Akshay (@akshay_pachaar)RAG 시스템의 검색 성능이 5천 개 문서에서는 90%였지만 50만 개 문서로 확장하자 50%로 급락하는 사례를 제시하며, 동일한 임베딩 모델과 리트리버를 써도 문서 규모 증가가 성능 저하를 유발할 수 있음을 짚는다. 대규모 RAG 설계의 핵심 문제를 묻는 LLM 인터뷰 질문이다.https://x.com/akshay_pachaar/status/2052371239520629243#rag #llm #embeddings #retrieval #nlp
Related
Google accidentally leaves a Pixel 11a clue in its Phone appIt looks like Google is already hard at work on the Pixel 11...
Google accidentally leaves a Pixel 11a clue in its Phone appIt looks like Google is already hard at work on the Pixel 11a, even though the flagship Pixel 11 series hasn't launched ...
UI changed? 🚨Old automation: ❌ Breaks.#AI-powered automation: ✅ Adapts.Start Your #Free Trial & See AI-Powered Testing i...
UI changed? 🚨Old automation: ❌ Breaks.#AI-powered automation: ✅ Adapts.Start Your #Free Trial & See AI-Powered Testing in Action: https://www.testrigtechnologies.com/ai-automation-...
「NotebookLM」が「Gemini Notebook」に改名。コード実行も可能にhttps://pc.watch.impress.co.jp/docs/news/2126004.html#impress #市場 #AI #Gemini
「NotebookLM」が「Gemini Notebook」に改名。コード実行も可能にhttps://pc.watch.impress.co.jp/docs/news/2126004.html#impress #市場 #AI #Gemini