Popular AI Software Stack Bundle

This book takes you from your first FastAPI endpoint to designing, building, testing, securing, and deploying professional production-grade systems. You will learn the framework through a realistic application that grows chapter by chapter, gaining hands-on experience with type hints, Pydantic validation, SQLAlchemy databases, authentication, WebSockets, caching, testing with pytest, Docker containerization, and production deployment behind Nginx. No prior web framework experience is required beyond basic Python knowledge.

This book is a comprehensive guide to PydanticAI, the Python agent framework that brings the rigor and developer experience of the Pydantic ecosystem to building production-grade generative AI applications. Whether you are a Python developer new to LLMs or an experienced AI practitioner looking for a framework that takes type safety seriously, this book will take you from your first agent to complex multi-agent systems with durable execution. Every chapter includes working code examples, real-world patterns, and practical exercises.

Retrieval-Augmented Generation has become the dominant architecture for production AI applications, and vector databases form its critical retrieval layer. This book takes you from the fundamentals of embeddings and similarity search through to advanced distributed deployments of Qdrant, the high-performance open-source vector database written in Rust. You will learn every facet of Qdrant's feature set: collections, points, payloads, HNSW indexing, quantization, hybrid search with dense and sparse vectors, metadata filtering, faceting, sharding, replication, security, monitoring, and scaling. Through detailed code examples in Python, JavaScript, Go, Java, C#, and Rust, you will build complete RAG pipelines integrated with LangChain, LlamaIndex, Haystack, and a wide range of embedding providers. This is not a tutorial collection; it is a comprehensive reference that explains the why behind every feature, the trade-offs between every configuration choice, and the production engineering practices that separate experimental prototypes from systems serving millions of queries per day.

This is a complete guide to administering PostgreSQL in production environments. Whether you are deploying your first database server or managing a fleet of high-availability clusters, this book walks you through everything from architecture internals and installation to security hardening, backup and recovery strategies, replication setups, performance tuning, and automated operations. It covers PostgreSQL 17 and 18 (the latest stable releases as of mid-2026) with practical examples, real-world configurations, hands-on labs, and production-tested best practices drawn from the official documentation and community expertise.