What this book covers

Chapter 1, Introduction to Vectors and Embeddings, covers the essentials of embeddings in machine learning.

Chapter 2, Getting Started with Vector Search in Elastic, explores the evolution of search in Elastic, from traditional keyword-based methods to advanced vector search.

Chapter 3, Model Management and Vector Considerations in Elastic, dives into managing embedding models in Elasticsearch, exploring Hugging Face’s platform, Elastic’s Eland library, and integration strategies.

Chapter 4, Performance Tuning—Working with Data, delves into optimizing vector search performance in Elasticsearch using ML model deployment tuning and node capacity estimation. This chapter will also cover load testing with Rally and troubleshooting kNN search response times.

Chapter 5, Image Search, explores the advancing field of image similarity search and its growing significance in discovery applications.

Chapter 6, Redacting Personal Identifiable Information Using Elasticsearch, covers how to build and tailor a PII Redaction Pipeline in Elasticsearch, crucial for data privacy and security.

Chapter 7, Next Generation of Observability Powered by Vectors, delves into integrating vectors with observability on the Elastic platform, focusing on log analytics, metric analytics, and application performance monitoring.

Chapter 8, The Power of Vectors and Embedding in Bolstering Cybersecurity, explores Elastic Learned Sparse EncodeR (ELSER) and its role in semantic search for cybersecurity. It explains ELSER’s capabilities in text analysis and phishing detection.

Chapter 9, Retrieval Augmented Generation with Elastic, dives into Retrieval Augmented Generation (RAG) in Elastic, blending lexical, vector, and contextual searches.

Chapter 10, Building an Elastic Plugin for ChatGPT, shows how to enhance ChatGPT’s context awareness with Elasticsearch and Embedchain, creating a Dynamic Contextual Layer (DCL) for up-to-date information retrieval.