Pathway 13: "I Want to Build RAG and Search Systems" (Search / Knowledge Engineer)

Target audience: Search engineers, knowledge engineers, and information retrieval professionals

Goal: Master the full retrieval pipeline from document processing through embedding, indexing, retrieval, reranking, and generation, with production evaluation methods.

Chapter Guide

• Focus Ch 01: Text Representation (foundations for embeddings) foundational text representations for embeddings
• Focus Ch 10: Working with LLM APIs API patterns for generation in RAG pipelines
• Focus Ch 11: Prompt Engineering prompt design for retrieval-augmented contexts
• Supplement Ch 12: Hybrid ML+LLM Architectures combine retrieval with ML ranking models
• Focus Ch 19: Embeddings and Vector Databases (all sections) core topic: embedding models and vector indexes
• Focus Ch 20: RAG (all sections; your core chapter) your core chapter: full RAG pipeline design
• Skim Ch 21: Conversational AI (conversational search) conversational search and follow-up queries
• Focus Ch 29: Evaluation (RAG evaluation methods) evaluate retrieval quality and answer accuracy
• Skim Ch 30: Observability and Monitoring monitor retrieval latency and cache hit rates
• Skim Ch 31: Production Engineering deploy and scale retrieval pipelines
• Optional Ch 34: Emerging Architectures new architectures that may change retrieval patterns
• Optional Ch 35: AI and Society data governance and societal context