https://aadityc91.github.io/#writing Articles on search, information retrieval, and RAG systems by Aaditya Chauhan. en-us Sat, 24 Oct 2026 03:29:31 +0000 https://www.infoq.com/articles/vector-search-hybrid-retrieval-rag/ https://www.infoq.com/articles/vector-search-hybrid-retrieval-rag/ Mon, 01 Jun 2026 00:00:00 +0000 Discussing the limitations of vector-only RAG pipelines and how combining BM25 with vector search via Reciprocal Rank Fusion enhances retrieval quality in production. https://hackernoon.com/your-embedding-model-will-deprecate-heres-what-to-do https://hackernoon.com/your-embedding-model-will-deprecate-heres-what-to-do Wed, 01 Apr 2026 00:00:00 +0000 Every embedding model gets deprecated eventually. A practitioner's guide to migrating a production RAG pipeline without breaking search quality or your budget. https://hackernoon.com/from-exact-knn-to-diskann-the-evolution-of-high-performance-vector-search https://hackernoon.com/from-exact-knn-to-diskann-the-evolution-of-high-performance-vector-search Sun, 01 Mar 2026 00:00:00 +0000 After years building search systems at hundreds of billions of records, here's what I learned about scaling vector search from kNN to HNSW to DiskANN. https://hackernoon.com/the-math-behind-the-match-building-production-search-for-people-names https://hackernoon.com/the-math-behind-the-match-building-production-search-for-people-names Sun, 01 Mar 2026 00:00:00 +0000 A deep dive into the algorithms and engineering tradeoffs behind building a people-name search system at production scale. https://hackernoon.com/ai-is-disrupting-everything-should-you-even-study-computer-science https://hackernoon.com/ai-is-disrupting-everything-should-you-even-study-computer-science Sun, 01 Feb 2026 00:00:00 +0000 Exploring whether a CS degree still makes sense in an era where AI is reshaping the software engineering profession.