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
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
I am a first-year CS student and I recently made a decision that most people around me think is unnecessary — I am building a relational database storage engine from scratch in raw C++, with zero STL dependency. No std::vector. No std::string. No iostream. Nothing. The Problem With How I Was Learning For a long time I was writing code that worked but I had no idea why it worked. I used abstraction