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
Memory leaks in JavaScript don't announce themselves with an error. They show up as a heap that grows by 20MB per minute — invisible in a five-minute Lighthouse run, fatal in a six-hour production session. Why React apps leak: A useEffect that opens a WebSocket and never closes it on unmount. A setInterval without clearInterval in the cleanup return. A global Map that grows without bound. In each
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
Random 30–50ms freezes with no obvious long tasks in the Performance panel often have one root cause: the garbage collector. V8 pauses JavaScript execution to reclaim memory, and if your allocation rate is high enough, those pauses happen frequently — creating jank that shows up as a sawtooth pattern in the memory timeline rather than a spike in the flame chart. What this covers: How V8's generati