Engineering Vector Search with Pgvector and Qdrant: Implementing Hybrid RAG for Semantic Search and Driven Applications
Format:
Paperback
En stock
0.49 kg
Sí
Nuevo
Amazon
USA
- Engineering Vector Search with Pgvector and Qdrant is a practical guide to designing and operating semantic retrieval systems using vector embeddings and similarity search. The book focuses on building dependable, scalable retrieval pipelines rather than experimental prototypes. Readers will explore how pgvector extends relational databases with vector capabilities, how Qdrant enables high-performance similarity search, and how both can be combined with structured filtering to support real-world application requirements. Topics include embedding storage, indexing strategies, query design, and system performance considerations. The book also examines architectural trade-offs, helping readers decide when to use database extensions, dedicated vector engines, or hybrid deployments. Practical examples demonstrate how these systems support modern AI workflows such as contextual search, document retrieval, and retrieval-augmented generation. This guide is written for engineers who want clarity, reliability, and production readiness in vector search systems. Best suited for:Backend and platform engineersAI and machine learning infrastructure teamsDatabase and data platform professionalsDevelopers building intelligent search features
IMPORT EASILY
By purchasing this product you can deduct VAT with your RUT number