「住友電工がグループ全社規模のRAG基盤を構築~QuickSolution®の高精度検索×生成AI連携で社内ナレッジを有効活用~」というプレスリリースがありました。 住友電工はグループ全社規模の大容量RAG基盤を約2週間という短期間で構築しました。必要な情報を検索・抽出し生成AIに連携する RAG技術を用いて、ファイルサーバなどに保存されている数百TB規模の社内情報から高精度に質問応答する機能を提供していて、住友電工グループ約29万人が対話形式で社内情報を収集できるようになり、ナレッジの有効活用にともなう生産性の向上やDX推進が可能になったということです。 当然のことですが、DeepResearhでは、WEB上のオープン情報しか収集しないため、その限界には注意する必要があります。 住友電工がグループ全社規模のRAG基盤を構築 https://www.sei-info.co.jp/quicksolution/news/news-qs20250307/ Sumitomo Electric Builds Group-wide RAG Infrastructure A press release titled "Sumitomo Electric Builds Group-wide RAG Infrastructure: Leveraging High-Precision QuickSolution® Search Integrated with Generative AI for Effective Internal Knowledge Utilization" was announced. Sumitomo Electric constructed a large-capacity, company-wide Retrieval-Augmented Generation (RAG) infrastructure in approximately two weeks. Utilizing RAG technology—which searches, extracts, and feeds relevant data into generative AI—the system provides high-precision question-and-answer functionality from internal company information stored across file servers, totaling hundreds of terabytes. This enables roughly 290,000 employees within the Sumitomo Electric Group to interactively access internal knowledge, improving productivity and accelerating digital transformation (DX) through effective knowledge utilization. It should be noted, however, that DeepResearch only collects publicly available information from the web, and its limitations must be considered accordingly. Your browser does not support viewing this document. Click here to download the document. Your browser does not support viewing this document. Click here to download the document. Your browser does not support viewing this document. Click here to download the document. Your browser does not support viewing this document. Click here to download the document.
0 Comments
Leave a Reply. |
著者萬秀憲 アーカイブ
March 2025
カテゴリー |