Garantía de entrega
SKU/Artículo: AMZ-B0FPLWN7HT
PostgreSQL as a Vector Database: Advanced pgvector for AI, RAG, and Multimodal LLMs
Format:
Paperback
Detalles del producto
Disponibilidad:
En stock
En stock
Peso con empaque:
0.81 kg
0.81 kg
Devolución:
Sí
Sí
Condición
Nuevo
Nuevo
Producto de:
Amazon
Amazon
Viaja desde
USA
USA
Sobre este producto
- PostgreSQL is a battle-tested relational database that powers countless production systems. With the pgvector extension, it also becomes a high-performance vector database capable of approximate nearest-neighbor (ANN) search over embeddings produced by modern AI models. This enables semantic search, Retrieval-Augmented Generation (RAG), and multimodal workflows (text, image, audio, video) to run alongside your transactional and analytical data—benefiting from SQL, ACID guarantees, row-level security, backups, and the rich Postgres ecosystem. Quick summary PostgreSQL as a Vector Database: Advanced pgvector for AI, RAG, and Multimodal LLMs is a practical guide to designing, building, and operating AI search and RAG systems directly on PostgreSQL. You’ll learn how to ingest and version embeddings, choose and tune indexes (HNSW, IVFFlat, brute-force), blend semantic and lexical ranking, enforce governance, and scale to real production workloads—without introducing a second database. Key features -Core concepts: embeddings, normalization, distance metrics, ANN trade-offs -Installing and configuring pgvector on self-managed, cloud, and Kubernetes setups -Schema patterns that separate hot vectors from large payloads and support multimodal data -Hybrid retrieval that combines pgvector with BM25 and structured filters in one SQL plan -End-to-end RAG: preprocessing, chunking, embedding, reranking, and grounded citations -Cross-modal search: text-to-image and image-to-text using unified schemas -Performance engineering: index tuning, parallelism, caching, materialized views, partitioning, and sharding -Reliability and cost control: observability, p50/p95 tracking, capacity planning -Security and compliance: row-level security, attribute-based access, redaction before egress, auditable tool use -CI/CD and migrations tailored to vector workloads (expand–backfill–contract, canary rollouts) -Future-ready patterns: Graph-RAG, multimodal fusion, and real-time retrieval This book is For; -Software engineers, -Data practitioners, SREs, and -Architects who know SQL or operate PostgreSQL and want to add AI features that are fast, accurate, and governed. No prior information-retrieval background is required; familiarity with basic Postgres administration and a scripting language (Python/TypeScript) is helpful but not mandatory. Bring meaning and structure together—ship AI search and RAG on the database you already trust. Open this book, run the queries, and turn PostgreSQL plus pgvector into a production-grade vector platform your users can rely on.
S/ 140.98
49% OFF
S/ 72.30
IMPORT EASILY
By purchasing this product you can deduct VAT with your RUT number
S/ 140.98
49% OFF
S/ 72.30
Hasta 6 cuotas sin intereses con BCP, BBVA y Diners
Llega en 5 a 10 días hábiles
con envío
Tienes garantía de entrega
Compra protegida
Disfruta de una experiencia de compra segura y confiable
![]()
Garantía de entrega
Con Tiendamia todas tus compras cuentan con Garantía de Entrega o devolución total de tu dinero.
Compras 100% seguras y garantizadas, para que pidas lo que sueñas y lo recibas del mundo a tu puerta.
Saber más.
Visa
Mastercard
American Express
