1. Introduction In a previous article (see: Home Data Center Series: Understanding RAG from Scratch (Part 1): Principles and Complete Process Analysis), I introduced the theoretical five-step process of RAG: "Segmentation → Vectorization → Vector Storage → Retrieval → Answer Generation"; subsequently…

1 Introduction: In my previous articles on RAGs and knowledge bases, the word vector frequently appears. It can be said that vector is one of the core concepts of AI. Anyone who has had some exposure to AI is likely familiar with this term. In fact, even without AI, everyone is familiar with the concept of vector...

1. The Crisis and Value of Personal Blogs Today. Once upon a time, personal blogs (hereafter referred to as blogs) were a beautiful form of writing on the internet. It was an era when everyone was willing to write and share their experiences: programmers recorded their study notes, travelers wrote down their travel stories, and food lovers…

1 Introduction In the previous article, I reviewed the core concepts and processes of RAG (see the article: Understanding RAG from Scratch in the Home Data Center Series (Part 1): Principles and Complete Process Analysis). However, that was still theoretical, just talk. To truly make RAG work, it must...

1 Introduction I've always had an idea—to build a chatbot for my blog that can understand the content of my blog posts and intelligently answer visitors' questions. While this requirement might seem simple at first glance, its actual implementation involves a series of unfamiliar and complex concepts: such as...

1 Introduction: My usual AI usage habits have always been quite simple—my priority has always been: 1. ChatGPT official client (I use the free quota, as I don't use it much anyway, and if I occasionally exceed the quota, I just wait a few hours as a forced break); 2. LobeChat...

1. Preface: It's been a while since I've updated the AI learning map on my blog. It's not that my interest in AI has waned; quite the contrary. Many ideas and explorations have already taken shape in my mind. The real reason I've stopped is actually very simple: many practical scenarios ultimately involve the "paid AI" model.

Preface In addition to Diffusion Bee introduced in the previous article, there is another free local AI image generation tool suitable for running on M series Macs: Draw Things. Introduction to Draw Things and installation software introduction...

Preface Originally, I wanted to write a tutorial on deploying "Stable Diffusion" on Mac, but I happened to see Diffusion Bee, which is actually based on "Stable Diffusion" but is very friendly to friends with no basic knowledge...

Preface In the previous article, I have written about how to run the llama3.2 3B model locally based on Ollama and call it using Lobechat (see article: Home Data Center Series Build Private AI: Build an Open Source Big Language Locally Based on Ollama...