about this book
AI-Powered Search shows you how to build cutting-edge search engines that continuously learn from both your users and your content to drive more domain-aware and intelligent search. You’ll learn modern, data-science-driven search techniques, such as
- Semantic search using dense vector embeddings from foundation models
- Retrieval augmented generation (RAG)
- Question answering and summarization combining search and large language models (LLMs)
- Fine-tuning Transformer-based LLMs
- Personalized search based on user signals and vector embeddings
- Collecting user behavioral signals and building signals-boosting models
- Semantic knowledge graphs for domain-specific learning
- Multimodal search (hybrid queries on text, image, and other types)
- Implementing generalizable machine-learned ranking models (learning to rank)
- Building click models to automate machine-learned ranking
- Vector search optimization techniques like ANN search, quantization, representation learning, and bi-encoders versus cross-encoders
- Generative search, hybrid search, and the search frontier