“RAG ENGINEERING” é um livro de Faramarz Kowsari na área de inteligência artificial. Esta página de descoberta em português do Brasil organiza os metadados públicos para tornar mais fáceis de encontrar os temas, o público, o idioma real de publicação e os caminhos oficiais de leitura ou compra.
Os metadados públicos situam este título em inteligência artificial, ferramentas modernas de IA ou fluxos de trabalho baseados em prompts.
Idioma de publicação: inglês. Esta é uma página de orientação em português do Brasil. O livro é publicado em inglês; título, prévia e opções de compra no Google Books correspondem a essa edição.
“RAG ENGINEERING” é um livro de Faramarz Kowsari na área de inteligência artificial. Esta página de descoberta em português do Brasil organiza os metadados públicos para tornar mais fáceis de encontrar os temas, o público, o idioma real de publicação e os caminhos oficiais de leitura ou compra.
Os metadados públicos situam este título em inteligência artificial, ferramentas modernas de IA ou fluxos de trabalho baseados em prompts.
Temas em destaque
Retrieval-augmented generation (RAG)Evidence-based AI architectureSource authority and provenanceRAG requirements engineeringInformation retrieval fundamentalsBM25 and lexical retrievalDense retrievalEmbedding modelsVector searchApproximate nearest neighborsDocument parsingChunking strategiesDocument hierarchySemantic boundaries
Descrição pública original do livro
inglês
RAG ENGINEERING: From First Principles to Production is a graduate-level engineering reference for building retrieval-augmented generation systems that can justify their answers with inspectable evidence. Rather than treating RAG as a prompt plus a vector database, the book begins with the source contract of the application: what information is authoritative, which user may access it, how freshness and supersession are represented, when the system should abstain, and what evidence must be preserved so a response can later be audited. The opening parts establish information-retrieval fundamentals, lexical baselines, corpus provenance, document parsing, chunking, hierarchy, embeddings, indexes and metadata before advancing to dense retrieval and approximate nearest-neighbor search.
The search architecture section develops a progression from sparse and dense retrieval to hybrid search, fusion, reranking and query adaptation, while keeping ranking quality separate from generation quality. Context assembly, grounded answer construction, citation support, abstention, multi-turn and temporal questions, multi-hop retrieval, structured outputs and tool-facing RAG are treated as distinct engineering problems with their own failure modes. The book repeatedly rejects the idea that retrieval automatically eliminates hallucination: an outdated, unauthorized or merely topical passage can be retrieved perfectly and still produce an operationally wrong answer.
Evaluation is treated as a first-class scientific discipline. Dedicated chapters cover benchmark design, dataset validity, retrieval metrics, grounded-answer and citation evaluation, ablation studies, significance, replication, continuous evaluation and quality monitoring. Advanced sections extend the architecture to…
Para quem é este livro?
O público-alvo é baseado na descrição pública do livro. Para leitores brasileiros, é importante observar que a edição disponível está publicada em inglês.
For software architects, applied AI engineers, machine-learning engineers, retrieval engineers, master's students, researchers and technical teams who already know Python and basic statistics and want a rigorous bridge from RAG fundamentals to evaluation, security, deployment, observability and production operations.
Objetivos de aprendizagem publicados
inglês
Define when retrieval is actually justified and translate broad product requests into measurable source, access, freshness, abstention and evidence requirements.
Build and verify a lexical baseline before adding embeddings, and distinguish exact-identifier retrieval from semantic retrieval needs.
Prepare document corpora with explicit provenance, governance, parsing, chunking, hierarchy, metadata and lifecycle rules.
Compare sparse, dense and hybrid retrieval using independently defined relevance judgments rather than anecdotal examples.
Use fusion and reranking as measurable components whose added latency and maintenance cost must be justified by evaluation.
Separate retrieval success from generation faithfulness and test context assembly, answer construction, citations and abstention independently.
Design benchmarks that include answerable, unanswerable, conflicting, stale, near-duplicate and unauthorized cases instead of only easy demonstrations.
Apply retrieval metrics and grounded-answer evaluation correctly, and use ablations and held-out tests to locate regressions and avoid hindsight tuning.