1 Why Do We Still Need “Guess What You Want” Because it overlaps with the newly added "Right Menu" feature on the article page, after some consideration, I decided to remove the "Guess What You Want" feature. However, this article is still kept as a reference example for implementing similar features. In previous articles (see: Building a "Lightweight Knowledge Index" for My Blog…

1 From “Single Reading” to “Continuous Reading” A major difference between my blog and traditional personal blogs is that there are many highly “continuous” series of articles: such as the “Cloudflare Series”, “Awakening of Voice” series, and also including the “Building a ‘..." series in which this article resides…

1 From Media Server to Media Showcase Site For people who have collected a large amount of movie and TV resources at home, they probably have more or less the idea of showing their collected resources to everyone—of course, “showing” here is simply looking at posters, looking at the scale of the collection, and seeing what movies and TV shows are collected…

1 The Starting Point of Blog Intelligent Recommendation At the end of the second article in this series (see: Adding a “Semantic Index” Layer to My Blog (II): Implementation of JSON Structure and Generation Script), we have already generated the key semantic-index.…

1 Introduction At the end of the first article in this series (see article: Building a “Lightweight Knowledge Index” for a Blog (Part 1): Structure Design and Build Process), we have already converged the entire knowledge index system into a clear structural model: from article acquisition, content organization, to relationship building and result output...

1 Introduction Recently, I have been thinking about what new features can be added to the blog structure, such as the content structure prompt added below the article page (see article: From Content to Structure: A Low-Cost Approach to Blog Context Evolution). However, there are still many further capabilities, such as: automatic content recommendation...

1 When Embedding Moves from Experiment to Basic Capability In the previous article introducing RAG, I introduced that the core tool for vectorizing segmented text is the "embedding model" (see article: Understanding RAG from Scratch (Part 1): Principles and Complete Process Analysis), and also in the subsequent...

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

1 The cause of the third optimization of the blog's active-active architecture: A few days ago, I was preparing to perform a very routine maintenance operation on the Mac mini node in the blog's active-active architecture: upgrading the version of Portainer. As a result, a seemingly insignificant small problem ended up putting the entire node...

1 Preface: I have been using an entry-level VPS ($39/year) from Racknerd's Chicago data center to build the “read-only node” in my blog's active-active architecture for almost half a year now. Over this half-year, the overall stability of the VPS has actually been quite good, at least...