Mini Search Engine was a from-scratch retrieval system that covered the mechanics behind search rather than hiding them behind a framework. The project implemented index construction, compressed postings, ranking functions, WAND-style acceleration, LSI with FAISS, and evaluation metrics so retrieval quality and efficiency could be compared in one pipeline.
Information Retrieval / 2026
Mini Search Engine
Built a complete mini search engine using Python, NumPy, SciPy, and FAISS, covering indexing, compression, TF-IDF, BM25 variants, WAND optimization, LSI retrieval, approximate nearest-neighbor search, and query evaluation.