{"width":"100%","blog_url":"https://techblog.ap-com.co.jp/","provider_name":"Hatena Blog","author_url":"https://blog.hatena.ne.jp/ywchen/","published":"2024-06-14 18:01:05","url":"https://techblog.ap-com.co.jp/entry/2024/06/14/180105","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Ftechblog.ap-com.co.jp%2Fentry%2F2024%2F06%2F14%2F180105\" title=\"Building a Production Scale, Totally Private, OSS RAG Pipeline with DBRX, Spark, and LanceDB - APC \u6280\u8853\u30d6\u30ed\u30b0\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","categories":["Databricks_EN","Databricks","DAIS2024"],"title":"Building a Production Scale, Totally Private, OSS RAG Pipeline with DBRX, Spark, and LanceDB","provider_url":"https://hatena.blog","height":"190","author_name":"ywchen","version":"1.0","blog_title":"APC \u6280\u8853\u30d6\u30ed\u30b0","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/a/apc_watanabe/20240607/20240607105046.png","description":"Preface In this session, the CEO of NCD, a data-centered organization, spoke extensively about his experiences in developing tools for data science and AI projects. The discussion was centered around their process of building the wholly private and open source RAG pipeline at a production scale. The\u2026","type":"rich"}