12 Learning semantic techniques and Atlas Vector Search
- Working with embeddings and vector databases
- Creating an Atlas Vector Search
- Exploring the
$vectorSearch aggregation pipeline stage
- Using Atlas Triggers to generate embeddings
Chapter 11 introduced Atlas Search, which is built with Apache Lucene. This powerful open source search engine enhances database functionality by providing full-text search capabilities integrated directly into MongoDB.
In this chapter, we explore Atlas Vector Search. This feature, also built on the foundation of Apache Lucene, extends MongoDB’s core server capabilities further by enabling vector-based search functionalities.
12.1 Starting with embeddings
12.1.1 Converting text to embeddings
12.1.2 Understanding vector databases
12.2 Using embeddings with Atlas Vector Search
12.2.1 Building an Atlas Vector Search index
12.2.2 Selecting a Vector Search source
12.2.3 Defining your Vector Search index
12.2.4 Creating an Atlas Vector Search index
12.3 Running Atlas Vector Search queries
12.3.1 Querying with embeddings
12.3.2 Using prefiltering with Atlas Vector Search
12.4 Executing vector search with programming languages
12.4.1 Using vector search with JavaScript
12.4.2 Using vector search and prefiltering with Python
12.4.3 Using vector search with prefilters in Ruby
12.5 Using Atlas Triggers for automated embeddings creation
12.6 Workload isolation with vector search dedicated nodes
12.7 Improving Atlas Vector Search performance
Summary