Back to Build Your Own Search Engine Workshops Build Your Own Search Engine Recording Recording Build Your Own Search Engine Chapters (11) [00:00] Intro and workshop goals [02:00] Preparing the environment [05:00] Basics of text search and information retrieval [10:00] TF-IDF vectorizer with sklearn [20:00] Query-document similarity and cosine similarity [30:00] Vectorizing all fields with boosting and filtering [40:00] TextSearch class [50:00] Embeddings and vector search [1:00:00] SVD and LSA for document embeddings [1:10:00] BERT embeddings [1:25:00] Practical tools and wrap-up Materials Workshop Code Repository code minsearch library (derived from this workshop) code Q&A RAG workshop (follow-up using search) code FAQ documents (workshop dataset) article