--- title: OpenSearch Optimizations for Production RAG, Part 2:... description: A deep-dive into optimizing OpenSearch lexical retrieval for production RAG systems. Covers BM25 scoring mechanics (term frequency, IDF, length normalization),... canonical: https://daily.dev/posts/opensearch-optimizations-for-production-rag-part-2-lexical-retrieval-gplqckejb twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: OpenSearch Optimizations for Production RAG, Part 2: Lexical Retrieval | daily.dev og:description: A deep-dive into optimizing OpenSearch lexical retrieval for production RAG systems. Covers BM25 scoring mechanics (term frequency, IDF, length normalization),... og:url: https://daily.dev/posts/opensearch-optimizations-for-production-rag-part-2-lexical-retrieval-gplqckejb og:image: https://api.daily.dev/og/posts/GpLQckeJB.png og:image:alt: OpenSearch Optimizations for Production RAG, Part 2: Lexical Retrieval og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenSearch Optimizations for Production RAG, Part 2: Lexical Retrieval **[Medium](https://daily.dev/sources/medium_js)** · 28 min read · 0 upvotes · 0 comments ## Summary A deep-dive into optimizing OpenSearch lexical retrieval for production RAG systems. Covers BM25 scoring mechanics (term frequency, IDF, length normalization), when to use term vs. match queries, structuring document vs. structured corpora, and the copy_to combined-fields pattern for reducing multi-field fanout. Explains the analyzer pipeline in detail — tokenizers, token filters, stopwords, stemming — and contrasts fuzzy matching vs. edge-ngram tokenization for partial/prefix matching. Also covers hard filters vs. soft boosts vs. scoring functions, where preprocessing logic belongs (analyzer chain vs. application code), analyzer symmetry with search_analyzer overrides, multilingual handling, and BM25's known failure modes (synonyms, abbreviations, concept drift) that semantic retrieval must complement. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [RAG with Hybrid Search: How Does Keyword Search Work?](https://daily.dev/posts/rag-with-hybrid-search-how-does-keyword-search-work--fd4ni5gk5) · Towards Data Science · 0 upvotes · 0 comments - [Hybrid Search and Re-Ranking in Production RAG](https://daily.dev/posts/hybrid-search-and-re-ranking-in-production-rag-u32wjtkwm) · Towards Data Science · 0 upvotes · 0 comments - [Query rewriting for RAG: how to improve retrieval accuracy](https://daily.dev/posts/query-rewriting-for-rag-how-to-improve-retrieval-accuracy-zlvb3onbr) · Meilisearch · 0 upvotes · 0 comments --- Tags: [#nlp](https://daily.dev/tags/nlp), [#rag](https://daily.dev/tags/rag), [#opensearch](https://daily.dev/tags/opensearch), [#full-text-search](https://daily.dev/tags/full-text-search) [View this post on daily.dev](https://daily.dev/posts/opensearch-optimizations-for-production-rag-part-2-lexical-retrieval-gplqckejb) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"OpenSearch Optimizations for Production RAG, Part 2: Lexical Retrieval","url":"https://daily.dev/posts/opensearch-optimizations-for-production-rag-part-2-lexical-retrieval-gplqckejb","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/opensearch-optimizations-for-production-rag-part-2-lexical-retrieval-gplqckejb"},"datePublished":"2026-07-22T23:13:49.221Z","dateModified":"2026-07-22T23:14:18.787Z","description":"A deep-dive into optimizing OpenSearch lexical retrieval for production RAG systems. Covers BM25 scoring mechanics (term frequency, IDF, length normalization),...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/85ab0b7ab1dea76476ad7db01ea3b965?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/85ab0b7ab1dea76476ad7db01ea3b965?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/opensearch-optimizations-for-production-rag-part-2-lexical-retrieval-gplqckejb","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"nlp,rag,opensearch,full-text-search","timeRequired":"PT28M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"OpenSearch Optimizations for Production RAG, Part 2: Lexical Retrieval"}]} ```