RAG簡介投影片：現況、原理、發展 / RAG Introduction Slides: Current Status, Mechanisms, and Development

這份投影片對檢索生成增強(Retrieval-Augmented Generation, RAG)的觀念作一個容易理解的介紹，也是「資訊檢索的AI革新：從資訊檢索到檢索增強生成」這篇的簡化版本。一般說到AI大家都會想到創造力、彷彿真人的表現，但RAG本質上更接近資訊檢索的問題。把它當作資料庫就很容易理解RAG的用途了。

This presentation provides an accessible introduction to the concept of Retrieval Augmented Generation (RAG), and is a simplified version of "The AI Revolution in Information Retrieval: From Information Retrieval to Retrieval-Augmented Generation". When people talk about AI, they often think of creativity and human-like performance, but RAG is essentially closer to the problems of information retrieval. Thinking of it as a database makes it easier to understand the purpose of RAG.

Fixed Short URL: https://l.pulipuli.info/24/nccu/rag 

希希助教的情人巧克力會送給最認真的同學喔！ / TA. Sissi's Valentine's Day Chocolates Will Go to the Most Hardworking Student!

你就是那位認真的同學嗎？

雜談：我可以只要RAG的「R」嗎？ / TALK: Can I Just Have the “R” in RAG?

很多人以為RAG可以取代搜尋引擎，但其實很多人要的功能只有「能用自然語言檢索」而已。

RAG應用方案：Google NotebookLM / RAG Application Solutions: Google NotebookLM

Google NotebookLM已經成為使用RAG的最基本入門產品了。它大幅拉高了RAG的競爭門檻。沒有做的比Google NotebookLM好的話，都沒資格出來賣錢了。這篇是我在介紹Google NotebookLM的投影片，供大家參考。

Google NotebookLM has become the most basic entry-level product for using RAG. It has significantly raised the competitive bar for RAG.  If it's not better than Google NotebookLM, it's not worth selling. These are my slides introducing Google NotebookLM for your reference.

公視地方新聞資料集 / PTS NEWS Local News Dataset

最近我因為研究需求蒐集了公視新聞網地方新聞的一些內容，並把資料整理表格資料集，提供給有需要的人使用。

Recently, for my research, I collected local news content from the PTS News website and organized the data into a tabular dataset, making it available for anyone who needs it.

只用CPU跑「小型」語言模型可行嗎？ / Is Running "Small" Language Models on CPUs Only Feasible?

很多人都說跑大型語言模型需要很高級的GPU，其實相對於門檻較高的大型語言模型，小型語言模型也一直在如火如荼地發展。最近我嘗試用12核CPU跟32GB的RAM來跑Gemma2:2B，意外地很順利呢。

Many people say that running large language models requires high-end GPUs. However, relative to the higher barrier to entry of large language models, small language models have also been developing rapidly. Recently, I experimented with running Gemma2:2B using a 12-core CPU and 32GB of RAM, and it went surprisingly smoothly.

RAG應用方案：SeaSalt.AI的SeaMeet、SeaChat / RAG Application Solutions: SeaSalt.AI's SeaMeet and SeaChat

我最近試用了SeaSalt公司底下的SeaMeet跟SeaChat，前者可以自動記錄並摘要 Google Meet會議內容，後者則是簡單建立聊天機器人。這篇就是我報告投影片的彙整，供大家參考。