Fixed-length chunking requires no external services, yet semantic chunking absolutely needs an Embedding API — why? The core idea of semantic chunking is to split text at semantic boundaries. Determining whether "two pieces of text belong to the same topic" requires converting text into vectors and computing similarity — that's exactly what the Embedding API does. Dimension Fixed-Length / Recur
My Hugo blog was downloading 3.6 MB of JavaScript and 40 KB of external CSS on every page load. For a static blog with mostly text and a few diagrams, that was absurd. Here is how I fixed it. HTML: 86 KB JavaScript: 3.6 MB (Mermaid + KaTeX) CSS: 40 KB (KaTeX stylesheets) Problem: render-blocking scripts loaded on every page for math and diagrams Adding minifyOutput = true to hugo.toml shrunk HTML
Why Does Switching Embedding Models Make Such a Huge Difference? In the first four articles, we built the RAG pipeline, tuned parameters, and mastered chunking strategies. But there's one question we haven't dived into: After your documents are chunked, how do they become vectors? This process is called Embedding. It transforms human-readable text into machine-computable vectors. The choice of E