Retrieval Augmented Generation (RAG) Explained: Embedding, Sentence BERT, Vector Database (HNSW)
Get your 5$ coupon for Gradient: https://gradient.1stcollab.com/umarjamilai
In this video we explore the entire Retrieval Augmented Generation pipeline. I will start by reviewing language models, their training and inference, and then explore the main ingredient of a RAG pipeline: embedding vectors. We will see what are embedding vectors, how they are computed, and how we can compute embedding vectors for sentences. We will also explore what is a vector database, while also exploring the popular HNSW (Hierarchical Navigable Small Worlds) algorithm used by vector databases to find embedding v…
Watch on YouTube ↗
(saves to browser)
Chapters (20)
Introduction
2:22
Language Models
4:33
Fine-Tuning
6:04
Prompt Engineering (Few-Shot)
7:24
Prompt Engineering (QA)
10:15
RAG pipeline (introduction)
13:38
Embedding Vectors
19:41
Sentence Embedding
23:17
Sentence BERT
28:10
RAG pipeline (review)
29:50
RAG with Gradient
31:38
Vector Database
33:11
K-NN (Naive)
35:16
Hierarchical Navigable Small Worlds (Introduction)
35:54
Six Degrees of Separation
39:35
Navigable Small Worlds
43:08
Skip-List
45:23
Hierarchical Navigable Small Worlds
47:27
RAG pipeline (review)
48:22
Closing
DeepCamp AI