Generation) - Augment AI models with external memory

preview_player
Показать описание
Would you like to make your LLMs better without going through the hastle of training or fine-tuning? Retrieval Augmented Generation(RAG) could be the answer.

In this video, we give a quick but comprehensive introduction to RAG.

⌚️ ⌚️ ⌚️ TIMESTAMPS ⌚️ ⌚️ ⌚️
0:00 - Intro
1:28 - What is RAG?
2:27 - Advantages of RAG
2:55 - RAG Framework
3:16 - Indexing
3:34 - Chunking
3:55 - Vector Database
5:10 - Retrieval
6:38 - An Example
9:05 - Extro

📚 📚 📚 MY KEY LINKS 📚 📚 📚

#machinelearning #deeplearning #aibites
Рекомендации по теме
Комментарии
Автор

The Augmentation is actually related to generation part, not augmented retrieval. Otherwise it would be called "Augmented Retrieval Generation" . I checked the original paper from Meta and they also say "Our work aims to expand the space of possible tasks with a single, unified
architecture, by learning a retrieval module to augment pre-trained, generative language models".

Though I agree the prompt is also augmented with the retrieved information to get an Augmented response

explorer
Автор

Is it a form of continual/lifelong learning

InquilineKea
Автор

typo in the thumbnail and description: retrieval

youtubercocuq