--- title: RAG chatbot accuracy: how data preparation beat model size description: A RAG chatbot built for a network of 25,000+ implant dentistry specialists achieved 98% accuracy and near-zero hallucinations using GPT-5 mini — a deliberately... canonical: https://daily.dev/posts/rag-chatbot-accuracy-how-data-preparation-beat-model-size-ukcoid0lx twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: RAG chatbot accuracy: how data preparation beat model size | daily.dev og:description: A RAG chatbot built for a network of 25,000+ implant dentistry specialists achieved 98% accuracy and near-zero hallucinations using GPT-5 mini — a deliberately... og:url: https://daily.dev/posts/rag-chatbot-accuracy-how-data-preparation-beat-model-size-ukcoid0lx og:image: https://api.daily.dev/og/posts/uKcoId0lx.png og:image:alt: RAG chatbot accuracy: how data preparation beat model size 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. # RAG chatbot accuracy: how data preparation beat model size **[Netguru](https://daily.dev/sources/netguru)** · 11 min read · 0 upvotes · 0 comments ## Summary A RAG chatbot built for a network of 25,000+ implant dentistry specialists achieved 98% accuracy and near-zero hallucinations using GPT-5 mini — a deliberately small model. The key insight: in RAG systems, accuracy is determined by data preparation and retrieval quality, not model size. The engineering effort went into rigorous source cleaning (handling clinical abbreviations, measurement formats, hyphenated breaks), empirically-tested chunk sizing (1,000–1,250 tokens to keep complete answers intact), strict prompt constraints (no fabrication, brand-neutral, scope-limited), and a golden dataset evaluation pipeline using Promptfoo and Langfuse. User testing with 24 specialists and a 31-member survey returned an NPS of 81, with 23 of 24 specialists clearly preferring it over general chatbots due to traceable, vetted citations. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Why Your Chatbot Feels Dumb — And How RAG Fixes It](https://daily.dev/posts/why-your-chatbot-feels-dumb-and-how-rag-fixes-it-vq4s1bzuc) · Medium · 0 upvotes · 0 comments - [Debugging Our Docs RAG, Part 1: Evaluating a Production RAG System](https://daily.dev/posts/debugging-our-docs-rag-part-1-evaluating-a-production-rag-system-nspolfjkp) · dltHub · 1 upvotes · 0 comments - [How to reduce AI hallucinations in e-commerce: a practical guide to RAG](https://daily.dev/posts/how-to-reduce-ai-hallucinations-in-e-commerce-a-practical-guide-to-rag-5cwo1bb30) · Netguru · 0 upvotes · 0 comments --- Tags: [#data-science](https://daily.dev/tags/data-science), [#llm](https://daily.dev/tags/llm), [#bots](https://daily.dev/tags/bots), [#rag](https://daily.dev/tags/rag), [#vector-search](https://daily.dev/tags/vector-search) [View this post on daily.dev](https://daily.dev/posts/rag-chatbot-accuracy-how-data-preparation-beat-model-size-ukcoid0lx) ```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":"RAG chatbot accuracy: how data preparation beat model size","url":"https://daily.dev/posts/rag-chatbot-accuracy-how-data-preparation-beat-model-size-ukcoid0lx","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/rag-chatbot-accuracy-how-data-preparation-beat-model-size-ukcoid0lx"},"datePublished":"2026-07-28T10:14:34.395Z","dateModified":"2026-07-28T10:15:51.656Z","description":"A RAG chatbot built for a network of 25,000+ implant dentistry specialists achieved 98% accuracy and near-zero hallucinations using GPT-5 mini — a deliberately...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bf655699ce6d3ab633dcd6952431bc2a?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bf655699ce6d3ab633dcd6952431bc2a?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Netguru","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":"Netguru","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/201e234294cb4132ab31418b7627dbab","url":"https://daily.dev/sources/netguru"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/rag-chatbot-accuracy-how-data-preparation-beat-model-size-ukcoid0lx","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"data-science,llm,bots,rag,vector-search","timeRequired":"PT11M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Netguru","item":"https://daily.dev/sources/netguru"},{"@type":"ListItem","position":3,"name":"RAG chatbot accuracy: how data preparation beat model size"}]} ```