--- title: "#bm25 articles | Hashnode" description: "Explore 18 articles tagged #bm25 on Hashnode. Tutorials, guides, and how-tos from the community." url: "https://hashnode.com/tag/bm25" --- Tag # #bm25 18 posts · 0 followers [Muhammad Tahir](https://hashnode.com/@mtahir27) · [Oct 11](https://hashnode.com/posts/hybrid-search-architecture-combining-bm25-keyword-search-with-dense-vector-embeddings/6acb4d0df9f50bf9fc84ab41) ### [Hybrid Search Architecture: Combining BM25 Keyword Search with Dense Vector Embeddings](https://mtdeveloper.hashnode.dev/hybrid-search-architecture-combining-bm25-keyword-search-with-dense-vector-embeddings?utm_source=hashnode&utm_medium=feed) This article was originally published on Muhammad Tahir's Portfolio. Introduction & Industry Context In the early wave of generative AI and Retrieval-Augmented Generation (RAG) deployments, engineerin 13 min read · [mtdeveloper.hashnode.dev](https://mtdeveloper.hashnode.dev/hybrid-search-architecture-combining-bm25-keyword-search-with-dense-vector-embeddings?utm_source=hashnode&utm_medium=feed) [market](https://hashnode.com/@eworldlive) · [Sep 28](https://hashnode.com/posts/bm25-vs-vector-vs-rrf-hybrid-on-85-chunks-vector-mrr-won-hybrid-did-not-always-win/6aba823f6bc54870afdb7bbe) ### [BM25 vs vector vs RRF hybrid on 85 chunks — vector MRR won (hybrid did not “always win”)](https://eworldlive.hashnode.dev/bm25-vs-vector-vs-rrf-hybrid-on-85-chunks-vector-mrr-won-hybrid-did-not-always-win?utm_source=hashnode&utm_medium=feed) Canonical: Hybrid BM25 + vector precision on eWorld.liveCheck date: 2026-09-26 PT · API spend $0 (CPU) Self-built 85-chunk Northline Hybrid Lab + 15 graded queries (5 keyword / 5 semantic / 5 mixed). 1 min read · [eworldlive.hashnode.dev](https://eworldlive.hashnode.dev/bm25-vs-vector-vs-rrf-hybrid-on-85-chunks-vector-mrr-won-hybrid-did-not-always-win?utm_source=hashnode&utm_medium=feed) [Internals Decoded](https://hashnode.com/@internalsdecoded) · [Sep 28](https://hashnode.com/posts/hybrid-search-and-reranking/6aba6f658842ae3e33d9ad7a) ### [Hybrid Search and Re-Ranking: The Cheapest Quality Win](https://internals-decoded.hashnode.dev/hybrid-search-and-reranking?utm_source=hashnode&utm_medium=feed) Keywords catch what vectors miss, and re-rankers fix the order. Most teams skip both. 13 min read · [internals-decoded.hashnode.dev](https://internals-decoded.hashnode.dev/hybrid-search-and-reranking?utm_source=hashnode&utm_medium=feed) [Viv Chaudhary](https://hashnode.com/@chuadharyviv) · [Sep 8](https://hashnode.com/posts/build-a-solid-rag-system-in-one-weekend-2026-edition/6aa04392e15956ac260ee923) ### [Build a Solid RAG System in One Weekend (2026 Edition)](https://truenorthbits.hashnode.dev/build-a-solid-rag-system-in-one-weekend-2026-edition?utm_source=hashnode&utm_medium=feed) The four decisions that actually determine whether your RAG system works - chunking, retrieval, reranking, and evaluation with the trade-offs the tutorials usually skip. 9 min read · [truenorthbits.hashnode.dev](https://truenorthbits.hashnode.dev/build-a-solid-rag-system-in-one-weekend-2026-edition?utm_source=hashnode&utm_medium=feed) [2](https://hashnode.com/posts/build-a-solid-rag-system-in-one-weekend-2026-edition/6aa04392e15956ac260ee923) [Aman Jain](https://hashnode.com/@aman454) · [Aug 2](https://hashnode.com/posts/how-rag-finds-the-right-evidence-dense-sparse-and-hybrid-retrieval/6a6fb32f63bf2279895b518f) ### [How RAG Finds the Right Evidence: Dense, Sparse, and Hybrid Retrieval](https://curious-pm.hashnode.dev/how-rag-finds-the-right-evidence-dense-sparse-and-hybrid-retrieval?utm_source=hashnode&utm_medium=feed) Comparing semantic search, BM25, Reciprocal Rank Fusion, evidence grading, and Corrective RAG 10 min read · [curious-pm.hashnode.dev](https://curious-pm.hashnode.dev/how-rag-finds-the-right-evidence-dense-sparse-and-hybrid-retrieval?utm_source=hashnode&utm_medium=feed) [Varun Vaibhav.S](https://hashnode.com/@theflighttech) · [Jul 8](https://hashnode.com/posts/how-i-automated-3-4-days-of-manual-work-at-l-t-using-python/6a4e34118b1bcd513a91935a) ### [How I Automated 3–4 Days of Manual Work at L&T Using Python](https://theflighttechlabs.hashnode.dev/how-i-automated-3-4-days-of-manual-work-at-l-t-using-python?utm_source=hashnode&utm_medium=feed) A PDF extraction pipeline built during my internship at L&T Construction — FAISS, BM25, PyMuPDF, and Python 6 min read · [theflighttechlabs.hashnode.dev](https://theflighttechlabs.hashnode.dev/how-i-automated-3-4-days-of-manual-work-at-l-t-using-python?utm_source=hashnode&utm_medium=feed) [Sukalyan Roy](https://hashnode.com/@Suka03) · [Jun 20](https://hashnode.com/posts/adding-rank-fusion-to-my-rag-retrieval-logic/6a362d027b82d052f9249dff) ### [Adding Rank Fusion to my RAG retrieval logic](https://sukalyanroy.hashnode.dev/adding-rank-fusion-to-my-rag-retrieval-logic?utm_source=hashnode&utm_medium=feed) More on Agentic Rags and Project updates 13 min read · [sukalyanroy.hashnode.dev](https://sukalyanroy.hashnode.dev/adding-rank-fusion-to-my-rag-retrieval-logic?utm_source=hashnode&utm_medium=feed) [Rahul Sehrawat](https://hashnode.com/@rahulseh1998) · [Apr 13](https://hashnode.com/posts/hybrid-search-beats-either-alone/69dc41765fb0eea3b1917bde) ### [Hybrid Search: BM25 + Vectors Beats Either Alone](https://ai-zero-to-hero.hashnode.dev/hybrid-search-beats-either-alone?utm_source=hashnode&utm_medium=feed) Dense retrieval misses keywords. Sparse retrieval misses semantics. Real RAG uses both, fuses the results, and ships a product that finds your product names, error codes, and edge cases. 11 min read · [ai-zero-to-hero.hashnode.dev](https://ai-zero-to-hero.hashnode.dev/hybrid-search-beats-either-alone?utm_source=hashnode&utm_medium=feed) [Elisé Baraka M.](https://hashnode.com/@ebmurha) · [Apr 7](https://hashnode.com/posts/building-a-rag-engine-part-1-retrieval-foundation/6a34afd4a52bc13ac97ad8b3) ### [Building a RAG Engine — Part 1: Retrieval Foundation](https://ebmurha.hashnode.dev/building-a-rag-engine-part-1-retrieval-foundation?utm_source=hashnode&utm_medium=feed) Building the search layer of a RAG engine with provenance, hybrid retrieval, grounded citations, multilingual handling, and evaluation. 14 min read · [ebmurha.hashnode.dev](https://ebmurha.hashnode.dev/building-a-rag-engine-part-1-retrieval-foundation?utm_source=hashnode&utm_medium=feed) [Ravi Mohta](https://hashnode.com/@ravimohta) · [Mar 17](https://hashnode.com/posts/in-store-retrieve-the-three-places-rag-quietly-fails-and-how-we-fixed-each-one/69b94746c22d3eeb8aa93763) ### [In, Store, Retrieve: The Three Places RAG Quietly Fails — And How We Fixed Each One](https://herald-ai.hashnode.dev/in-store-retrieve-the-three-places-rag-quietly-fails-and-how-we-fixed-each-one?utm_source=hashnode&utm_medium=feed) What five months of building a private AI document intelligence system taught me about retrieval quality, LLM reliability, and the gap between "it works" and "it works well" 18 min read · [herald-ai.hashnode.dev](https://herald-ai.hashnode.dev/in-store-retrieve-the-three-places-rag-quietly-fails-and-how-we-fixed-each-one?utm_source=hashnode&utm_medium=feed)