Semantic Search with Vector Embeddings

This course explores retrieval evaluation, search-quality optimisation, and semantic search applications for building effective retrieval systems. It focuses on techniques for measuring retrieval performance, diagnosing search failures, improving ranking quality, and understanding the transition from locally managed semantic search to vector databases. Through structured lessons and practical demonstrations, you will learn how relevance judgements and labelled evaluation sets support retrieval assessment, how Precision@k, Recall@k, and Mean Reciprocal Rank measure search quality, and how qualitative error analysis identifies retrieval weaknesses. You will also work with chunking strategies, query expansion and rewriting, cross-encoder reranking, and retrieval parameter tuning to improve search performance. The course progresses from retrieval evaluation and optimisation to building and deploying an interactive semantic search application, emphasizing systematic measurement, experimentation, and improvement. Rather than treating search quality as a fixed outcome, it focuses on evaluating retrieval behaviour, refining retrieval strategies, and recognising when locally managed indexes need to evolve into persistent vector database solutions. By the end of this course, you will be able to: - Evaluate retrieval quality using relevance judgements and standard retrieval metrics - Diagnose retrieval failures through quantitative and qualitative error analysis - Compare embedding models and chunking strategies using consistent evaluation methods - Improve search quality using query expansion, rewriting, and cross-encoder reranking - Tune top-k, chunk size, and similarity thresholds using evaluation results - Build and deploy an interactive semantic search application with Streamlit - Explain the purpose, architecture, and core data elements of vector databases This course is ideal for AI engineers, machine learning practitioners, developers, and professionals building semantic search and retrieval applications. A foundational understanding of Python, vector embeddings, similarity measures, and basic retrieval concepts is recommended; prior experience with retrieval evaluation, reranking, or vector databases is not required. Join us to learn how to evaluate, optimize, build, and deploy semantic search systems while developing the foundational knowledge needed to progress toward vector database-based retrieval solutions.

This course explores vector indexing and retrieval methods for building efficient search systems with embeddings. It focuses on techniques that move beyond exact vector comparison toward scalable indexing, semantic retrieval, keyword-based retrieval, and hybrid search. Through structured lessons and practical demonstrations, you will learn how k-nearest-neighbour search supports top-k retrieval, how FAISS indexes store and search vectors, and how dense retrieval uses embeddings for semantic matching. You will also work with sparse retrieval using BM25, combine dense and sparse rankings for hybrid search, and apply metadata-aware filtering to improve retrieval relevance. The course progresses from exact search foundations to reusable retrieval pipelines, emphasizing indexing, ranking, persistence, and document mapping. Rather than treating retrieval as a single search operation, it focuses on designing complete workflows that encode data, build indexes, retrieve relevant results, and maintain connections between vectors and source documents. By the end of this course, you will be able to: - Apply k-nearest-neighbour search and top-k retrieval for vector similarity - Build and operate FAISS indexes for efficient vector search - Implement dense semantic retrieval using Sentence Transformers - Build sparse retrieval systems using BM25-based keyword ranking - Combine dense and sparse rankings to create hybrid retrieval workflows - Design reusable retrieval pipelines with filtering, persistence, and document mapping This course is ideal for AI engineers, machine learning practitioners, developers, and professionals building semantic search and retrieval systems. A foundational understanding of Python, vector embeddings, and similarity measures is recommended; prior experience with FAISS or advanced retrieval techniques is not required. Join us to learn how to design and build efficient retrieval systems that combine vector search, keyword matching, hybrid ranking, and reusable retrieval pipelines.