Unlocking Data with Generative AI and RAG

8

Similarity Searching with Vectors

This chapter is all about the R or retrieval part of retrieval-augmented generation (RAG). Specifically, we are going to talk about four areas related to similarity searches: indexing, distance metrics, similarity algorithms, and vector search services. With this in mind, in this chapter, we will cover the following:

• Distance metrics versus similarity algorithms versus vector search
• Vector space
• Code lab 8.1 – Semantic distance metrics
• Different search paradigms – sparse, dense, and hybrid
• Code lab 8.2 – Hybrid search with a custom function
• Code lab 8.3 – Hybrid search with LangChain’s EnsembleRetriever
• Semantic search algorithms such as k-NN and ANN
• Indexing techniques that enhance ANN search efficiency ...