Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Vector Databases for RAG: Indexing and Similarity Methods

AI Bites via YouTube

Overview

Learn about Vector Databases (Vector DBs) and their crucial role in Retrieval Augmented Generation (RAG) pipelines through this comprehensive video tutorial. Explore the fundamentals of Vector DBs, including their purpose in storing embeddings for efficient data retrieval, and dive deep into various indexing methods such as Flat Indexing, Local Sensitivity Hashing (LSH), Hierarchical Navigable Small World (HNSW), Inverted File Indexing (IFI), Product Quantization (PQ), Approximate Nearest Neighbour Oh Yeah (Annoy), and Random Projection (RP). Master the criteria for selecting appropriate indexing methods and understand the querying process in Vector DBs, building upon concepts from related tutorials on PDF parsing, chunking methods, and embedding in RAG systems.

Syllabus

- Intro
- Why Vector DBs
- Types of DBs
- How do Vector DBs work?
- Flat Indexing
- Local Sensitivity Hashing LSH
- Hierarchical Navigable Small World HNSW
- Inverted File Indexing IFI
- Product Quantization PQ
- Approximate Nearest Neighbour Oh Yeah Annoy
- Random Projection RP
- Which Indexing method to choose?
- Querying VectorDBs

Taught by

AI Bites

Reviews

Start your review of Vector Databases for RAG: Indexing and Similarity Methods

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.