Course Curriculum

    1. Introduction

    2. Learning Objectives

    1. What is a Vector Database?

    2. Vector Embeddings

    3. Vector Space

    4. Vector Database Fundamentals

    1. Vector Search

    2. Build the Vector Search Pipeline

    3. Vector Search

    4. Types of Vector Searches

    5. Vector Search

    1. ANN Algorithms

    2. Navigate the HNSW Graph

    3. Approximate Nearest Neighbors

    1. Overview of the RAG System

    2. Chunking

    3. Filtering with Metadata

    4. Retrieval: Hybrid Search and Query Re-Writing

    5. Hybrid Search

    6. Fine-Tuned Embedding Models

    7. Optimizing the RAG

    1. Scale, Reliability, and Cost

    2. Multi-Tenancy

    3. Vector Compression

    4. Vector Databases in Production

About this course

  • Free
  • 40 lessons
  • 2 hours of video content