1. From "Single Article Reading" to "Continuous Reading" A significant difference between my blog and traditional personal blogs is the presence of numerous highly continuous series of articles: such as the "Cloudflare Series," the "Awakening of the Voice" series, and also the series currently in which this article is titled "Building a Blog..."
1. From Media Servers to Film and Television Showcase Sites: For those who have amassed a large collection of film and television resources at home, there's probably a thought that's been on their minds to share their collection with others—of course, "share" here simply means looking at the posters, the scale of the collection, and what films or movies are included…
1. The starting point for intelligent blog recommendations: In the second article of this series (see: Adding a "Semantic Index" to your blog (Part 2): JSON Structure and Script Generation Implementation), we finally generated the crucial semantic-index using a Python script…
1. Introduction In the first article of this series (see article: Building a Lightweight Knowledge Index for Your Blog (Part 1): Structure Design and Construction Process), we have already summarized the entire knowledge indexing system into a clear structural model: from article retrieval and content organization to relationship building and result output…
1. Introduction Recently, I've been thinking about what new features can be added to the blog's structure, such as content structure indicators at the bottom of article pages (see the article: From Content to Structure: A Low-Cost Evolutionary Approach to Blog Development). However, there are still many more advanced capabilities, such as: automatic content recommendations…
1. From Experimentation to Fundamental Capability: In a previous article introducing RAG, I mentioned 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). In subsequent articles…
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. The Reason for the Third Optimization of the Blog's Active-Active Architecture A few days ago, I was preparing to perform a routine maintenance operation on the Mac mini node in the blog's active-active architecture: upgrading the Portainer version. However, a seemingly insignificant small problem ultimately caused the entire node…
1. Introduction I've been using a base-level VPS (US$39/year) from Racknerd's Chicago data center to build the "read-only node" in my blog's active-active architecture for about half a year now. Over this time, the VPS's overall stability has been quite good…
1. Introduction In previous articles, I wrote two about building your own Umami: one on setting up version 1.33.1 (see article: Docker Series: Building a Website Traffic Monitoring System Based on Umami), and the other on setting up version 2.11.3 (see article: Home Data Center…